Fastn

Provides 250+ connectors and tools with managed OAuth 2.1 authentication for secure, scalable MCP access.
  • python

13

GitHub Stars

python

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

You can deploy and use the Fastn MCP Server to securely connect AI agents and applications to 250+ enterprise services, manage authentication, and run multi-step tool workflows with sub-second latency.

How to use

Install and run the MCP server, then point your MCP client at the hosted endpoint or start a self-hosted instance to begin discovering and executing tools.

If you use the hosted server, connect to the MCP HTTP transport at the provided shttp URL and let the server handle OAuth 2.1 authentication for you. If you prefer a self-hosted setup, run the local MCP server and expose it via standard transports (stdio, SSE, or Streamable HTTP) to your MCP client.

How to install

Prerequisites: you need Python and a working environment for Python projects, plus Docker if you plan to deploy with containers.

To run a hosted instance, you don’t install anything locally—your client communicates with the hosted endpoint directly.

To self-host, install the server package and start the MCP service using the provided CLI commands.

pip install fastn-mcp-server
fastn-mcp --shttp --port 8000

Additional configuration and usage notes

The MCP server supports three authentication methods. Use MCP OAuth 2.1 for standard flows, or pass a Fastn auth token or API key for token-based access. You can also run the server without authentication for local development.

Transport options include stdio for local clients, SSE for streaming HTTP, and Streamable HTTP for remote deployments. You can run with a pre-set project or skill to streamline tool usage, and you can manage flows to compose multiple tools into automation.

To expose OAuth metadata publicly for remote deployments, start the server with a public URL and ensure OAuth endpoints resolve at the well-known path.

Security and deployment notes

The server is designed for enterprise-grade security with managed authentication, audit trails, and access governance. Use the provided configurations to enable OAuth 2.1 and protect resources.

When running behind a reverse proxy or in production, use a real domain and ensure the OAuth metadata URL is reachable by clients. Disable auth only in development environments.

Troubleshooting tips

If clients cannot obtain OAuth metadata, verify the server URL configuration and ensure the OAuth endpoints are publicly reachable. Check that your client is pointing to the correct /shttp endpoint.

If a specific tool or connector is not appearing, use the tool discovery command to browse available connectors, then connect the desired ones before listing tools or running flows.

Available tools

find_tools

Search for available connector tools by natural language prompt. Returns matching tools with IDs and input schemas.

execute_tool

Execute a connector tool by its ID with parameters. Returns the result directly.

list_connectors

Browse all 250+ available connectors in the registry, including ones not yet connected.

list_skills

List available skills in the project.

list_projects

List available projects for the authenticated user.

list_flows

List saved automations (flows) in the project.

run_flow

Execute a saved flow by its ID.

delete_flow

Remove a flow from the project.

create_flow

Create a flow from natural language (under development).

update_flow

Update an existing flow (under development).

configure_custom_auth

Register a custom JWT auth provider (Auth0, Firebase, Supabase).

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational