PluginBench
MCP Server
Maintained
MIT

io.github.TheAiSingularity/agentic-research MCP Server

io.github.TheAiSingularity/agentic-research

What is the io.github.TheAiSingularity/agentic-research MCP server?

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

How to install io.github.TheAiSingularity/agentic-research

Copy-paste configuration for popular MCP clients.

transport: stdio
Config generated by PluginBench — verify against the source before use.
Environment / auth
  • OPENAI_BASE_URL

    Any OpenAI-compatible endpoint. Default: OpenAI cloud. Use http://localhost:11434/v1 for Ollama.

  • OPENAI_API_KEY
    secret

    API key for the endpoint above. Use 'ollama' as a sentinel value when running locally against Ollama.

  • MODEL_SYNTHESIZER

    Model identifier used for the synthesize node. Defaults to 'gpt-5-mini'; set to 'gemma3:4b' for Mac-local Ollama.

  • MODEL_PLANNER

    Model for the plan / classify / critic / compress / verify nodes. Defaults to 'gpt-5-nano'.

  • EMBED_MODEL

    Embedding model identifier (for retrieval + memory). Default 'text-embedding-3-small'; use 'nomic-embed-text' on Ollama.

  • SEARXNG_URL

    Base URL of the SearXNG meta-search instance. Default http://localhost:8888.

  • LOCAL_CORPUS_PATH

    Path to an index directory built via scripts/index_corpus.py. When set, local corpus hits augment web search.

  • ENABLE_RERANK

    Set to '1' to enable the BAAI/bge-reranker-v2-m3 cross-encoder rerank stage. First run downloads ~560MB.

  • ENABLE_FETCH

    Set to '0' to skip the trafilatura full-page fetch stage. Default '1'.

~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "agentic-research": {
      "command": "agentic-research-mcp",
      "args": [
        "agentic-research-engine"
      ],
      "env": {
        "OPENAI_BASE_URL": "<YOUR_OPENAI_BASE_URL>",
        "OPENAI_API_KEY": "<YOUR_OPENAI_API_KEY>",
        "MODEL_SYNTHESIZER": "<YOUR_MODEL_SYNTHESIZER>",
        "MODEL_PLANNER": "<YOUR_MODEL_PLANNER>",
        "EMBED_MODEL": "<YOUR_EMBED_MODEL>",
        "SEARXNG_URL": "<YOUR_SEARXNG_URL>",
        "LOCAL_CORPUS_PATH": "<YOUR_LOCAL_CORPUS_PATH>",
        "ENABLE_RERANK": "<YOUR_ENABLE_RERANK>",
        "ENABLE_FETCH": "<YOUR_ENABLE_FETCH>"
      }
    }
  }
}

Related MCP servers

17 Base data tools for agents over Streamable HTTP MCP. Pay per call in USDC via x402; no API key.

Runtime constitutional verification for AI answers with transparent reasoning chains and audit trails.

11
TypeScript
Apache-2.0
View repository →

Verified AI-tool prices and AI product margin math for agents.

0
TypeScript
MIT
View repository →

Will a local LLM run on your hardware? GGUF quant, buy-vs-rent-vs-API cost, used-GPU prices.

Delegate real-world actions from Claude Code, Codex, and other agents to Hermes Agent.

1
TypeScript
MIT
View repository →

Amazon Seller Central + Ads: settlement-accurate P&L, full PPC, every write staged for approval.

1
MIT
View repository →