What does the open mcp server do?

It connects Open to MCP-compatible AI assistants such as Claude and Cursor. Instead of copying data back and forth by hand, the assistant works with Open directly.

How do I install the open mcp server?

Register the server in your MCP client's configuration file and restart the client. This page carries ready-made configuration blocks for Claude Desktop, Claude Code and Cursor.

What credentials does it need?

It reads `ALLOWED_PATH`, `OPENAI_API_KEY`, `API_AUTH_TOKEN`, `DJANGO_SECRET_KEY`, `SWARM_CONFIG_PATH` from the environment. Store these in your client's env block or a secrets manager — never commit them to a repository — and grant the narrowest scope that still covers your use case.

Open MCP Server — Setup, Tools and Config Guide

What is the Open MCP server?

Open MCP server is a locally run integration for AI assistants that speak the Model Context Protocol. Open Swarm: Orchestrating AI Agent Swarms with Django.

What you get

As a CLI tool (swarm-cli): run blueprints locally, interactively or one-shot, and optionally compile them into standalone executables. 2. As an API service (swarm-api): serve blueprints over an OpenAI-compatible REST API (/v1/models, /v1/chat/completions, /v1/responses), so any OpenAI client — SDKs, chat UIs, integrations — can talk to your agents. The OpenAPI spec is served at /api/schema/ (with Swagger UI at /api/schema/swagger-ui/).

Setting it up

Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client. The configuration blocks on this page cover the common clients.

Configuration and credentials

You will need 5 environment variables: ALLOWED_PATH, OPENAI_API_KEY, API_AUTH_TOKEN, DJANGO_SECRET_KEY, SWARM_CONFIG_PATH. 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.

Before you rely on it

It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
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 open mcp server does with a few real requests.

Choosing this one

Plenty of developer tooling servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

How to install the Open MCP server

{
  "llm": {
    "default": {
      "provider": "openai",
      "model": "gpt-4o",
      "base_url": "https://api.openai.com/v1",
      "api_key": "${OPENAI_API_KEY}"
    },
    "local": {
      "provider": "ollama",
      "model": "llama3",
      "base_url": "http://localhost:11434"
    }
  },
  "mcpServers": {
    "filesystem": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-filesystem", "${ALLOWED_PATH}"],
      "env": { "ALLOWED_PATH": "${ALLOWED_PATH}" }
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

Variable	Description	Required
ALLOWED_PATH	Filesystem location the server is allowed to use.	Optional
OPENAI_API_KEY	Credential the server authenticates with.	Yes
API_AUTH_TOKEN	Credential the server authenticates with.	Yes
DJANGO_SECRET_KEY	Credential the server authenticates with.	Yes
SWARM_CONFIG_PATH	Filesystem location the server is allowed to use.	Optional

Open MCP Server

What is the Open MCP server?

What you get

Setting it up

Configuration and credentials

Before you rely on it

Choosing this one

How to install the Open MCP server

Configuration

Frequently asked questions

Alternatives to the Open MCP server

Context7

Playwright

GitHub

Linear

Git

Time