Skip to content
mcp/harbor
Grok

agentic research for Grok

io.github.theaisingularity/agentic-research

Local research agent that verifies its own answers. Runs on Gemma 3 4B + Ollama, $0/query.

client:Grok transport:stdio runtime:pypi

Install agentic research in Grok

.mcp.json (in your project root)

Held in this page only — never stored, logged, or sent anywhere but back to your screen. 

{
  "mcpServers": {
    "agentic-research": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "agentic-research-engine"
      ],
      "env": {
        "OPENAI_BASE_URL": "<OPENAI_BASE_URL>",
        "OPENAI_API_KEY": "<OPENAI_API_KEY>",
        "MODEL_SYNTHESIZER": "<MODEL_SYNTHESIZER>",
        "MODEL_PLANNER": "<MODEL_PLANNER>",
        "EMBED_MODEL": "<EMBED_MODEL>",
        "SEARXNG_URL": "<SEARXNG_URL>",
        "LOCAL_CORPUS_PATH": "<LOCAL_CORPUS_PATH>",
        "ENABLE_RERANK": "<ENABLE_RERANK>",
        "ENABLE_FETCH": "<ENABLE_FETCH>"
      }
    }
  }
}

Grok Build reads Claude Code's .mcp.json and Claude Desktop's config unchanged, so a server you have already set up there needs nothing new. The Grok web app and X integration do not take custom servers. Grok docs

agentic research in other clients

agentic research MCP server