Ashby MCP Server

Instructions

Implementation Reference

• src/ashby/server.py:407-434 (handler)

  The tool logic is handled dynamically by a generic `handle_call_tool` function that maps tool names to Ashby API endpoints via a mapping table. The tool `interview_plan_list` is mapped to `/interviewPlan.list`.

  @server.call_tool()
  async def handle_call_tool(name: str, arguments: dict[str, Any]) -> list[types.TextContent]:
      """Route tool calls to the correct Ashby endpoint, passing arguments directly."""
      endpoint = TOOL_ENDPOINT_MAP.get(name)
      if not endpoint:
          return [types.TextContent(type="text", text=f"Unknown tool: {name}")]
  
      try:
          # Pass arguments straight through -- tool schemas already use Ashby's
          # camelCase param names so no translation is needed.
          response = ashby.post(endpoint, data=arguments if arguments else None)
          return [types.TextContent(type="text", text=json.dumps(response, indent=2))]
      except requests.exceptions.HTTPError as e:
          error_body = ""
          if e.response is not None:
              try:
                  error_body = e.response.text
              except Exception:
                  pass
          return [
              types.TextContent(
                  type="text",
                  text=f"Ashby API error on {endpoint}: {e}\n{error_body}",
              )
          ]
      except Exception as e:
          return [types.TextContent(type="text", text=f"Error calling {endpoint}: {e}")]

• src/ashby/server.py:289-298 (schema)

  Tool definition for `interview_plan_list` in the `server.py` file.

  types.Tool(
      name="interview_plan_list",
      description="List all interview plans.",
      inputSchema={
          "type": "object",
          "properties": {
              "includeArchived": {"type": "boolean", "description": "Include archived plans"},
          },
      },
  ),