search_entities

Instructions

Implementation Reference

• graphite_mcp/server.py:50-62 (schema)

  Tool definition (schema) for search_entities: defines name, description, and inputSchema with 'query' (required), 'entity_type', 'sector', and 'limit' (optional) parameters.

  Tool(
      name="search_entities",
      description="Search the financial knowledge graph for companies, people, patents by name, ticker, or description. Example: search_entities(query='NVIDIA') or search_entities(query='semiconductor', sector='semiconductors')",
      inputSchema={
          "type": "object",
          "properties": {
              "query": {"type": "string", "description": "Search query (name, ticker, or keyword)"},
              "entity_type": {"type": "string", "description": "Filter by type", "enum": ["company", "person", "patent", "product", "regulation", "event"]},
              "sector": {"type": "string", "description": "Filter by sector: semiconductors, software, pharma, etc."},
              "limit": {"type": "integer", "description": "Max results (default 20)", "default": 20},
          },
          "required": ["query"],
      },

• graphite_mcp/server.py:50-63 (registration)

  Registration: search_entities is included as a Tool in the list returned by the @server.list_tools() handler, making it available to MCP clients.

  Tool(
      name="search_entities",
      description="Search the financial knowledge graph for companies, people, patents by name, ticker, or description. Example: search_entities(query='NVIDIA') or search_entities(query='semiconductor', sector='semiconductors')",
      inputSchema={
          "type": "object",
          "properties": {
              "query": {"type": "string", "description": "Search query (name, ticker, or keyword)"},
              "entity_type": {"type": "string", "description": "Filter by type", "enum": ["company", "person", "patent", "product", "regulation", "event"]},
              "sector": {"type": "string", "description": "Filter by sector: semiconductors, software, pharma, etc."},
              "limit": {"type": "integer", "description": "Max results (default 20)", "default": 20},
          },
          "required": ["query"],
      },
  ),

• graphite_mcp/server.py:145-151 (handler)

  Handler: when the tool name is 'search_entities', it calls the central REST API endpoint /api/v1/search with the query, entity_type, sector, and limit parameters.

  if name == "search_entities":
      result = await _get("/search", params={
          "q": arguments["query"],
          "type": arguments.get("entity_type"),
          "sector": arguments.get("sector"),
          "limit": arguments.get("limit", 20),
      })

• graphite_mcp/server.py:38-42 (helper)

  Helper function _get: used by the search_entities handler to make the actual HTTP GET request to the central server.

  async def _get(path: str, params: Optional[dict] = None) -> dict:
      async with httpx.AsyncClient(timeout=30) as client:
          resp = await client.get(_url(path), params=params, headers=_headers())
          resp.raise_for_status()
          return resp.json()