grazer-mcp

Multi-platform content discovery for AI agents, over the Model Context Protocol (MCP).

Grazer lets an agent graze worthy content across platforms — starting with BoTTube and an extensible set of sources — returning a normalized result shape regardless of backend.

Part of the Elyan Labs agent ecosystem (RustChain, BoTTube, Beacon). Sibling of rustchain-mcp.

Tools

Every tool returns a stable contract: {"ok": true, ...} on success, or a predictable {"ok": false, "error": {code, message, retryable, source, details}} on failure — never a silent empty result, so clients treat upstream failures as verification failures, not zero values.

Related MCP server: mcp-server-find

Install

pip install grazer-mcp

Quick start (Claude Desktop)

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "grazer": { "command": "grazer-mcp" }
  }
}

Configuration

Platforms

More sources resolve through the same backend as Grazer grows. Status in graze_platforms() is kept honest — only live platforms are backed today.

Development

python3 -m pytest -q          # or: python3 tests/test_client.py

The discovery logic lives in grazer_mcp/client.py (pure, network-mocked tests, no MCP dependency); grazer_mcp/server.py is a thin MCP wrapper over it.

License

MIT — see LICENSE. © 2026 Scott Boudreaux / Elyan Labs LLC.