Agimus MCP Server

Connects AI coding tools (Claude Desktop, Claude Code, Cursor, OpenAI Codex and other Model Context Protocol clients) to the Agimus data platform. The server gives the AI live awareness of your ontology (entities, properties, links, categories, types), reads of live data as object sets, and the Agimus Python SDK reference, so it writes correct code instead of guessing field names. There is no dataset surface: every read is an entity of the ontology.

What the AI gets

Tools (13)

Discovery:

Read (read-only; bulk and writes happen through the SDK in user code):

Every read is one object set: an entity and ordered steps (filter, pivot, with, top); a filter is a clause, and/or/not, or a link predicate ({"link": L, "any": F}, {"link": L, "none": F}). The steps parameter's description carries the grammar.

The related objects of one object are a filter on its key and a pivot. Every set tool takes an optional plane (operational or analytical) to choose which plane serves the set; the platform chooses when it is omitted, and a plane that cannot serve the set is refused at once with the entity named.

Resources

• agimus://schema/entities/{entity}: live, full schema for one entity
• agimus://docs/sdk-reference: the full Agimus Python SDK reference (sourced directly from the SDK's README so it never drifts)

Install & configure

The recommended path is uvx: it auto-installs the latest version on first run and keeps it isolated. No prior pip install is required.

Claude Code

Add to ~/.claude/claude_code_config.json:

{
  "mcpServers": {
    "agimus": {
      "command": "uvx",
      "args": ["agimus-mcp"],
      "env": { "AGIMUS_API_KEY": "agm_your_api_key_here" }
    }
  }
}

Cursor

Create .cursor/mcp.json in your project root:

{
  "mcpServers": {
    "agimus": {
      "command": "uvx",
      "args": ["agimus-mcp"],
      "env": { "AGIMUS_API_KEY": "agm_your_api_key_here" }
    }
  }
}

OpenAI Codex

Add to ~/.codex/config.toml:

[mcp_servers.agimus]
command = "uvx"
args = ["agimus-mcp"]
env = { AGIMUS_API_KEY = "agm_your_api_key_here" }

Claude Desktop

Add to claude_desktop_config.json (Claude → Settings → Developer → Edit Config):

{
  "mcpServers": {
    "agimus": {
      "command": "uvx",
      "args": ["agimus-mcp"],
      "env": { "AGIMUS_API_KEY": "agm_your_api_key_here" }
    }
  }
}

Alternative install: pip

If you prefer a pinned global install:

pip install agimus-mcp

Then replace "command": "uvx", "args": ["agimus-mcp"] with "command": "agimus-mcp" in any config above.

CLI options

agimus-mcp [--api-key agm_xxx] [--base-url URL] [--timeout SECONDS] [--log-level LEVEL]

Every flag has an environment-variable equivalent:

Logs are written to stderr; stdout is reserved for the MCP stdio protocol.

Requires Python 3.10 or later and the agimus SDK 1.x, which it installs.

License

MIT