# How to integrate Highergov MCP with LlamaIndex

```json
{
  "title": "How to integrate Highergov MCP with LlamaIndex",
  "toolkit": "Highergov",
  "toolkit_slug": "highergov",
  "framework": "LlamaIndex",
  "framework_slug": "llama-index",
  "url": "https://composio.dev/toolkits/highergov/framework/llama-index",
  "markdown_url": "https://composio.dev/toolkits/highergov/framework/llama-index.md",
  "updated_at": "2026-05-12T10:14:59.338Z"
}
```

## Introduction

This guide walks you through connecting Highergov to LlamaIndex using the Composio tool router. By the end, you'll have a working Highergov agent that can list recent federal contract awards for it services, show all active dla contract opportunities today, retrieve grant history for a specific agency through natural language commands.
This guide will help you understand how to give your LlamaIndex agent real control over a Highergov account through Composio's Highergov MCP server.
Before we dive in, let's take a quick look at the key ideas and tools involved.

## Also integrate Highergov with

- [OpenAI Agents SDK](https://composio.dev/toolkits/highergov/framework/open-ai-agents-sdk)
- [Claude Agent SDK](https://composio.dev/toolkits/highergov/framework/claude-agents-sdk)
- [Claude Code](https://composio.dev/toolkits/highergov/framework/claude-code)
- [Claude Cowork](https://composio.dev/toolkits/highergov/framework/claude-cowork)
- [Codex](https://composio.dev/toolkits/highergov/framework/codex)
- [OpenClaw](https://composio.dev/toolkits/highergov/framework/openclaw)
- [Hermes](https://composio.dev/toolkits/highergov/framework/hermes-agent)
- [CLI](https://composio.dev/toolkits/highergov/framework/cli)
- [Google ADK](https://composio.dev/toolkits/highergov/framework/google-adk)
- [LangChain](https://composio.dev/toolkits/highergov/framework/langchain)
- [Vercel AI SDK](https://composio.dev/toolkits/highergov/framework/ai-sdk)
- [Mastra AI](https://composio.dev/toolkits/highergov/framework/mastra-ai)
- [CrewAI](https://composio.dev/toolkits/highergov/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 Highergov
- Connect LlamaIndex to the Highergov MCP server
- Build a Highergov-powered agent using LlamaIndex
- Interact with Highergov 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 Highergov MCP server, and what's possible with it?

The Highergov MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Highergov account. It provides structured and secure access to government contracting and grant intelligence, so your agent can perform actions like searching contracts, analyzing award history, retrieving agency details, and fetching grant data on your behalf.
- Comprehensive contract search and retrieval: Quickly have your agent look up federal contracts, filter by last modified date, or leverage saved searches to find exactly what you need.
- Award and grant history analysis: Direct your agent to access detailed award and grant histories, making it simple to track funding trends across agencies or time periods.
- Agency and program intelligence: Ask your agent to list and explore government agencies, defense programs, or contract vehicles to support your market research.
- Document and opportunity extraction: Let your agent fetch associated documents or list DLA contract opportunities for deeper due diligence and competitive analysis.
- IDV and contract vehicle tracking: Monitor Indefinite Delivery Vehicles (IDVs) and contract vehicles to better understand procurement patterns and strategic opportunities.

## Supported Tools

| Tool slug | Name | Description |
|---|---|---|
| `HIGHERGOV_GET_AGENCIES` | Get Agencies | Retrieves government agency information from the HigherGov database with pagination support. Use this tool to: - List all federal agencies with details like name, abbreviation, type, and hierarchy - Search for a specific agency by its unique agency_key identifier - Navigate through paginated results of agencies (28,000+ agencies available) The response includes agency hierarchy levels (level_1 through level_7) showing parent-child relationships between agencies, along with pagination metadata for browsing through results. |
| `HIGHERGOV_GET_CONTRACTS` | Get Contracts | Retrieve federal government contract data from HigherGov. Returns paginated list of contracts with details including awardees, agencies, amounts, dates, NAICS/PSC codes, and performance information. Supports filtering by date, search criteria, award ID, awardee, agency, industry codes, and more. Data updates daily by 2am for two days prior. |
| `HIGHERGOV_GET_CONTRACT_VEHICLES` | Get Contract Vehicles | Retrieve federal multi-award contract vehicles from HigherGov. Contract vehicles are pre-established contracting mechanisms that streamline procurement. Use this to list available vehicles with optional filtering by vehicle key and sorting by award date. Supports pagination with up to 100 records per page. Updated ad hoc as new awards are made. |
| `HIGHERGOV_GET_DOCUMENTS` | Get Documents | Retrieve document metadata and download URLs for files associated with government opportunities, contracts, and grants from HigherGov. **When to use:** After calling Get Opportunities, Get Contracts, or Get Grants, use this tool to fetch the actual documents (RFPs, amendments, attachments, etc.) associated with those records. **How to use:** 1. First call Get Opportunities, Get Contracts, or Get Grants 2. Extract the 'document_path' field from the response 3. Parse the 'related_key' parameter from that document_path URL 4. Pass that related_key to this tool to retrieve the documents **Important notes:** - Download URLs expire after 60 minutes; retrieve new URLs by calling this endpoint again - Some opportunities/contracts/grants may have no associated documents (returns empty results) - Results are paginated; use page and page_size parameters for large document sets |
| `HIGHERGOV_GET_GRANT_HISTORY` | Get Grant History | Tool to fetch historical data on grants from the HigherGov API. REQUIRED: At least one filter parameter (award_id or last_modified_date) must be provided. Use cases: - Retrieve history for a specific grant by award_id - Retrieve grants modified since a specific date using last_modified_date - Paginate through results using page and page_size parameters |
| `HIGHERGOV_GET_GRANT_OPPORTUNITIES` | Get Grant Opportunities | Retrieve government grant and contract opportunities from HigherGov. Returns Federal contracts, SLED (State/Local) opportunities, grants, and SBIR opportunities with comprehensive details including agency info, dates, contacts, and award estimates. Use this when you need to: - Find government opportunities by date (posted_date or captured_date recommended) - Search for opportunities with specific keywords - Filter opportunities by agency, status, or other criteria - Get detailed opportunity information including contact details and documents REQUIRED: Must provide at least one filter (posted_date, captured_date, search_id, source_id, agency_key, opp_key, or version_key). For best results, use posted_date or captured_date with optional keyword filtering. |
| `HIGHERGOV_GET_GRANT_PROGRAMS` | Get Grant Programs | Tool to retrieve information on grant programs. Use when you need to list available grant programs with pagination. |
| `HIGHERGOV_GET_NAICS` | Get NAICS Codes | Retrieve NAICS (North American Industry Classification System) codes with detailed descriptions. Returns a paginated list of NAICS codes that can be filtered by code prefix and sorted. Useful for finding industry classifications, understanding NAICS hierarchies, and identifying relevant codes for business categorization. |
| `HIGHERGOV_GET_OPPORTUNITY_HISTORY` | Get Opportunity History | Retrieve historical opportunity data from HigherGov with pagination support. This tool requires at least one identifying filter (captured_date, opp_key, version_key, search_id, posted_date, source_id, or agency_key). Most commonly used with captured_date to get all opportunities from a specific date, optionally filtered by source_type ('sam' or 'sled'). Returns paginated results with comprehensive opportunity details including title, description, agency, dates, contact information, and links to documents. |
| `HIGHERGOV_GET_PEOPLE` | Get People | Retrieves contact information for federal and state/local government personnel from HigherGov. Returns detailed contact records including names, titles, emails, phone numbers, and affiliated agencies. Data is updated in real-time. Use this to find government contacts, especially when you have an email address or need to browse through personnel listings. Common use cases: - Find contact details for a specific government employee by email - Browse government personnel with pagination - Get the most recently updated contacts using ordering |
| `HIGHERGOV_GET_PSC` | Get Product and Service Codes | Tool to retrieve information on Product and Service Codes. Use when fetching PSC entries with optional pagination and filtering by code. |
| `HIGHERGOV_GET_PURSUITS` | Get Pursuits | Tool to retrieve user-specific pursuits. Use when you need to fetch a user's pursuits with optional filtering by status and pagination. |
| `HIGHERGOV_GET_SBIR_OPPORTUNITIES` | Get SBIR Opportunities | Retrieve SBIR (Small Business Innovation Research) opportunities from HigherGov. SBIR is a U.S. government program that provides funding to small businesses for research and development with commercialization potential. This action retrieves SBIR opportunities from federal agencies. By default, retrieves opportunities captured since 2024-01-01. Use filters to narrow results by specific dates, agencies, or opportunity identifiers. Supports pagination for large result sets. Key use cases: - Find recent SBIR opportunities for a specific federal agency - Track SBIR opportunities by capture/posting dates - Retrieve details for specific SBIR opportunities by ID - Monitor new SBIR opportunities added to the system Note: At least one filter parameter (captured_date, posted_date, search_id, source_id, agency_key, opp_key, or version_key) is required by the API. The action provides captured_date with a sensible default. |
| `HIGHERGOV_GET_SLED_CONTRACT_OPPORTUNITIES` | Get SLED Contract Opportunities | Tool to retrieve state and local (SLED) contract opportunities. Uses the general Opportunity endpoint with optional filters. |
| `HIGHERGOV_GET_SUBCONTRACT_AWARDS` | Get Subcontract Awards | Retrieves federal subcontract award data from HigherGov. Returns paginated subcontract records with details about subcontract recipients, amounts, prime contracts, and awarding agencies. **Important**: At least one filter parameter (last_modified_date or search_id) is required by the API. Use this when you need to: - Find subcontracts modified on a specific date - List subcontracts from a saved HigherGov search - Access detailed subcontract award information including recipient details and prime contract relationships Data is updated weekly. Use the last_modified_date field to track updates. |
| `HIGHERGOV_GET_SUBGRANT_AWARDS` | Get Subgrant Awards | Retrieves federal subgrant award data from HigherGov. Returns paginated subgrant records with details about subgrant recipients, funding amounts, associated prime grants, and program information. **Important**: At least one filter parameter (last_modified_date or search_id) is required by the API. Use this when you need to: - Find subgrant awards modified on a specific date - List subgrant awards from a saved HigherGov search - Access detailed subgrant award information including recipient details and prime grant relationships Data is updated regularly. Use the last_modified_date field to track updates. |

## Supported Triggers

None listed.

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

The Highergov MCP server is an implementation of the Model Context Protocol that connects your AI agent to Highergov. It provides structured and secure access so your agent can perform Highergov 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 Highergov account and project
- Basic familiarity with async Python/Typescript

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

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 Highergov 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, highergov)
- 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 Highergov 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=["highergov"],
    )

    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 Highergov actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Highergov 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: ["highergov"],
    },
  );

  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 Highergov 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 Highergov
```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 Highergov, 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=["highergov"],
    )

    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 Highergov actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Highergov 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: ["highergov"],
    },
  );

  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 Highergov 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 Highergov to LlamaIndex through Composio's Tool Router MCP layer.
Key takeaways:
- Tool Router dynamically exposes Highergov 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 Highergov MCP Agent with another framework

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

## Related Toolkits

- [Excel](https://composio.dev/toolkits/excel) - Microsoft Excel is a robust spreadsheet application for organizing, analyzing, and visualizing data. It's the go-to tool for calculations, reporting, and flexible data management.
- [21risk](https://composio.dev/toolkits/_21risk) - 21RISK is a web app built for easy checklist, audit, and compliance management. It streamlines risk processes so teams can focus on what matters.
- [Abstract](https://composio.dev/toolkits/abstract) - Abstract provides a suite of APIs for automating data validation and enrichment tasks. It helps developers streamline workflows and ensure data quality with minimal effort.
- [Addressfinder](https://composio.dev/toolkits/addressfinder) - Addressfinder is a data quality platform for verifying addresses, emails, and phone numbers. It helps you ensure accurate customer and contact data every time.
- [Agenty](https://composio.dev/toolkits/agenty) - Agenty is a web scraping and automation platform for extracting data and automating browser tasks—no coding needed. It streamlines data collection, monitoring, and repetitive online actions.
- [Ambee](https://composio.dev/toolkits/ambee) - Ambee is an environmental data platform providing real-time, hyperlocal APIs for air quality, weather, and pollen. Get precise environmental insights to power smarter decisions in your apps and workflows.
- [Ambient weather](https://composio.dev/toolkits/ambient_weather) - Ambient Weather is a platform for personal weather stations with a robust API for accessing local, real-time, and historical weather data. Get detailed environmental insights directly from your own sensors for smarter apps and automations.
- [Anonyflow](https://composio.dev/toolkits/anonyflow) - Anonyflow is a service for encryption-based data anonymization and secure data sharing. It helps organizations meet GDPR, CCPA, and HIPAA data privacy compliance requirements.
- [Api ninjas](https://composio.dev/toolkits/api_ninjas) - Api ninjas offers 120+ public APIs spanning categories like weather, finance, sports, and more. Developers use it to supercharge apps with real-time data and actionable endpoints.
- [Api sports](https://composio.dev/toolkits/api_sports) - Api sports is a comprehensive sports data platform covering 2,000+ competitions with live scores and 15+ years of stats. Instantly access up-to-date sports information for analysis, apps, or chatbots.
- [Apify](https://composio.dev/toolkits/apify) - Apify is a cloud platform for building, deploying, and managing web scraping and automation tools called Actors. It lets you automate data extraction and workflow tasks at scale—no infrastructure headaches.
- [Autom](https://composio.dev/toolkits/autom) - Autom is a lightning-fast search engine results data platform for Google, Bing, and Brave. Developers use it to access fresh, low-latency SERP data on demand.
- [Beaconchain](https://composio.dev/toolkits/beaconchain) - Beaconchain is a real-time analytics platform for Ethereum 2.0's Beacon Chain. It provides detailed insights into validators, blocks, and overall network performance.
- [Big data cloud](https://composio.dev/toolkits/big_data_cloud) - BigDataCloud provides APIs for geolocation, reverse geocoding, and address validation. Instantly access reliable location intelligence to enhance your applications and workflows.
- [Bigpicture io](https://composio.dev/toolkits/bigpicture_io) - BigPicture.io offers APIs for accessing detailed company and profile data. Instantly enrich your applications with up-to-date insights on 20M+ businesses.
- [Bitquery](https://composio.dev/toolkits/bitquery) - Bitquery is a blockchain data platform offering indexed, real-time, and historical data from 40+ blockchains via GraphQL APIs. Get unified, reliable access to complex on-chain data for analytics, trading, and research.
- [Brightdata](https://composio.dev/toolkits/brightdata) - Brightdata is a leading web data platform offering advanced scraping, SERP APIs, and anti-bot tools. It lets you collect public web data at scale, bypassing blocks and friction.
- [Builtwith](https://composio.dev/toolkits/builtwith) - BuiltWith is a web technology profiler that uncovers the technologies powering any website. Gain actionable insights into analytics, hosting, and content management stacks for smarter research and lead generation.
- [Byteforms](https://composio.dev/toolkits/byteforms) - Byteforms is an all-in-one platform for creating forms, managing submissions, and integrating data. It streamlines workflows by centralizing form data collection and automation.
- [Cabinpanda](https://composio.dev/toolkits/cabinpanda) - Cabinpanda is a data collection platform for building and managing online forms. It helps streamline how you gather, organize, and analyze responses.

## Frequently Asked Questions

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

With a standalone Highergov MCP server, the agents and LLMs can only access a fixed set of Highergov tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Highergov 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 Highergov tools.

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

Yes, absolutely. You can configure which Highergov 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 Highergov data and credentials are handled as safely as possible.

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