find_toolsLABSCO SUMMARY
Two tools instead of two hundred, which is the only way this scales.
Exposing 250 connectors as individual tools would bury a model. Search-then-execute keeps the surface small and moves the matching into the server, and the documented fallback — if find_tools returns nothing relevant, call list_connectors, because the connector may simply not be linked yet — saves the loop where the model concludes the capability does not exist. The narrower endpoint paths are worth using for coding assistants, where a smaller surface is the point.
What it is
A managed MCP gateway. Rather than exposing hundreds of tools at once, it exposes a discovery tool and an execution tool: describe what you need, get back matching connector tools with their input schemas, then call one by id.
What you get
- find_tools searches available connector tools by natural-language prompt and returns matches with ids and input schemas
- execute_tool runs one of those tools by id with your parameters and returns the result directly
- list_connectors browses the full registry, including connectors not yet connected — which is where you look when find_tools comes back empty
- list_skills and list_projects scope the session
- list_flows, run_flow and delete_flow manage saved multi-step automations; create_flow and update_flow are marked as under development
- configure_custom_auth registers a custom JWT provider such as Auth0, Firebase or Supabase
- The endpoint path decides the tool set: /shttp exposes all 11 tools, /shttp/tools exposes 5, and adding a project id or a skill id narrows it further to 4 or 3
Requirements
A Fastn account from app.fastn.ai with your connectors linked. The hosted endpoint at https://mcp.live.fastn.ai/shttp needs no install — authentication runs through MCP OAuth 2.1 automatically, or you can pass a token or API key in an Authorization header, optionally with x-project-id. The self-hosting instructions name fastn-mcp-server on PyPI, which does not have it; the self-hosted server then runs as fastn-mcp --shttp --port 8000, with FASTN_API_KEY and FASTN_PROJECT_ID for the stdio path.
Setup effort
Build from source — git clone https://github.com/fastn-ai/fastn-mcp.git
USE CASES
01
Doing something in a SaaS tool you have not wired up individually
Describe the action, get the matching tool and its schema, then execute it.
02
Finding out what is even available
The registry lists connectors including the ones you have not connected yet.
03
Running a saved automation
Flows compose several tools and run by id.
04
Keeping a coding assistant's tool list short
A narrower endpoint path exposes fewer tools to that client.
05
Using your own identity provider
Register a custom JWT provider rather than adopting a new login.
11 tools
Listed in project docs. Your client may show a different list.
execute_toollist_connectorslist_skillslist_projectslist_flowsrun_flowdelete_flowcreate_flowupdate_flowconfigure_custom_authBEFORE YOU INSTALL
What to know first
Tools you get
11 tools named in the project's documentation.
Requires
A client that can reach a remote MCP server over HTTP
Where it runs
Of the 3 documented clients, 1 runs the server on your machine and 2 connect to a hosted endpoint.
INSTALLATION
Connect your client
Server setup
From source
TERMINAL
git clone https://github.com/fastn-ai/fastn-mcp.git
cd fastn-mcp
python -m venv .venv
source .venv/bin/activate
pip install -e ".[dev]"Hosted endpoint
ENDPOINT URL
https://mcp.live.fastn.ai/shttpAdd this hosted endpoint to your MCP client.
MCP Clients
Claude Code
CLAUDE CODE · JSON
{
"mcpServers": {
"tools": {
"type": "http",
"url": "https://mcp.live.fastn.ai/shttp"
}
}
}Cursor
CURSOR · JSON
{
"mcpServers": {
"tools": {
"url": "https://mcp.live.fastn.ai/shttp/tools"
}
}
}Any MCP client — local stdio
ANY MCP CLIENT — LOCAL STDIO · JSON
{
"mcpServers": {
"tools": {
"command": "fastn-mcp",
"args": [
"--stdio"
],
"env": {
"FASTN_API_KEY": "<YOUR_FASTN_API_KEY>",
"FASTN_PROJECT_ID": "<YOUR_FASTN_PROJECT_ID>"
}
}
}
}
