Connect MCP servers to FastClaw agents
Give FastClaw agents external tools through the Model Context Protocol — add http or stdio MCP servers per agent from the console.
Per-agent servers
Each agent has its own MCP list, so tools stay scoped to the agents that should have them.
http and stdio
Connect remote servers by URL with optional headers, or launch local servers as subprocesses with a command, args and env.
Alongside skills
MCP tools sit next to built-in tools, installed skills and plugins in every conversation.
What you can do
- Let a team agent query your databases, ticketing or internal APIs — see FastClaw for teams.
- Extend an agent beyond its skills with any MCP-compatible tool server.
- Run tool-heavy work safely by combining MCP with a Docker or E2B sandbox.
Set it up
- Open the agent in the console and go to its MCP tab.
- Click Add server, give it a name and choose a type:
- http — enter the URL and optional headers (one
KEY=VALUEper line). - stdio — enter the command, arguments and environment variables.
- http — enter the URL and optional headers (one
- Save. The server's tools are available to the agent in its next conversation.
Notes
MCP is part of FastClaw's skills and tools system.
Frequently asked questions
More Integrations
All IntegrationsE2B
Run every FastClaw agent command in an isolated E2B cloud sandbox — skills and workspace hydrated in, files synced back after each call.
Docker
Use Docker as FastClaw's sandbox backend to isolate agent commands on your own hardware — or deploy FastClaw itself with Docker Compose.
PostgreSQL
Swap FastClaw's default SQLite file for PostgreSQL to run multiple pods behind a load balancer, with automatic schema migrations.
Try it on your own agents
Start free in FastClaw Cloud, or self-host the single binary in a minute.