research_list
List research requests from Exa with pagination support. Use cursor and limit to control results.
Instructions
List research requests using Exa.
Tool call template
This tool declares no required parameters. Add optional parameters from the input schema as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {},
"name": "research_list"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| cursor | No | Pagination cursor from a previous response. | |
| limit | No | Maximum number of results to return. |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Implementation Reference
- src/mcp_exa/_server.py:517-549 (handler)The research_list tool handler function, registered via @mcp.tool() decorator. It accepts optional cursor and limit parameters, builds an arguments dict, and delegates to the remote Exa MCP server by calling _call_mcp_tool with the tool name 'exa_research_list'.
@mcp.tool() def research_list( cursor: str | None = None, limit: int | None = None, ) -> dict[str, Any]: """List research requests using Exa. Args: cursor: Pagination cursor from a previous response. limit: Maximum number of results to return. Returns: Dict containing the list of research requests. Example: >>> research_list(limit=10) {"data": [...], "has_more": true, "next_cursor": "..."} """ import asyncio arguments: dict[str, Any] = {} if cursor is not None: arguments["cursor"] = cursor if limit is not None: arguments["limit"] = limit try: result = asyncio.get_event_loop().run_until_complete( _call_mcp_tool("exa_research_list", arguments) ) return result except Exception as e: return {"error": str(e)} - src/mcp_exa/_server.py:517-517 (registration)The tool is registered as an MCP tool via the @mcp.tool() decorator on the FastMCP instance named 'mcp-exa'. The mcp instance is created at line 10 and exported via __init__.py.
@mcp.tool() - src/mcp_exa/_server.py:30-69 (helper)Helper function _call_mcp_tool that sends a JSON-RPC request to the public Exa MCP server. It is called by research_list with the tool name 'exa_research_list' and the arguments dict.
async def _call_mcp_tool(tool_name: str, arguments: dict[str, Any]) -> dict[str, Any]: """Call a tool on the public Exa MCP server.""" request = { "jsonrpc": "2.0", "id": 1, "method": "tools/call", "params": { "name": tool_name, "arguments": arguments, }, } async with httpx.AsyncClient(timeout=60.0) as client: response = await client.post( f"{BASE_URL}/mcp", json=request, headers={ "accept": "application/json, text/event-stream", "content-type": "application/json", }, ) response.raise_for_status() response_text = response.text lines = response_text.split("\n") for line in lines: if line.startswith("data: "): data = line[6:] result = {"jsonrpc": "2.0", "id": 1, "result": {}} try: parsed = eval(data) except Exception: pass else: if "result" in parsed and parsed["result"].get("content"): return { "results": parsed["result"]["content"][0].get("text", "") } return {"results": ""}