Agentic Research Engine MCP Server

by theaisingularityio.github.TheAiSingularity/agentic-researchv0.1.3

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

2Pythonstdioofficial registry

context tax

queued

security

queued

cold start

queued

freshness

Slowing6mo ago

Install Agentic Research Engine MCP server

claude mcp add agentic-research-engine -e OPENAI_API_KEY='<openai-api-key>' -- uvx agentic-research-engine

{
  "mcpServers": {
    "agentic-research-engine": {
      "command": "uvx",
      "args": [
        "agentic-research-engine"
      ],
      "env": {
        "OPENAI_API_KEY": "<openai-api-key>"
      }
    }
  }
}

Add to ~/.cursor/mcp.json (global) or .cursor/mcp.json (project).

{
  "mcpServers": {
    "agentic-research-engine": {
      "command": "uvx",
      "args": [
        "agentic-research-engine"
      ],
      "env": {
        "OPENAI_API_KEY": "<openai-api-key>"
      }
    }
  }
}

Settings → Developer → Edit Config (claude_desktop_config.json), then restart.

{
  "servers": {
    "agentic-research-engine": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "agentic-research-engine"
      ],
      "env": {
        "OPENAI_API_KEY": "<openai-api-key>"
      }
    }
  }
}

Add to .vscode/mcp.json in your workspace.

{
  "mcpServers": {
    "agentic-research-engine": {
      "command": "uvx",
      "args": [
        "agentic-research-engine"
      ],
      "env": {
        "OPENAI_API_KEY": "<openai-api-key>"
      }
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json.

Configuration

Variable	Required	Secret	Description
OPENAI_BASE_URL	—	—	Any OpenAI-compatible endpoint. Default: OpenAI cloud. Use http://localhost:11434/v1 for Ollama.
OPENAI_API_KEY	—	yes	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'.

Freshness

Slowing — last maintenance signal 6mo ago. The newest of the signals below sets the band.

Last commit (default branch)
2026-04-21 · 6mo ago · GitHub
Latest release
2026-04-20 · 6mo ago · GitHub · v0.1.3
Package published
no data · npm/PyPI
Registry entry updated
2026-04-20 · 6mo ago · official registry · v0.1.3

FAQ

›How do I install the Agentic Research Engine MCP server in Claude Code?

Run: claude mcp add agentic-research-engine -e OPENAI_API_KEY='<openai-api-key>' -- uvx agentic-research-engine. For Cursor, VS Code, Claude Desktop and Windsurf, use the install tabs above.

›Does Agentic Research Engine require an API key?

Yes. It expects OPENAI_API_KEY, of which 1 is a secret.

›Can I use Agentic Research Engine as a remote (hosted) MCP server?

No hosted endpoint is published; it runs locally over stdio.

›Is Agentic Research Engine in the official MCP registry?

Yes, as io.github.TheAiSingularity/agentic-research.