Back to Browse

Agentic Research Engine Oss MCP Server

Developer ToolsLow Risk8.5MCP RegistryLocal
Free

Server data from the Official MCP Registry

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

About

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

Security Report

8.5
Low Risk8.5Low Risk

Valid MCP server (2 strong, 4 medium validity signals). 3 known CVEs in dependencies Package registry verified. Imported from the Official MCP Registry.

14 files analyzed · 4 issues found

Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.

Permissions Required

This plugin requests these system permissions. Most are normal for its category.

file_system

Check that this permission is expected for this type of plugin.

env_vars

Check that this permission is expected for this type of plugin.

What You'll Need

Set these up before or after installing:

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

Environment variable: OPENAI_BASE_URL

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

Environment variable: OPENAI_API_KEY

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

Environment variable: MODEL_SYNTHESIZER

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

Environment variable: MODEL_PLANNER

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

Environment variable: EMBED_MODEL

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

Environment variable: SEARXNG_URL

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

Environment variable: LOCAL_CORPUS_PATH

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

Environment variable: ENABLE_RERANK

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

Environment variable: ENABLE_FETCH

How to Install

Add this to your MCP configuration file:

{
  "mcpServers": {
    "io-github-theaisingularity-agentic-research": {
      "env": {
        "EMBED_MODEL": "your-embed-model-here",
        "SEARXNG_URL": "your-searxng-url-here",
        "ENABLE_FETCH": "your-enable-fetch-here",
        "ENABLE_RERANK": "your-enable-rerank-here",
        "MODEL_PLANNER": "your-model-planner-here",
        "OPENAI_API_KEY": "your-openai-api-key-here",
        "OPENAI_BASE_URL": "your-openai-base-url-here",
        "LOCAL_CORPUS_PATH": "your-local-corpus-path-here",
        "MODEL_SYNTHESIZER": "your-model-synthesizer-here"
      },
      "args": [
        "agentic-research-engine"
      ],
      "command": "uvx"
    }
  }
}

Reviews

No reviews yet

Be the first to review this server!