# How to integrate Appcircle MCP with Claude Agent SDK

```json
{
  "title": "How to integrate Appcircle MCP with Claude Agent SDK",
  "toolkit": "Appcircle",
  "toolkit_slug": "appcircle",
  "framework": "Claude Agent SDK",
  "framework_slug": "claude-agents-sdk",
  "url": "https://composio.dev/toolkits/appcircle/framework/claude-agents-sdk",
  "markdown_url": "https://composio.dev/toolkits/appcircle/framework/claude-agents-sdk.md",
  "updated_at": "2026-05-12T10:01:45.854Z"
}
```

## Introduction

This guide walks you through connecting Appcircle to the Claude Agent SDK using the Composio tool router. By the end, you'll have a working Appcircle agent that can trigger a new ios app build pipeline, fetch latest build status for your project, list all available distribution profiles through natural language commands.
This guide will help you understand how to give your Claude Agent SDK agent real control over a Appcircle account through Composio's Appcircle MCP server.
Before we dive in, let's take a quick look at the key ideas and tools involved.

## Also integrate Appcircle with

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

## TL;DR

Here's what you'll learn:
- Get and set up your Claude/Anthropic and Composio API keys
- Install the necessary dependencies
- Initialize Composio and create a Tool Router session for Appcircle
- Configure an AI agent that can use Appcircle as a tool
- Run a live chat session where you can ask the agent to perform Appcircle operations

## What is Claude Agent SDK?

The Claude Agent SDK is Anthropic's official framework for building AI agents powered by Claude. It provides a streamlined interface for creating agents with MCP tool support and conversation management.
Key features include:
- Native MCP Support: Built-in support for Model Context Protocol servers
- Permission Modes: Control tool execution permissions
- Streaming Responses: Real-time response streaming for interactive applications
- Context Manager: Clean async context management for sessions

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

The Appcircle MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Appcircle account. It provides structured and secure access to your mobile CI/CD pipelines, so your agent can perform actions like triggering builds, monitoring workflows, managing artifacts, and automating mobile app deployments on your behalf.
- Automated mobile app builds: Let your agent trigger new builds for iOS and Android apps, manage build profiles, and handle build parameters seamlessly.
- Workflow monitoring and insights: Enable your agent to fetch real-time statuses, logs, and detailed reports from your Appcircle build and test workflows.
- Test execution and results retrieval: Instruct your agent to start automated test runs, collect results, and surface issues or test failures for rapid feedback.
- Artifact management and distribution: Have your agent access, download, or distribute app binaries, install links, and build artifacts to your team or testers.
- Deployment automation: Direct your agent to publish builds to app stores or internal distribution channels, streamlining release management for your mobile apps.

## Supported Tools

| Tool slug | Name | Description |
|---|---|---|
| `APPCIRCLE_BUILD_REPO_WEBHOOK_CALLBACK_STANDARD` | Standard Repo Webhook Callback | Trigger Appcircle builds via Git provider webhook callbacks. This action forwards webhook payloads from GitHub, GitLab, Bitbucket, or Azure DevOps to Appcircle's build webhook endpoint to automatically trigger builds when code is pushed. Use this action when: - Simulating or testing webhook-triggered builds - Programmatically triggering builds using webhook payloads - Integrating custom CI/CD workflows that need to trigger Appcircle builds - Replaying or debugging webhook events Requirements: - The organization must exist and have webhook integration configured in Appcircle - Build profiles must be set up with repository connections - The webhook URL pattern is: https://api.appcircle.io/build/v1/callback/hooks/{provider}/{org_id}/V7 Note: The action returns the raw HTTP response including status code and response body, allowing you to handle success, validation errors, or authentication issues appropriately. |
| `APPCIRCLE_BUILD_WEBHOOK_CUSTOM_INTEGRATION` | Custom Integration Webhook Callback | Triggers Appcircle builds via custom integration webhook endpoint by forwarding Git provider webhook payloads. This action is designed to receive and forward webhook payloads from Git providers (GitHub, GitLab, Bitbucket, Azure DevOps) to Appcircle's build system. The webhook URL format and parameters (organization_id, integration_id, version) are provided by Appcircle when you configure custom integrations for repositories connected via SSH or public URL in the build profile settings. Use this action when: - You need to programmatically trigger Appcircle builds from Git provider webhook events - Testing webhook integrations with different payload structures - Implementing custom CI/CD workflows that forward webhook events to Appcircle Note: The organization_id and integration_id values must correspond to actual configurations in Appcircle. Test payloads will typically return 400/404 errors indicating no valid configuration exists for the provided IDs. |
| `APPCIRCLE_DISTRIBUTION_LIST_PROFILES` | List Distribution Profiles | List all distribution profiles for the authenticated organization. Distribution profiles are used to manage and distribute app builds to testers. This endpoint supports pagination, sorting, and filtering by profile name. Use this when you need to retrieve available distribution profiles. |
| `APPCIRCLE_GET_DISTRIBUTE_SENT_PROFILES` | Get Distribution Sent Profiles | Get distinct profile names for App Sharing Report filter. Returns a list of unique profile names that can be used to filter app sharing reports within the specified date range and organization. Use this to discover available profile names before querying detailed sharing reports. |
| `APPCIRCLE_GET_PUBLISH_ACTIVITY_REPORT` | Get Publish Activity Report | Retrieve the publish activity report for your organization. Returns paginated list of publish activities with filtering options by date range, platform, action type, and organization. Use this to monitor and audit publish operations across profiles. |
| `APPCIRCLE_LIST_BUILD_PROFILES` | List Build Profiles | List all build profiles for the authenticated organization. Build profiles define the configuration for building mobile applications. Use this to discover available build profiles and their IDs before triggering builds or configuring webhooks. |
| `APPCIRCLE_LIST_BUNDLE_IDENTIFIERS` | List Bundle Identifiers | List all bundle identifiers in Appcircle. Returns all bundle identifiers configured in your organization, including their platforms, capabilities, and associated credentials. Use this to discover available bundle identifiers before managing signing identities or app configurations. |
| `APPCIRCLE_LIST_ORGANIZATIONS` | List Organizations | List organizations accessible to the authenticated user. Returns a paginated list of organizations with their details including ID, name, logo URL, and SSO status. Supports search filtering and pagination controls. Use this to discover available organizations before performing organization-specific operations like managing builds, distributions, or webhooks. |
| `APPCIRCLE_LIST_STORE_PROFILES` | List Store Profiles | List all Enterprise App Store profiles for the authenticated organization. Enterprise App Store profiles are used to distribute apps internally. Use this to discover available store profiles and their IDs before listing app versions or managing store content. |
| `APPCIRCLE_RENAME_VARIABLE_GROUP` | Rename Variable Group | Tool to rename an environment group (variable group) in Appcircle. Use when you need to update the name of an existing variable group to better reflect its purpose or environment. |
| `APPCIRCLE_STORE_IN_APP_AUTH_TOKEN` | Obtain In-App Update Auth Token | Tool to fetch an access token for Enterprise App Store in-app updates. Use when you have the enterprise store profileId and secret and need to obtain a bearer token for subsequent update requests. |
| `APPCIRCLE_STORE_IN_APP_DOWNLOAD_VERSION_WITH_USER` | Download In-App Update Version with User | Tool to download a specific in-app store version and attribute the download to a user for reporting. Use when triggering an in-app update download after obtaining an access token. |
| `APPCIRCLE_STORE_INAPP_LIST_APP_VERSIONS` | List Enterprise App Store App Versions | Tool to list available app versions for the Enterprise App Store profile. Use when fetching available in-app update versions. |
| `APPCIRCLE_STORE_LIST_PROFILE_APP_VERSIONS_V2` | List Store Profile App Versions V2 | Tool to list app versions under a given store profile. Use when you need to fetch all versions for a specific Enterprise App Store profile after obtaining its ID. |

## Supported Triggers

None listed.

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

The Appcircle MCP server is an implementation of the Model Context Protocol that connects your AI agent to Appcircle. It provides structured and secure access so your agent can perform Appcircle 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 starting, make sure you have:
- Composio API Key and Claude/Anthropic API Key
- Primary know-how of Claude Agents SDK
- A Appcircle account
- Some knowledge of Python

### 1. Getting API Keys for Claude/Anthropic and Composio

Claude/Anthropic API Key
- Go to the [Anthropic Console](https://console.anthropic.com/settings/organization/api-keys) and create an API key. You'll need credits to use the models.
- Keep the API key safe.
Composio API Key
- Log in to the [Composio dashboard](https://dashboard.composio.dev?utm_source=toolkits&utm_medium=framework_docs).
- Navigate to your API settings and generate a new API key.
- Store this key securely as you'll need it for authentication.

### 2. Install dependencies

No description provided.
```python
pip install composio-anthropic claude-agent-sdk python-dotenv
```

```typescript
npm install @anthropic-ai/claude-agent-sdk @composio/core dotenv
```

### 3. Set up environment variables

Create a .env file in your project root.
What's happening:
- COMPOSIO_API_KEY authenticates with Composio
- USER_ID identifies the user for session management
- ANTHROPIC_API_KEY authenticates with Anthropic/Claude
```bash
COMPOSIO_API_KEY=your_composio_api_key_here
USER_ID=your_user_id_here
ANTHROPIC_API_KEY=your_anthropic_api_key_here
```

### 4. Import dependencies

No description provided.
```python
import asyncio
from claude_agent_sdk import ClaudeSDKClient, ClaudeAgentOptions
import os
from composio import Composio
from dotenv import load_dotenv

load_dotenv()
```

```typescript
import 'dotenv/config';
import readline from 'node:readline';
import { Composio } from '@composio/core';
import { query, type Options } from "@anthropic-ai/claude-agent-sdk";

dotenv.config();
```

### 5. Create a Composio instance and Tool Router session

No description provided.
```python
async def chat_with_remote_mcp():
    api_key = os.getenv("COMPOSIO_API_KEY")
    if not api_key:
        raise RuntimeError("COMPOSIO_API_KEY is not set")

    composio = Composio(api_key=api_key)

    # Create Tool Router session for Appcircle
    mcp_server = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["appcircle"]
    )

    url = mcp_server.mcp.url

    if not url:
        raise ValueError("Session URL not found")
```

```typescript
async function chat() {
  const { COMPOSIO_API_KEY, USER_ID } = process.env;
  if (!COMPOSIO_API_KEY || !USER_ID) {
    throw new Error('COMPOSIO_API_KEY and USER_ID required in .env');
  }

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

  // Create Tool Router session for Appcircle
  const session = await composio.create(USER_ID, {
    toolkits: ['appcircle'],
  });
  const mcpUrl = session?.mcp.url;
```

### 6. Configure Claude Agent with MCP

No description provided.
```python
# Configure remote MCP server for Claude
options = ClaudeAgentOptions(
    permission_mode="bypassPermissions",
    mcp_servers={
        "composio": {
            "type": "http",
            "url": url,
            "headers": {
                "x-api-key": os.getenv("COMPOSIO_API_KEY")
            }
        }
    },
    system_prompt="You are a helpful assistant with access to Appcircle tools via Composio.",
    max_turns=10
)
```

```typescript
const options: Options = {
  permissionMode: 'bypassPermissions',
  mcpServers: {
    composio: {
      type: 'http',
      url: mcpUrl,
      headers: { 'x-api-key': COMPOSIO_API_KEY }
    }
  },
  systemPrompt: 'You are a helpful assistant with access to Appcircle tools via Composio.',
  maxTurns: 10,
};
```

### 7. Create client and start chat loop

No description provided.
```python
# Create client with context manager
async with ClaudeSDKClient(options=options) as client:
    print("\nChat started. Type 'exit' or 'quit' to end.\n")

    # Main chat loop
    while True:
        user_input = input("You: ").strip()
        if user_input.lower() in {"exit", "quit"}:
            print("Goodbye!")
            break

        # Send query
        await client.query(user_input)

        # Receive and print response
        print("Claude: ", end="", flush=True)
        async for message in client.receive_response():
            if hasattr(message, "content"):
                for block in message.content:
                    if hasattr(block, "text"):
                        print(block.text, end="", flush=True)
        print()
```

```typescript
const rl = readline.createInterface({
    input: process.stdin,
    output: process.stdout,
    prompt: 'You: '
  });

  console.log('\nChat started. Type "exit" to quit.\n');

  let isProcessing = false;

  async function ask(prompt: string) {
    isProcessing = true;
    rl.pause();

    process.stdout.write('Claude is thinking...');
    const stream = query({ prompt, options });

    let firstChunk = true;
    for await (const msg of stream) {
      const content = (msg as any).message?.content || (msg as any).content;
      if (Array.isArray(content)) {
        for (const block of content) {
          if (block.type === 'text' && block.text) {
            if (firstChunk) {
              process.stdout.write('\r\x1b[K');
              process.stdout.write('Claude: ');
              firstChunk = false;
            }
            process.stdout.write(block.text);
          }
        }
      }
    }
    process.stdout.write('\n\n');

    isProcessing = false;
    rl.resume();
    rl.prompt();
  }

  rl.on('line', async (line) => {
    if (isProcessing) return;

    const input = line.trim();
    if (input === 'exit') {
      rl.close();
      process.exit(0);
    }
    if (input) await ask(input);
    else rl.prompt();
  });

  await ask('What can you help me with?');
}
```

### 8. Run the application

No description provided.
```python
if __name__ == "__main__":
    asyncio.run(chat_with_remote_mcp())
```

```typescript
try {
  await chat();
} catch (error) {
  console.error(error);
  process.exit(1);
}
```

## Complete Code

```python
import asyncio
from claude_agent_sdk import ClaudeSDKClient, ClaudeAgentOptions
import os
from composio import Composio
from dotenv import load_dotenv

load_dotenv()

async def chat_with_remote_mcp():
    api_key = os.getenv("COMPOSIO_API_KEY")
    if not api_key:
        raise RuntimeError("COMPOSIO_API_KEY is not set")

    composio = Composio(api_key=api_key)

    # Create Tool Router session for Appcircle
    mcp_server = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["appcircle"]
    )

    url = mcp_server.mcp.url

    if not url:
        raise ValueError("Session URL not found")

    # Configure remote MCP server for Claude
    options = ClaudeAgentOptions(
        permission_mode="bypassPermissions",
        mcp_servers={
            "composio": {
                "type": "http",
                "url": url,
                "headers": {
                    "x-api-key": os.getenv("COMPOSIO_API_KEY")
                }
            }
        },
        system_prompt="You are a helpful assistant with access to Appcircle tools via Composio.",
        max_turns=10
    )

    # Create client with context manager
    async with ClaudeSDKClient(options=options) as client:
        print("\nChat started. Type 'exit' or 'quit' to end.\n")

        # Main chat loop
        while True:
            user_input = input("You: ").strip()
            if user_input.lower() in {"exit", "quit"}:
                print("Goodbye!")
                break

            # Send query
            await client.query(user_input)

            # Receive and print response
            print("Claude: ", end="", flush=True)
            async for message in client.receive_response():
                if hasattr(message, "content"):
                    for block in message.content:
                        if hasattr(block, "text"):
                            print(block.text, end="", flush=True)
            print()

if __name__ == "__main__":
    asyncio.run(chat_with_remote_mcp())
```

```typescript
import 'dotenv/config';
import readline from 'node:readline';
import { Composio } from '@composio/core';
import { query, type Options } from "@anthropic-ai/claude-agent-sdk";

async function chat() {
  const { COMPOSIO_API_KEY, USER_ID } = process.env;
  if (!COMPOSIO_API_KEY || !USER_ID) {
    throw new Error('COMPOSIO_API_KEY and USER_ID required in .env');
  }

  const composio = new Composio({ apiKey: COMPOSIO_API_KEY });
  const session = await composio.create(USER_ID, {
    toolkits: ['appcircle']
  });
  const mcp_url = session?.mcp.url;

  const options: Options = {
    permissionMode: 'bypassPermissions',
    mcpServers: {
      composio: {
        type: 'http',
        url: mcp_url,
        headers: { 'x-api-key': COMPOSIO_API_KEY }
      }
    },
    systemPrompt: 'You are a helpful assistant with access to Appcircle tools via Composio.',
    maxTurns: 10,
  };

  const rl = readline.createInterface({
    input: process.stdin,
    output: process.stdout,
    prompt: 'You: '
  });

  console.log('\nChat started. Type "exit" to quit.\n');

  let isProcessing = false;

  async function ask(prompt: string) {
    isProcessing = true;
    rl.pause();

    process.stdout.write('Claude is thinking...');
    const stream = query({ prompt, options });

    let firstChunk = true;
    for await (const msg of stream) {
      const content = (msg as any).message?.content || (msg as any).content;
      if (Array.isArray(content)) {
        for (const block of content) {
          if (block.type === 'text' && block.text) {
            if (firstChunk) {
              process.stdout.write('\r\x1b[K');
              process.stdout.write('Claude: ');
              firstChunk = false;
            }
            process.stdout.write(block.text);
          }
        }
      }
    }
    process.stdout.write('\n\n');

    isProcessing = false;
    rl.resume();
    rl.prompt();
  }

  rl.on('line', async (line) => {
    if (isProcessing) return;

    const input = line.trim();
    if (input === 'exit') {
      rl.close();
      process.exit(0);
    }
    if (input) await ask(input);
    else rl.prompt();
  });

  await ask('What can you help me with?');
}

try {
  await chat();
} catch (error) {
  console.error(error);
  process.exit(1);
}
```

## Conclusion

You've successfully built a Claude Agent SDK agent that can interact with Appcircle through Composio's Tool Router.
Key features:
- Native MCP support through Claude's agent framework
- Streaming responses for real-time interaction
- Permission bypass for smooth automated workflows
You can extend this by adding more toolkits, implementing custom business logic, or building a web interface around the agent.

## How to build Appcircle MCP Agent with another framework

- [OpenAI Agents SDK](https://composio.dev/toolkits/appcircle/framework/open-ai-agents-sdk)
- [Claude Code](https://composio.dev/toolkits/appcircle/framework/claude-code)
- [Claude Cowork](https://composio.dev/toolkits/appcircle/framework/claude-cowork)
- [Codex](https://composio.dev/toolkits/appcircle/framework/codex)
- [OpenClaw](https://composio.dev/toolkits/appcircle/framework/openclaw)
- [Hermes](https://composio.dev/toolkits/appcircle/framework/hermes-agent)
- [CLI](https://composio.dev/toolkits/appcircle/framework/cli)
- [Google ADK](https://composio.dev/toolkits/appcircle/framework/google-adk)
- [LangChain](https://composio.dev/toolkits/appcircle/framework/langchain)
- [Vercel AI SDK](https://composio.dev/toolkits/appcircle/framework/ai-sdk)
- [Mastra AI](https://composio.dev/toolkits/appcircle/framework/mastra-ai)
- [LlamaIndex](https://composio.dev/toolkits/appcircle/framework/llama-index)
- [CrewAI](https://composio.dev/toolkits/appcircle/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.
- [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.
- [Bolt iot](https://composio.dev/toolkits/bolt_iot) - Bolt IoT is a platform for building and managing IoT projects with cloud-based device control and monitoring. It makes connecting sensors and actuators to the internet seamless for automation and data insights.

## Frequently Asked Questions

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

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

### Can I use Tool Router MCP with Claude Agent SDK?

Yes, you can. Claude Agent SDK 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 Appcircle tools.

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

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

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