# How to integrate Circleci MCP with LlamaIndex

```json
{
  "title": "How to integrate Circleci MCP with LlamaIndex",
  "toolkit": "Circleci",
  "toolkit_slug": "circleci",
  "framework": "LlamaIndex",
  "framework_slug": "llama-index",
  "url": "https://composio.dev/toolkits/circleci/framework/llama-index",
  "markdown_url": "https://composio.dev/toolkits/circleci/framework/llama-index.md",
  "updated_at": "2026-05-12T10:06:15.190Z"
}
```

## Introduction

This guide walks you through connecting Circleci to LlamaIndex using the Composio tool router. By the end, you'll have a working Circleci agent that can trigger a new pipeline on main branch, list all pipelines for backend service, get test results from last successful build through natural language commands.
This guide will help you understand how to give your LlamaIndex agent real control over a Circleci account through Composio's Circleci MCP server.
Before we dive in, let's take a quick look at the key ideas and tools involved.

## Also integrate Circleci with

- [OpenAI Agents SDK](https://composio.dev/toolkits/circleci/framework/open-ai-agents-sdk)
- [Claude Agent SDK](https://composio.dev/toolkits/circleci/framework/claude-agents-sdk)
- [Claude Code](https://composio.dev/toolkits/circleci/framework/claude-code)
- [Claude Cowork](https://composio.dev/toolkits/circleci/framework/claude-cowork)
- [Codex](https://composio.dev/toolkits/circleci/framework/codex)
- [OpenClaw](https://composio.dev/toolkits/circleci/framework/openclaw)
- [Hermes](https://composio.dev/toolkits/circleci/framework/hermes-agent)
- [CLI](https://composio.dev/toolkits/circleci/framework/cli)
- [Google ADK](https://composio.dev/toolkits/circleci/framework/google-adk)
- [LangChain](https://composio.dev/toolkits/circleci/framework/langchain)
- [Vercel AI SDK](https://composio.dev/toolkits/circleci/framework/ai-sdk)
- [Mastra AI](https://composio.dev/toolkits/circleci/framework/mastra-ai)
- [CrewAI](https://composio.dev/toolkits/circleci/framework/crew-ai)

## TL;DR

Here's what you'll learn:
- Set your OpenAI and Composio API keys
- Install LlamaIndex and Composio packages
- Create a Composio Tool Router session for Circleci
- Connect LlamaIndex to the Circleci MCP server
- Build a Circleci-powered agent using LlamaIndex
- Interact with Circleci through natural language

## What is LlamaIndex?

LlamaIndex is a data framework for building LLM applications. It provides tools for connecting LLMs to external data sources and services through agents and tools.
Key features include:
- ReAct Agent: Reasoning and acting pattern for tool-using agents
- MCP Tools: Native support for Model Context Protocol
- Context Management: Maintain conversation context across interactions
- Async Support: Built for async/await patterns

## What is the Circleci MCP server, and what's possible with it?

The Circleci MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Circleci account. It provides structured and secure access to your Circleci projects and pipelines, so your agent can trigger builds, fetch job artifacts, monitor workflows, and analyze test results on your behalf.
- Automated pipeline triggering and management: Let your agent start new builds for specific branches or tags, enabling continuous integration workflows without manual intervention.
- Workflow and job status monitoring: Ask your agent to fetch detailed information about jobs and workflows, including status, timing, and execution environment, to stay on top of your CI/CD processes.
- Artifact and test result retrieval: Have the agent collect job artifacts or extract comprehensive test metadata and failure messages for easier debugging and reporting.
- Pipeline and runner insights: Get your agent to list all pipelines for a project or enumerate available self-hosted runners, making it simple to manage and audit your Circleci resources.
- User and configuration access: Retrieve user profile details or fetch pipeline YAML configurations as needed for documentation, troubleshooting, or workflow optimization.

## Supported Tools

| Tool slug | Name | Description |
|---|---|---|
| `CIRCLECI_CREATE_CONTEXT` | Create Context | Tool to create a new context in CircleCI. Contexts are used to secure and share environment variables across projects. Use this when you need to set up a new environment configuration for your CircleCI workflows. |
| `CIRCLECI_CREATE_CONTEXT_GRAPHQL` | Create Context (GraphQL) | Tool to create a new CircleCI context using the GraphQL API. Use when you need to create a context for storing environment variables in CircleCI. The mutation returns error information if creation fails or payload data if successful. |
| `CIRCLECI_CREATE_CONTEXT_RESTRICTION` | Create Context Restriction | Tool to create a context restriction in CircleCI. Use when you need to limit context access based on project, expression rules, or group membership. |
| `CIRCLECI_CREATE_ORGANIZATION_ORB_ALLOWLIST` | Create Organization Orb Allowlist | Tool to create a new URL Orb allow-list entry for an organization. Use when you need to allow URL-based orb references from specific URL prefixes in CircleCI pipelines for an organization. |
| `CIRCLECI_CREATE_ORGANIZATION_PROJECT` | Create Organization Project | Tool to create a new project within a CircleCI organization. Use when you need to programmatically set up a new project for CI/CD automation. |
| `CIRCLECI_CREATE_ORG_GROUP` | Create Organization Group | Tool to create a group in an organization. Use when you need to organize users within a CircleCI organization by creating logical groups. |
| `CIRCLECI_CREATE_PROJECT_ENV_VAR` | Create Project Environment Variable | Tool to create a new environment variable for a CircleCI project. Use when you need to add a new environment variable that will be available in project builds. |
| `CIRCLECI_CREATE_USAGE_EXPORT_JOB` | Create Usage Export Job | Tool to create a usage export job for a CircleCI organization. Use when you need to export usage data for billing, analysis, or reporting purposes. Rate limited to 10 queries per hour. Maximum date window is 32 days, with up to 13 months of historical data available. |
| `CIRCLECI_DELETE_CONTEXT_GRAPHQL` | Delete Context (GraphQL) | Tool to delete a CircleCI context by its UUID using GraphQL API. Use when you need to permanently remove a context from your CircleCI organization. This action is irreversible and will delete all environment variables associated with the context. |
| `CIRCLECI_DELETE_CONTEXT_RESTRICTION` | Delete Context Restriction | Tool to delete a context restriction by its ID. Use when you need to remove a specific restriction from a CircleCI context. |
| `CIRCLECI_DELETE_NAMESPACE` | Delete Namespace and Related Orbs | Tool to delete a CircleCI registry namespace and all its associated orbs. Use when you need to permanently remove a namespace from the registry. This is a destructive operation that cannot be undone. |
| `CIRCLECI_DELETE_NAMESPACE_ALIAS` | Delete Namespace Alias | Tool to remove a namespace alias by name in CircleCI. Use when you need to delete an existing namespace alias that is no longer needed. The mutation returns a boolean indicating success and any errors that occurred during deletion. |
| `CIRCLECI_DELETE_ORGANIZATION_ORB_ALLOWLIST` | Delete Organization Orb Allowlist Entry | Tool to remove an entry from the organization's URL orb allow-list. Use when you need to revoke access to a previously allowed orb URL. |
| `CIRCLECI_DELETE_ORG_GROUP` | Delete Organization Group | Tool to delete a group from a CircleCI organization. Use when you need to remove a group permanently from the organization. |
| `CIRCLECI_DELETE_PROJECT` | Delete Project | Tool to delete a CircleCI project and its settings. Use when you need to permanently remove a project from CircleCI. This action cannot be undone. |
| `CIRCLECI_DELETE_PROJECT_ENV_VAR` | Delete Project Environment Variable | Tool to delete an environment variable from a CircleCI project. Use when you need to remove an existing environment variable by name. |
| `CIRCLECI_GET_CONTEXT` | Get Context | Tool to retrieve a context by its unique ID. Use when you need details about a specific CircleCI context. |
| `CIRCLECI_GET_CURRENT_USER` | Get Current User | Tool to retrieve information about the currently authenticated user. Use when you need details about the signed-in user's profile, permissions, and account settings. |
| `CIRCLECI_GET_FLAKY_TESTS` | Get Flaky Tests | Tool to get flaky tests for a project. Use when you need to identify tests that passed and failed in the same commit. Branch-agnostic insights help improve test reliability. |
| `CIRCLECI_GET_JOB_ARTIFACTS` | Get Job Artifacts | Retrieves artifacts (output files like test results, logs, build binaries, reports) produced by a CircleCI job. Use this when you need to access files generated during a job's execution, such as test reports, coverage data, compiled binaries, or deployment artifacts. Returns download URLs for each artifact. Note: Jobs may produce zero artifacts if none were explicitly stored using 'store_artifacts' in the config. |
| `CIRCLECI_GET_JOB_DETAILS` | Get Job Details | Tool to fetch details of a specific job within a project. Use when you need status, timing, and executor information for a CircleCI job by its number. |
| `CIRCLECI_GET_ORB_DETAILS` | Get Orb Details | Tool to query detailed information about a CircleCI orb using the GraphQL API. Use when you need to retrieve orb metadata, versions, usage statistics, or namespace details. |
| `CIRCLECI_GET_ORB_VERSION` | Get Orb Version | Tool to retrieve detailed information about a specific CircleCI orb version via GraphQL. Use when you need orb source code, version history, usage statistics, or metadata for a specific orb version. |
| `CIRCLECI_GET_ORGANIZATION` | Get Organization | Tool to retrieve organization details from CircleCI using GraphQL query. Use when you need organization information by ID or by name and VCS type. |
| `CIRCLECI_GET_ORGANIZATION_GROUP` | Get Organization Group | Tool to retrieve a group in an organization. Use when you need to get details about a specific group within a CircleCI organization. |
| `CIRCLECI_GET_PIPELINE_CONFIG` | Get Pipeline Config | Tool to fetch pipeline configuration by ID. Use when you need the source or compiled YAML of a specific pipeline. |
| `CIRCLECI_GET_PIPELINE_DEFINITION` | Get Pipeline Definition | Tool to retrieve a pipeline definition by project and definition ID. Use when you need details about a specific pipeline definition's configuration, sources, and metadata. |
| `CIRCLECI_GET_PROJECT` | Get Project | Tool to retrieve a CircleCI project by its slug. Use when you need project details such as organization info, project ID, or VCS configuration. |
| `CIRCLECI_GET_PROJECT_WORKFLOWS` | Get Project Workflows | Tool to get summary metrics for all workflows of a project. Use when you need to analyze performance across all workflows, including success rates, duration metrics, throughput, and credits used. |
| `CIRCLECI_GET_TEST_METADATA` | Get Test Metadata | Tool to fetch test metadata for a specific job. Use when you need detailed test results, run times, and failure messages after a job completes. |
| `CIRCLECI_GET_USAGE_EXPORT_JOB` | Get Usage Export Job | Tool to retrieve a usage export job by organization ID and job ID. Use when you need to check the status or download URLs of a usage export job. |
| `CIRCLECI_GET_USER_INFORMATION` | Get User Information | Tool to retrieve information about a CircleCI user by their unique ID. Use when you need user profile details after obtaining the user ID. |
| `CIRCLECI_GET_WORKFLOW_SUMMARY` | Get Workflow Summary | Tool to get metrics and trends for a workflow. Use when you need workflow performance insights including success rates, duration metrics, and trends over time. |
| `CIRCLECI_LIST_CONTEXT_ENV_VARS` | List Context Environment Variables | Tool to list all environment variables for a specific context. Use when you need to retrieve or paginate through environment variables stored in a CircleCI context. |
| `CIRCLECI_LIST_INSIGHTS_BRANCHES` | List Insights Branches | Tool to get all branches for a project from CircleCI Insights. Use when you need to retrieve the list of branches that have workflow runs in the project. |
| `CIRCLECI_LIST_INSIGHTS_SUMMARY` | List Insights Summary | Tool to get summary metrics with trends for the entire organization and for each project. Use when you need organization-wide performance analytics across all projects. |
| `CIRCLECI_LIST_NAMESPACE_ORBS` | List Namespace Orbs | Tool to list orbs in a CircleCI registry namespace with pagination support. Use when you need to browse available orbs in a namespace, filter by visibility (public/private), or retrieve orb statistics. Returns up to 20 orbs per page with cursor-based pagination. |
| `CIRCLECI_LIST_ORB_CATEGORIES` | List Orb Categories | Tool to retrieve all CircleCI orb categories with pagination support. Use when you need to list available categories for orb classification. Returns up to 20 categories per page with cursor-based pagination. |
| `CIRCLECI_LIST_ORBS` | List Orbs | Tool to list CircleCI orbs with pagination support via GraphQL API. Use when you need to browse available orbs, filter by certification status, or discover orbs with their usage statistics. Returns up to 20 orbs per page with cursor-based pagination. |
| `CIRCLECI_LIST_ORGANIZATION_GROUPS` | List Organization Groups | Tool to list all groups in a CircleCI organization. Use when you need to retrieve groups for an organization to manage permissions or view group memberships. |
| `CIRCLECI_LIST_PAGES_SUMMARY` | List Pages Summary | Tool to get summary metrics and trends for a project across its workflows and branches. Use when you need to analyze project performance, track success rates, throughput, credits usage, and duration trends. |
| `CIRCLECI_LIST_PIPELINE_DEFINITIONS` | List Pipeline Definitions | Tool to list all pipeline definitions for a specific project. Use when you need to retrieve available pipeline configurations for a project. |
| `CIRCLECI_LIST_PIPELINES` | List Pipelines | Tool to get a list of pipelines for an organization. Use when you need to retrieve pipelines across multiple projects or for a specific organization. |
| `CIRCLECI_LIST_PIPELINES_FOR_PROJECT` | List Pipelines for Project | Tool to list all pipelines for a specific project. Use when you need to retrieve the pipelines for a project (e.g., to display recent runs on a dashboard). |
| `CIRCLECI_LIST_PROJECT_ENV_VARS` | List Project Environment Variables | Tool to list all environment variables for a CircleCI project. Use when you need to retrieve project-level environment variables. Note that values are masked for security. |
| `CIRCLECI_LIST_PROJECT_SCHEDULES` | List Project Schedules | Tool to list all schedules for a specific project. Use when you need to retrieve scheduled pipeline triggers for a project. |
| `CIRCLECI_LIST_SELF_HOSTED_RUNNERS` | List Self-Hosted Runners | List self-hosted runners in CircleCI. Use this to retrieve information about your organization's self-hosted runners, optionally filtered by namespace or resource class. Useful for monitoring runner availability and status. |
| `CIRCLECI_LIST_USER_COLLABORATIONS` | List User Collaborations | Tool to retrieve organizations where the authenticated user has access. Use when you need to list all organizations a user can collaborate on. |
| `CIRCLECI_LIST_WORKFLOWS_BY_PIPELINE_ID` | List Workflows by Pipeline ID | Tool to list all workflows associated with a specific pipeline. Use when you need to fetch or paginate through workflows by pipeline ID. |
| `CIRCLECI_LIST_WORKFLOWS_JOBS_WORKFLOWS` | List Workflows Jobs Workflows | Tool to get summary metrics for a project workflow's jobs. Use when you need performance analytics like success rates, duration statistics, and credit usage for jobs in a specific workflow. |
| `CIRCLECI_LIST_WORKFLOWS_TEST_METRICS` | List Workflows Test Metrics | Tool to get test metrics for a project's workflows. Use when you need to analyze test performance, identify flaky tests, or find the slowest tests in a workflow. |
| `CIRCLECI_QUERY_CONTEXT` | Query Context | Tool to retrieve a CircleCI context by its UUID using GraphQL API. Use when you need to fetch context details including ID, name, and creation time. Returns null in the data field if the context ID does not exist. |
| `CIRCLECI_QUERY_NAMESPACE_EXISTS` | Query Namespace Exists | Tool to determine if a namespace exists in the CircleCI registry. Use when you need to verify namespace existence before performing operations. Returns a boolean indicating whether the namespace exists. |
| `CIRCLECI_QUERY_ORB_CATEGORY_ID` | Query Orb Category ID | Tool to fetch the unique category ID for a CircleCI orb category by its name. Use when you need to categorize orbs or query category-specific information. Returns null in the data field if the category name does not exist. |
| `CIRCLECI_QUERY_ORB_EXISTS` | Query Orb Exists | Tool to check if an orb exists in CircleCI registry and retrieve its privacy status. Use when you need to verify orb existence or check if an orb is private/public. Returns null in the data.orb field if the orb does not exist. |
| `CIRCLECI_QUERY_ORB_ID` | Query Orb ID | Tool to fetch an orb's ID and optionally its namespace ID by orb name. Use when you need to query orb identifiers for CircleCI orbs. The name parameter should be the full orb reference (namespace/orbname). Optionally provide the namespace parameter to also retrieve the namespace ID in the same call. |
| `CIRCLECI_QUERY_ORB_LATEST_VERSION` | Query Orb Latest Version | Tool to fetch the latest published version of a CircleCI orb. Use when you need to check the most recent version number of an orb for dependency management or updates. Returns null in the data field if the orb does not exist. |
| `CIRCLECI_QUERY_ORB_SOURCE` | Query Orb Source | Tool to retrieve source code of a specific CircleCI orb version via GraphQL. Use when you need to access the YAML configuration or inspect the implementation of an orb version. Returns null if the orb version reference does not exist. |
| `CIRCLECI_QUERY_PLAN_METRICS` | Query Plan Metrics | Tool to query plan metrics including credit usage by project and organization for a date range. Use when you need to analyze credit consumption, compute time usage, or project-level metrics for an organization. |
| `CIRCLECI_REMOVE_CONTEXT_ENV_VAR_GRAPHQL` | Remove Context Environment Variable (GraphQL) | Tool to remove an environment variable from a CircleCI context using GraphQL API. Use when you need to delete a context-level environment variable by its name. |
| `CIRCLECI_RENAME_NAMESPACE` | Rename Namespace | Tool to rename a CircleCI namespace by its UUID identifier. Use when you need to change the name of an existing namespace. Returns the renamed namespace ID on success, or errors if the operation fails. |
| `CIRCLECI_STORE_ENVIRONMENT_VARIABLE` | Store Environment Variable | Tool to store an environment variable in a CircleCI context using GraphQL mutation. Use when you need to add or update an environment variable within a specific context. |
| `CIRCLECI_TRIGGER_PIPELINE` | Trigger Pipeline | Triggers a new CI/CD pipeline run for a specified CircleCI project. Use this tool to programmatically start a build on a specific branch or tag, optionally passing custom pipeline parameters for conditional workflow execution. Requires write access to the project. |
| `CIRCLECI_UPSERT_CONTEXT_ENV_VAR` | Upsert Context Environment Variable | Tool to add or update an environment variable in a CircleCI context. Use when you need to set or modify context-level environment variables for your CircleCI projects. |
| `CIRCLECI_VALIDATE_ORB_CONFIG` | Validate Orb Config | Tool to validate CircleCI orb YAML configuration using the orbConfig GraphQL query. Use when you need to verify that an orb definition is syntactically correct before publishing or using it. Returns validation status, any errors found, and the processed YAML output. |

## Supported Triggers

None listed.

## Creating MCP Server - Stand-alone vs Composio SDK

The Circleci MCP server is an implementation of the Model Context Protocol that connects your AI agent to Circleci. It provides structured and secure access so your agent can perform Circleci operations on your behalf through a secure, permission-based interface.
With Composio's managed implementation, you don't have to create your own developer app. For production, if you're building an end product, we recommend using your own credentials. The managed server helps you prototype fast and go from 0-1 faster.

## Step-by-step Guide

### 1. Prerequisites

Before you begin, make sure you have:
- Python 3.8/Node 16 or higher installed
- A Composio account with the API key
- An OpenAI API key
- A Circleci account and project
- Basic familiarity with async Python/Typescript

### 1. Getting API Keys for OpenAI, Composio, and Circleci

No description provided.

### 2. Installing dependencies

No description provided.
```python
pip install composio-llamaindex llama-index llama-index-llms-openai llama-index-tools-mcp python-dotenv
```

```typescript
npm install @composio/llamaindex @llamaindex/openai @llamaindex/tools @llamaindex/workflow dotenv
```

### 3. Set environment variables

Create a .env file in your project root:
These credentials will be used to:
- Authenticate with OpenAI's GPT-5 model
- Connect to Composio's Tool Router
- Identify your Composio user session for Circleci access
```bash
OPENAI_API_KEY=your-openai-api-key
COMPOSIO_API_KEY=your-composio-api-key
COMPOSIO_USER_ID=your-user-id
```

### 4. Import modules

No description provided.
```python
import asyncio
import os
import dotenv

from composio import Composio
from composio_llamaindex import LlamaIndexProvider
from llama_index.core.agent.workflow import ReActAgent
from llama_index.core.workflow import Context
from llama_index.llms.openai import OpenAI
from llama_index.tools.mcp import BasicMCPClient, McpToolSpec

dotenv.load_dotenv()
```

```typescript
import "dotenv/config";
import readline from "node:readline/promises";
import { stdin as input, stdout as output } from "node:process";

import { Composio } from "@composio/core";

import { mcp } from "@llamaindex/tools";
import { agent as createAgent } from "@llamaindex/workflow";
import { openai } from "@llamaindex/openai";

dotenv.config();
```

### 5. Load environment variables and initialize Composio

No description provided.
```python
OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY")
COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID")

if not OPENAI_API_KEY:
    raise ValueError("OPENAI_API_KEY is not set in the environment")
if not COMPOSIO_API_KEY:
    raise ValueError("COMPOSIO_API_KEY is not set in the environment")
if not COMPOSIO_USER_ID:
    raise ValueError("COMPOSIO_USER_ID is not set in the environment")
```

```typescript
const OPENAI_API_KEY = process.env.OPENAI_API_KEY;
const COMPOSIO_API_KEY = process.env.COMPOSIO_API_KEY;
const COMPOSIO_USER_ID = process.env.COMPOSIO_USER_ID;

if (!OPENAI_API_KEY) throw new Error("OPENAI_API_KEY is not set");
if (!COMPOSIO_API_KEY) throw new Error("COMPOSIO_API_KEY is not set");
if (!COMPOSIO_USER_ID) throw new Error("COMPOSIO_USER_ID is not set");
```

### 6. Create a Tool Router session and build the agent function

What's happening here:
- We create a Composio client using your API key and configure it with the LlamaIndex provider
- We then create a tool router MCP session for your user, specifying the toolkits we want to use (in this case, circleci)
- The session returns an MCP HTTP endpoint URL that acts as a gateway to all your configured tools
- LlamaIndex will connect to this endpoint to dynamically discover and use the available Circleci tools.
- The MCP tools are mapped to LlamaIndex-compatible tools and plug them into the Agent.
```python
async def build_agent() -> ReActAgent:
    composio_client = Composio(
        api_key=COMPOSIO_API_KEY,
        provider=LlamaIndexProvider(),
    )

    session = composio_client.create(
        user_id=COMPOSIO_USER_ID,
        toolkits=["circleci"],
    )

    mcp_url = session.mcp.url
    print(f"Composio MCP URL: {mcp_url}")

    mcp_client = BasicMCPClient(mcp_url, headers={"x-api-key": COMPOSIO_API_KEY})
    mcp_tool_spec = McpToolSpec(client=mcp_client)
    tools = await mcp_tool_spec.to_tool_list_async()

    llm = OpenAI(model="gpt-5")

    description = "An agent that uses Composio Tool Router MCP tools to perform Circleci actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Circleci actions.
    """
    return ReActAgent(tools=tools, llm=llm, description=description, system_prompt=system_prompt, verbose=True)
```

```typescript
async function buildAgent() {

  console.log(`Initializing Composio client...${COMPOSIO_USER_ID!}...`);
  console.log(`COMPOSIO_USER_ID: ${COMPOSIO_USER_ID!}...`);

  const composio = new Composio({
    apiKey: COMPOSIO_API_KEY,
    provider: new LlamaindexProvider(),
  });

  const session = await composio.create(
    COMPOSIO_USER_ID!,
    {
      toolkits: ["circleci"],
    },
  );

  const mcpUrl = session.mcp.url;
  console.log(`Composio Tool Router MCP URL: ${mcpUrl}`);

  const server = mcp({
    url: mcpUrl,
    clientName: "composio_tool_router_with_llamaindex",
    requestInit: {
      headers: {
        "x-api-key": COMPOSIO_API_KEY!,
      },
    },
    // verbose: true,
  });

  const tools = await server.tools();

  const llm = openai({ apiKey: OPENAI_API_KEY, model: "gpt-5" });

  const agent = createAgent({
    name: "composio_tool_router_with_llamaindex",
        description : "An agent that uses Composio Tool Router MCP tools to perform actions.",
    systemPrompt:
      "You are a helpful assistant connected to Composio Tool Router."+
"Use the available tools to answer user queries and perform Circleci actions." ,
    llm,
    tools,
  });

  return agent;
}
```

### 7. Create an interactive chat loop

No description provided.
```python
async def chat_loop(agent: ReActAgent) -> None:
    ctx = Context(agent)
    print("Type 'quit', 'exit', or Ctrl+C to stop.")

    while True:
        try:
            user_input = input("\nYou: ").strip()
        except (KeyboardInterrupt, EOFError):
            print("\nBye!")
            break

        if not user_input or user_input.lower() in {"quit", "exit"}:
            print("Bye!")
            break

        try:
            print("Agent: ", end="", flush=True)
            handler = agent.run(user_input, ctx=ctx)

            async for event in handler.stream_events():
                # Stream token-by-token from LLM responses
                if hasattr(event, "delta") and event.delta:
                    print(event.delta, end="", flush=True)
                # Show tool calls as they happen
                elif hasattr(event, "tool_name"):
                    print(f"\n[Using tool: {event.tool_name}]", flush=True)

            # Get final response
            response = await handler
            print()  # Newline after streaming
        except KeyboardInterrupt:
            print("\n[Interrupted]")
            continue
        except Exception as e:
            print(f"\nError: {e}")
```

```typescript
async function chatLoop(agent: ReturnType<typeof createAgent>) {
  const rl = readline.createInterface({ input, output });

  console.log("Type 'quit' or 'exit' to stop.");

  while (true) {
    let userInput: string;

    try {
      userInput = (await rl.question("\nYou: ")).trim();
    } catch {
      console.log("\nAgent: Bye!");
      break;
    }

    if (!userInput) {
      continue;
    }

    const lower = userInput.toLowerCase();
    if (lower === "quit" || lower === "exit") {
      console.log("Agent: Bye!");
      break;
    }

    try {
      process.stdout.write("Agent: ");

      const stream = agent.runStream(userInput);
      let finalResult: any = null;

      for await (const event of stream) {
        // The event.data contains the streamed content
        const data: any = event.data;

        // Check for streaming delta content
        if (data?.delta) {
          process.stdout.write(data.delta);
        }

        // Store final result for fallback
        if (data?.result || data?.message) {
          finalResult = data;
        }
      }

      // If no streaming happened, show the final result
      if (finalResult) {
        const answer =
          finalResult.result ??
          finalResult.message?.content ??
          finalResult.message ??
          "";
        if (answer && typeof answer === "string" && !answer.includes("[object")) {
          process.stdout.write(answer);
        }
      }

      console.log(); // New line after streaming completes
    } catch (err: any) {
      console.error("\nAgent error:", err?.message ?? err);
    }
  }

  rl.close();
}
```

### 8. Define the main entry point

What's happening here:
- We're orchestrating the entire application flow
- The agent gets built with proper error handling
- Then we kick off the interactive chat loop so you can start talking to Circleci
```python
async def main() -> None:
    agent = await build_agent()
    await chat_loop(agent)

if __name__ == "__main__":
    # Handle Ctrl+C gracefully
    signal.signal(signal.SIGINT, lambda s, f: (print("\nBye!"), exit(0)))
    try:
        asyncio.run(main())
    except KeyboardInterrupt:
        print("\nBye!")
```

```typescript
async function main() {
  try {
    const agent = await buildAgent();
    await chatLoop(agent);
  } catch (err) {
    console.error("Failed to start agent:", err);
    process.exit(1);
  }
}

main();
```

### 9. Run the agent

When prompted, authenticate and authorise your agent with Circleci, then start asking questions.
```bash
python llamaindex_agent.py
```

```typescript
npx ts-node llamaindex-agent.ts
```

## Complete Code

```python
import asyncio
import os
import signal
import dotenv

from composio import Composio
from composio_llamaindex import LlamaIndexProvider
from llama_index.core.agent.workflow import ReActAgent
from llama_index.core.workflow import Context
from llama_index.llms.openai import OpenAI
from llama_index.tools.mcp import BasicMCPClient, McpToolSpec

dotenv.load_dotenv()

OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY")
COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID")

if not OPENAI_API_KEY:
    raise ValueError("OPENAI_API_KEY is not set")
if not COMPOSIO_API_KEY:
    raise ValueError("COMPOSIO_API_KEY is not set")
if not COMPOSIO_USER_ID:
    raise ValueError("COMPOSIO_USER_ID is not set")

async def build_agent() -> ReActAgent:
    composio_client = Composio(
        api_key=COMPOSIO_API_KEY,
        provider=LlamaIndexProvider(),
    )

    session = composio_client.create(
        user_id=COMPOSIO_USER_ID,
        toolkits=["circleci"],
    )

    mcp_url = session.mcp.url
    print(f"Composio MCP URL: {mcp_url}")

    mcp_client = BasicMCPClient(mcp_url, headers={"x-api-key": COMPOSIO_API_KEY})
    mcp_tool_spec = McpToolSpec(client=mcp_client)
    tools = await mcp_tool_spec.to_tool_list_async()

    llm = OpenAI(model="gpt-5")
    description = "An agent that uses Composio Tool Router MCP tools to perform Circleci actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Circleci actions.
    """
    return ReActAgent(
        tools=tools,
        llm=llm,
        description=description,
        system_prompt=system_prompt,
        verbose=True,
    );

async def chat_loop(agent: ReActAgent) -> None:
    ctx = Context(agent)
    print("Type 'quit', 'exit', or Ctrl+C to stop.")

    while True:
        try:
            user_input = input("\nYou: ").strip()
        except (KeyboardInterrupt, EOFError):
            print("\nBye!")
            break

        if not user_input or user_input.lower() in {"quit", "exit"}:
            print("Bye!")
            break

        try:
            print("Agent: ", end="", flush=True)
            handler = agent.run(user_input, ctx=ctx)

            async for event in handler.stream_events():
                # Stream token-by-token from LLM responses
                if hasattr(event, "delta") and event.delta:
                    print(event.delta, end="", flush=True)
                # Show tool calls as they happen
                elif hasattr(event, "tool_name"):
                    print(f"\n[Using tool: {event.tool_name}]", flush=True)

            # Get final response
            response = await handler
            print()  # Newline after streaming
        except KeyboardInterrupt:
            print("\n[Interrupted]")
            continue
        except Exception as e:
            print(f"\nError: {e}")

async def main() -> None:
    agent = await build_agent()
    await chat_loop(agent)

if __name__ == "__main__":
    # Handle Ctrl+C gracefully
    signal.signal(signal.SIGINT, lambda s, f: (print("\nBye!"), exit(0)))
    try:
        asyncio.run(main())
    except KeyboardInterrupt:
        print("\nBye!")
```

```typescript
import "dotenv/config";
import readline from "node:readline/promises";
import { stdin as input, stdout as output } from "node:process";

import { Composio } from "@composio/core";
import { LlamaindexProvider } from "@composio/llamaindex";

import { mcp } from "@llamaindex/tools";
import { agent as createAgent } from "@llamaindex/workflow";
import { openai } from "@llamaindex/openai";

dotenv.config();

const OPENAI_API_KEY = process.env.OPENAI_API_KEY;
const COMPOSIO_API_KEY = process.env.COMPOSIO_API_KEY;
const COMPOSIO_USER_ID = process.env.COMPOSIO_USER_ID;

if (!OPENAI_API_KEY) {
    throw new Error("OPENAI_API_KEY is not set in the environment");
  }
if (!COMPOSIO_API_KEY) {
    throw new Error("COMPOSIO_API_KEY is not set in the environment");
  }
if (!COMPOSIO_USER_ID) {
    throw new Error("COMPOSIO_USER_ID is not set in the environment");
  }

async function buildAgent() {

  console.log(`Initializing Composio client...${COMPOSIO_USER_ID!}...`);
  console.log(`COMPOSIO_USER_ID: ${COMPOSIO_USER_ID!}...`);

  const composio = new Composio({
    apiKey: COMPOSIO_API_KEY,
    provider: new LlamaindexProvider(),
  });

  const session = await composio.create(
    COMPOSIO_USER_ID!,
    {
      toolkits: ["circleci"],
    },
  );

  const mcpUrl = session.mcp.url;
  console.log(`Composio Tool Router MCP URL: ${mcpUrl}`);

  const server = mcp({
    url: mcpUrl,
    clientName: "composio_tool_router_with_llamaindex",
    requestInit: {
      headers: {
        "x-api-key": COMPOSIO_API_KEY!,
      },
    },
    // verbose: true,
  });

  const tools = await server.tools();

  const llm = openai({ apiKey: OPENAI_API_KEY, model: "gpt-5" });

  const agent = createAgent({
    name: "composio_tool_router_with_llamaindex",
    description:
      "An agent that uses Composio Tool Router MCP tools to perform actions.",
    systemPrompt:
      "You are a helpful assistant connected to Composio Tool Router."+
"Use the available tools to answer user queries and perform Circleci actions." ,
    llm,
    tools,
  });

  return agent;
}

async function chatLoop(agent: ReturnType<typeof createAgent>) {
  const rl = readline.createInterface({ input, output });

  console.log("Type 'quit' or 'exit' to stop.");

  while (true) {
    let userInput: string;

    try {
      userInput = (await rl.question("\nYou: ")).trim();
    } catch {
      console.log("\nAgent: Bye!");
      break;
    }

    if (!userInput) {
      continue;
    }

    const lower = userInput.toLowerCase();
    if (lower === "quit" || lower === "exit") {
      console.log("Agent: Bye!");
      break;
    }

    try {
      process.stdout.write("Agent: ");

      const stream = agent.runStream(userInput);
      let finalResult: any = null;

      for await (const event of stream) {
        // The event.data contains the streamed content
        const data: any = event.data;

        // Check for streaming delta content
        if (data?.delta) {
          process.stdout.write(data.delta);
        }

        // Store final result for fallback
        if (data?.result || data?.message) {
          finalResult = data;
        }
      }

      // If no streaming happened, show the final result
      if (finalResult) {
        const answer =
          finalResult.result ??
          finalResult.message?.content ??
          finalResult.message ??
          "";
        if (answer && typeof answer === "string" && !answer.includes("[object")) {
          process.stdout.write(answer);
        }
      }

      console.log(); // New line after streaming completes
    } catch (err: any) {
      console.error("\nAgent error:", err?.message ?? err);
    }
  }

  rl.close();
}

async function main() {
  try {
    const agent = await buildAgent();
    await chatLoop(agent);
  } catch (err: any) {
    console.error("Failed to start agent:", err?.message ?? err);
    process.exit(1);
  }
}

main();
```

## Conclusion

You've successfully connected Circleci to LlamaIndex through Composio's Tool Router MCP layer.
Key takeaways:
- Tool Router dynamically exposes Circleci tools through an MCP endpoint
- LlamaIndex's ReActAgent handles reasoning and orchestration; Composio handles integrations
- The agent becomes more capable without increasing prompt size
- Async Python provides clean, efficient execution of agent workflows
You can easily extend this to other toolkits like Gmail, Notion, Stripe, GitHub, and more by adding them to the toolkits parameter.

## How to build Circleci MCP Agent with another framework

- [OpenAI Agents SDK](https://composio.dev/toolkits/circleci/framework/open-ai-agents-sdk)
- [Claude Agent SDK](https://composio.dev/toolkits/circleci/framework/claude-agents-sdk)
- [Claude Code](https://composio.dev/toolkits/circleci/framework/claude-code)
- [Claude Cowork](https://composio.dev/toolkits/circleci/framework/claude-cowork)
- [Codex](https://composio.dev/toolkits/circleci/framework/codex)
- [OpenClaw](https://composio.dev/toolkits/circleci/framework/openclaw)
- [Hermes](https://composio.dev/toolkits/circleci/framework/hermes-agent)
- [CLI](https://composio.dev/toolkits/circleci/framework/cli)
- [Google ADK](https://composio.dev/toolkits/circleci/framework/google-adk)
- [LangChain](https://composio.dev/toolkits/circleci/framework/langchain)
- [Vercel AI SDK](https://composio.dev/toolkits/circleci/framework/ai-sdk)
- [Mastra AI](https://composio.dev/toolkits/circleci/framework/mastra-ai)
- [CrewAI](https://composio.dev/toolkits/circleci/framework/crew-ai)

## Related Toolkits

- [Supabase](https://composio.dev/toolkits/supabase) - Supabase is an open-source backend platform offering scalable Postgres databases, authentication, storage, and real-time APIs. It lets developers build modern apps without managing infrastructure.
- [Codeinterpreter](https://composio.dev/toolkits/codeinterpreter) - Codeinterpreter is a Python-based coding environment with built-in data analysis and visualization. It lets you instantly run scripts, plot results, and prototype solutions inside supported platforms.
- [GitHub](https://composio.dev/toolkits/github) - GitHub is a code hosting platform for version control and collaborative software development. It streamlines project management, code review, and team workflows in one place.
- [Ably](https://composio.dev/toolkits/ably) - Ably is a real-time messaging platform for live chat and data sync in modern apps. It offers global scale and rock-solid reliability for seamless, instant experiences.
- [Abuselpdb](https://composio.dev/toolkits/abuselpdb) - Abuselpdb is a central database for reporting and checking IPs linked to malicious online activity. Use it to quickly identify and report suspicious or abusive IP addresses.
- [Alchemy](https://composio.dev/toolkits/alchemy) - Alchemy is a blockchain development platform offering APIs and tools for Ethereum apps. It simplifies building and scaling Web3 projects with robust infrastructure.
- [Algolia](https://composio.dev/toolkits/algolia) - Algolia is a hosted search API that powers lightning-fast, relevant search experiences for web and mobile apps. It helps developers deliver instant, typo-tolerant, and scalable search without complex infrastructure.
- [Anchor browser](https://composio.dev/toolkits/anchor_browser) - Anchor browser is a developer platform for AI-powered web automation. It transforms complex browser actions into easy API endpoints for streamlined web interaction.
- [Apiflash](https://composio.dev/toolkits/apiflash) - Apiflash is a website screenshot API for programmatically capturing web pages. It delivers high-quality screenshots on demand for automation, monitoring, or reporting.
- [Apiverve](https://composio.dev/toolkits/apiverve) - Apiverve delivers a suite of powerful APIs that simplify integration for developers. It's designed for reliability and scalability so you can build faster, smarter applications without the integration headache.
- [Appcircle](https://composio.dev/toolkits/appcircle) - Appcircle is an enterprise-grade mobile CI/CD platform for building, testing, and publishing mobile apps. It streamlines mobile DevOps so teams ship faster and with more confidence.
- [Appdrag](https://composio.dev/toolkits/appdrag) - Appdrag is a cloud platform for building websites, APIs, and databases with drag-and-drop tools and code editing. It accelerates development and iteration by combining hosting, database management, and low-code features in one place.
- [Appveyor](https://composio.dev/toolkits/appveyor) - AppVeyor is a cloud-based continuous integration service for building, testing, and deploying applications. It helps developers automate and streamline their software delivery pipelines.
- [Backendless](https://composio.dev/toolkits/backendless) - Backendless is a backend-as-a-service platform for mobile and web apps, offering database, file storage, user authentication, and APIs. It helps developers ship scalable applications faster without managing server infrastructure.
- [Baserow](https://composio.dev/toolkits/baserow) - Baserow is an open-source no-code database platform for building collaborative data apps. It makes it easy for teams to organize data and automate workflows without writing code.
- [Bench](https://composio.dev/toolkits/bench) - Bench is a benchmarking tool for automated performance measurement and analysis. It helps you quickly evaluate, compare, and track your systems or workflows.
- [Better stack](https://composio.dev/toolkits/better_stack) - Better Stack is a monitoring, logging, and incident management solution for apps and services. It helps teams ensure application reliability and performance with real-time insights.
- [Bitbucket](https://composio.dev/toolkits/bitbucket) - Bitbucket is a Git-based code hosting and collaboration platform for teams. It enables secure repository management and streamlined code reviews.
- [Blazemeter](https://composio.dev/toolkits/blazemeter) - Blazemeter is a continuous testing platform for web and mobile app performance. It empowers teams to automate and analyze large-scale tests with ease.
- [Blocknative](https://composio.dev/toolkits/blocknative) - Blocknative delivers real-time mempool monitoring and transaction management for public blockchains. Instantly track pending transactions and optimize blockchain interactions with live data.

## Frequently Asked Questions

### What are the differences in Tool Router MCP and Circleci MCP?

With a standalone Circleci MCP server, the agents and LLMs can only access a fixed set of Circleci tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Circleci and many other apps based on the task at hand, all through a single MCP endpoint.

### Can I use Tool Router MCP with LlamaIndex?

Yes, you can. LlamaIndex fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Circleci tools.

### Can I manage the permissions and scopes for Circleci while using Tool Router?

Yes, absolutely. You can configure which Circleci scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

### How safe is my data with Composio Tool Router?

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Circleci data and credentials are handled as safely as possible.

---
[See all toolkits](https://composio.dev/toolkits) · [Composio docs](https://docs.composio.dev/llms.txt)