Fastclaw MCP Server

Fastclaw MCP server exists for a simple reason — assistants are far more useful when they can act on Fastclaw directly instead of describing what you should do. Multi-Agent Framework.

What you get

Platform admin: agents, models, skills, users, API keys

FastClaw is an Agent Factory — it creates, manages, and runs AI agents. Each agent has its own personality (SOUL.md), memory, skills, and tools. FastClaw handles the LLM communication, tool execution, sandbox isolation, and session management.

What the assistant can call

Once Fastclaw is connected, these are the calls the assistant has available:

• Built-in — exec, read_file, write_file, list_dir, web_fetch, web_search, memory_search
• OpenAI — compatible /v1/chat/completions (streaming)
• Per — agent scheduler /api/agents/{id}/cron (list / toggle / delete)
• App — user provisioning POST /v1/users — third-party apps mint a stable fastclaw user_id per end-user, idempotent on (api_key, external_id). Or pass user
• Channels — The Channels tool exposed by this server
• Skills — The Skills tool exposed by this server
• Memory — The Memory tool exposed by this server
• Local — The Local tool exposed by this server
• Commands — The Commands tool exposed by this server
• Kubernetes — No config file is mounted — bootstrap is env-only. See deploy/k8s/ for full manifests

Configuration and credentials

You will need 2 environment variables: FASTCLAW_STORAGE_DSN, OPENAI_API_KEY. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

Setting it up

Being a remote server, there is no local install. You register the endpoint with your client, authorise it once, and the tools appear.

Choosing this one

Among the cloud and infrastructure options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Fastclaw's toolset — Built-in, OpenAI, Per and 7 more — is a fair guide to whether it matches your workflow. It is maintained by fastclaw-ai; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Before you rely on it

• Your data travels to the provider's service, so the usual questions apply about what you send and what they retain.
• With 10 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Fastclaw.
• Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
• MCP clients confirm each tool call by default. Leave that on until you have watched what the fastclaw mcp server does with a few real requests.