APIWeaver + mcp-use: Complete MCP Integration

APIWeaver is a MCP server that An MCP server that dynamically creates MCP servers from web API configurations. This allows you to easily integrate any REST API, GraphQL endpoint, or web service into an MCP-compatible tool that can be used by AI assistants like Claude..

When integrated with mcp-use, you can:

• Register and configure APIs at runtime without server restart
• Support for REST APIs, GraphQL endpoints, and web services
• Multiple authentication methods for different API requirements

This guide provides step-by-step instructions to set up APIWeaver in mcp-use, including configuration, examples, and troubleshooting.

What You'll Achieve

After completing this setup:

• APIWeaver will be fully integrated and operational
• You can use APIWeaver tools directly in mcp-use
• All APIWeaver capabilities will be available for your workflows
• Access to 6 different tools

Prerequisites

Before starting, ensure you have:

• mcp-use installed and configured
• Compatible operating system (Python 3.8+, Node.js 16+, pip Installation, npm/yarn Installation)

Installation

Step 1: Install APIWeaver

Configuration

Step 2: Configure mcp-use

1. Open mcp-use settings
2. Navigate to MCP server configuration
3. Add APIWeaver server with appropriate settings
4. Save and restart if needed

Examples

Once configured, you can use APIWeaver in mcp-use:

Register REST API with Authentication

Add a REST API with Bearer token authentication

Ask mcp-use: "Register the JSONPlaceholder API (https://jsonplaceholder.typicode.com) with GET and POST methods"

Expected Result: API registered successfully with auto-generated tools for posts, users, and comments endpoints

GraphQL Endpoint Integration

Connect to a GraphQL API for data querying

Ask mcp-use: "Register the GitHub GraphQL API with authentication and create tools for repository queries"

Expected Result: GraphQL endpoint configured with query tools for repositories, issues, and user data

API Testing and Validation

Test API connectivity before integration

Ask mcp-use: "Test connection to the Stripe API with my API key before registering it"

Expected Result: Connection test successful with API schema validation and endpoint verification

Multi-API Workflow

Integrate multiple APIs for complex workflows

Ask mcp-use: "Register both Twitter API and SendGrid API to create a workflow for social media monitoring and email alerts"

Expected Result: Both APIs registered with tools for tweet monitoring, email sending, and automated workflow execution

Testing Your Setup

1. Launch mcp-use
2. Verify APIWeaver is available in the tools list
3. Test basic APIWeaver functionality

Troubleshooting

Common Issues

API Registration Failed

Symptoms: Registration errors, Invalid API configuration, Connection timeouts

Cause: Incorrect API URL, authentication issues, or network problems

Solution:

• Verify API endpoint URL is accessible
• Check authentication credentials are valid
• Test API manually with curl or Postman first
• Ensure network connectivity and firewall settings

Authentication Not Working

Symptoms: 401 Unauthorized, 403 Forbidden, Auth token invalid

Cause: Incorrect authentication method or invalid credentials

Solution:

• Verify authentication method matches API requirements
• Check API key/token is not expired
• Confirm header format and parameter names
• Test authentication with API documentation examples

Transport Mode Not Connecting

Symptoms: Connection refused, Transport errors, Client not recognizing server

Cause: Incorrect transport configuration or port conflicts

Solution:

• Use streamable-http for modern clients
• Check port is not in use: netstat -an | grep :8000
• Verify host/port settings match client configuration
• Try different transport modes (stdio/http/sse)

Python Dependencies Missing

Symptoms: Import errors, Module not found, Package installation failures

Cause: Missing Python packages or virtual environment issues

Solution:

• Install requirements: pip install -r requirements.txt
• Create virtual environment: python -m venv apiweaver-env
• Activate environment before installation
• Upgrade pip: python -m pip install --upgrade pip

API Schema Generation Failed

Symptoms: Tool generation errors, Schema parsing failures, Endpoint mapping issues

Cause: Unsupported API format or incomplete API documentation

Solution:

• Provide OpenAPI/Swagger specification if available
• Start with simple GET endpoints first
• Manually configure complex APIs step by step
• Check API documentation for required parameters

Connection Refused or Server Unreachable

Symptoms: ECONNREFUSED error, Connection timeout, Cannot reach server

Cause: MCP server not running or incorrect URL

Solution:

• Verify MCP server is running and accessible
• Check server URL is correct (protocol, host, port, path)
• Test server URL in browser or with curl to confirm it responds
• Ensure firewall allows connections to server port
• Verify CORS settings if accessing from browser

Import Errors or Module Not Found

Symptoms: ModuleNotFoundError: mcp_use, Cannot find module "mcp-use"

Cause: Package not installed or wrong environment

Solution:

• Verify installation: pip show mcp-use (Python) or npm list mcp-use (JS)
• Ensure using correct Python virtual environment or Node.js project
• Reinstall package: pip install --upgrade mcp-use or npm install mcp-use
• Check package.json or requirements.txt includes mcp-use

Tool Discovery Returns Empty List

Symptoms: list_tools() returns [], No tools available, Tools not found

Cause: MCP server not properly configured or not exposing tools

Solution:

• Verify MCP server is properly initialized and configured
• Check server logs to confirm tools are registered
• Test server directly with MCP inspector or test client
• Ensure server implements MCP protocol correctly
• Verify transport type (HTTP/SSE) matches server configuration

Tool Execution Fails or Returns Errors

Symptoms: Tool call throws exception, Invalid arguments error, Execution timeout

Cause: Incorrect arguments or server-side execution failure

Solution:

• Verify tool arguments match schema definition from list_tools()
• Check required arguments are provided with correct types
• Review server logs for detailed error messages
• Test tool with minimal valid arguments first
• Increase timeout if tool requires longer execution time

LangChain.js Integration Not Working

Symptoms: getLangChainTools() fails, Tools not recognized by agent, Type errors

Cause: Version mismatch or incorrect integration setup

Solution:

• Ensure LangChain.js version is compatible with mcp-use
• Verify TypeScript version meets requirements
• Check tool schema conversion is working correctly
• Use latest versions of both mcp-use and LangChain.js
• Review LangChain.js documentation for agent setup

Transport Type Errors (HTTP vs SSE)

Symptoms: SSE connection fails, HTTP polling not working, Event stream errors

Cause: Mismatch between client transport and server capabilities

Solution:

• Verify server supports the transport type you are using
• Try alternative transport: switch between "http" and "sse"
• Check server documentation for supported transport types
• For SSE, ensure server sends proper Content-Type: text/event-stream
• For HTTP, verify server accepts POST requests with JSON payload

APIWeaver not appearing in mcp-use

Symptoms: Server not listed, Tools not available

Cause: Configuration or installation issue

Solution:

• Verify configuration syntax
• Check APIWeaver installation
• Restart mcp-use
• Check logs for error messages

Next Steps

Now that APIWeaver is integrated with mcp-use:

• Explore all APIWeaver capabilities through mcp-use
• Check out other MCP servers that work with mcp-use
• Join the MCP community for tips and support
• Consider contributing to APIWeaver development

Need Help?

• Search for APIWeaver documentation
• Check the mcp-use MCP guide
• Join the MCP community discussions