outlty-mcp
Provides tools to interact with a FastAPI backend that uses API-key authentication, enabling listing, retrieving, creating user APIs, and making requests to those APIs.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@outlty-mcpList my user APIs"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
outlty-mcp
A Python MCP server exposing your FastAPI API-key routes as MCP tools for use in Claude Code (and any MCP client).
Tools
list_user_apis
get_user_api
create_user_api
make_request
Related MCP server: OpenAPI MCP Server
Prerequisites
Python 3.10+
Your backend running and accessible (default base URL: http://localhost:8000)
An API key valid for the backend. The backend supports either:
X-API-Key: <key>Authorization: ApiKey <key>
Install
python -m venv .venv
source .venv/bin/activate
pip install -r requirements.txtRun with uvx (recommended)
You can run this server without a local install using uv.
Local checkout:
uvx --from . outlty-mcpFrom Git repository (example):
uvx --from git+https://github.com/your-org/outly-mcp-server.git outlty-mcpYou can also pin a version published to an index:
uvx outlty-mcpRun (standalone debug)
This server communicates via stdio when launched by an MCP client, but you can validate it imports:
python server.pyConfiguration (env)
OUTLY_MCP_API_BASE_URL(default:http://localhost:8000)OUTLY_MCP_API_KEY(required)OUTLY_MCP_AUTH_HEADER(default:X-API-Key; set toAuthorizationto sendAuthorization: ApiKey <key>)
Claude Code configuration (JSON)
Add this to your Claude configuration (e.g., ~/.config/anthropic/claude_desktop_config.json or the workspace .claued.json depending on your setup). See Claude docs for exact location.
{
"mcpServers": {
"outlty-mcp": {
"command": "uvx",
"args": ["outlty-mcp"],
"env": {
"OUTLY_MCP_API_BASE_URL": "http://localhost:8000",
"OUTLY_MCP_API_KEY": "ak_xxx_your_secret",
"OUTLY_MCP_AUTH_HEADER": "X-API-Key"
}
}
}
}If you prefer Authorization header:
{
"mcpServers": {
"outlty-mcp": {
"command": "uvx",
"args": ["outlty-mcp"],
"env": {
"OUTLY_MCP_API_BASE_URL": "http://localhost:8000",
"OUTLY_MCP_API_KEY": "ak_xxx_your_secret",
"OUTLY_MCP_AUTH_HEADER": "Authorization"
}
}
}
}Tool schemas
list_user_apis: GET
/api-key/user-apisget_user_api(id: string): GET
/api-key/user-apis/{id}create_user_api(user_query: string): POST
/api-key/user-apismake_request(url: string, input_data: object): POST
/api-key/user-apis/make-request
This server cannot be deployed
Maintenance
Related MCP Connectors
The OpenRouter for tools. One MCP connection gives any AI agent 254 hosted tools, pay per call.
Zero-setup MCP gateway securely connecting AI to your tools with authentication and workflows
MCP server that lets AI assistants use all OneSchema features exposed via the public API.
Give any MCP-compatible AI assistant a builder for live, hosted web tools and workflows.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceWraps FastAPI REST endpoints as MCP tools, enabling natural language interaction with user management, task management, and mathematical calculations through Gemini CLI.1-
- AlicenseNot gradedqualityDmaintenanceExposes OpenAPI endpoints as MCP tools, enabling LLMs to discover and interact with REST APIs through the MCP protocol.5 npmMIT
- AlicenseNot gradedqualityBmaintenanceExposes FastAPI routes as MCP tools with auto-discovery, Pydantic schema extraction, and built-in observability.Apache 2.0
- FlicenseNot gradedqualityDmaintenanceEnables LLM-powered agents to securely communicate with and orchestrate downstream microservices via FastAPI endpoints exposed as MCP tools.-