SERVER

Agentic Research Engine

Rank #42,008

io.github.TheAiSingularity/agentic-research

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

2 versions

2 GitHub stars

by theaisingularity (1 servers)View repository ↗Claim this server

First listed

Apr 19, 2026

Last publish date

Apr 20, 2026

OVERVIEW

Agentic Research Engine is a Model Context Protocol (MCP) server published by theaisingularity. It ranks #42,008 of 137,492 servers tracked on MCP Toplist, and its repository has 2 GitHub stars. Agentic Research Engine is listed across 2 registries — Official MCP and PulseMCP, with 2 tracked versions. It was first listed on Apr 19, 2026 and most recently updated on Apr 20, 2026.

STANDING

#42,008of 137,492 tracked serversTop 50%

Ranks ahead of 95,484 of 137,492 servers on MCP Toplist.

CONNECT

Use Agentic Research Engine

No setupRuns out of the box

No credentials or required configuration declared — add it to your MCP client and go.

Python package (PyPI)

claude mcp add agentic-research -e "OPENAI_BASE_URL=<your OPENAI_BASE_URL>" -e "OPENAI_API_KEY=<your OPENAI_API_KEY>" -e "MODEL_SYNTHESIZER=<your MODEL_SYNTHESIZER>" -e "MODEL_PLANNER=<your MODEL_PLANNER>" -e "EMBED_MODEL=<your EMBED_MODEL>" -e "SEARXNG_URL=<your SEARXNG_URL>" -e "LOCAL_CORPUS_PATH=<your LOCAL_CORPUS_PATH>" -e "ENABLE_RERANK=<your ENABLE_RERANK>" -e "ENABLE_FETCH=<your ENABLE_FETCH>" -- uvx agentic-research-engine

Replace each placeholder with your own value before saving.

Python package (PyPI)

[mcp_servers.agentic-research]
command = "uvx"
args = ["agentic-research-engine"]

[mcp_servers.agentic-research.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>"

Add to ~/.codex/config.toml. Replace each placeholder with your own value before saving.

Python package (PyPI)

{
  "mcpServers": {
    "agentic-research": {
      "command": "uvx",
      "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>"
      }
    }
  }
}

Add to claude_desktop_config.json (Settings → Developer → Edit Config). Replace each placeholder with your own value before saving.

Python package (PyPI)

{
  "mcpServers": {
    "agentic-research": {
      "command": "uvx",
      "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>"
      }
    }
  }
}

Add to ~/.cursor/mcp.json (global) or .cursor/mcp.json (per project). Replace each placeholder with your own value before saving.

Python package (PyPI)

{
  "servers": {
    "agentic-research": {
      "type": "stdio",
      "command": "uvx",
      "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>"
      }
    }
  }
}

Save as .vscode/mcp.json in your workspace. Replace each placeholder with your own value before saving.

Python package (PyPI)

{
  "mcpServers": {
    "agentic-research": {
      "command": "uvx",
      "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>"
      }
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json. Replace each placeholder with your own value before saving.

Python package (PyPI)

{
  "mcpServers": {
    "agentic-research": {
      "command": "uvx",
      "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>"
      }
    }
  }
}

Replace each placeholder with your own value before saving.

BADGE

Show your rank

Maintain this server? Add the live rank badge to your README — it updates automatically as the leaderboard changes.

Markdown

[![MCP Toplist](https://mcptoplist.com/badge/io.github.TheAiSingularity%2Fagentic-research.svg)](https://mcptoplist.com/server/io.github.TheAiSingularity%2Fagentic-research)

HTML

<a href="https://mcptoplist.com/server/io.github.TheAiSingularity%2Fagentic-research"><img src="https://mcptoplist.com/badge/io.github.TheAiSingularity%2Fagentic-research.svg" alt="MCP Toplist: Top 50% of 137,492" /></a>

Variants: append ?metric=score or ?metric=stars to the image URL.

REGISTRIES

Listed on 2 registries

Official MCP

PulseMCP

ORGANIZATION

theaisingularity

Organization

theaisingularity

Servers in org

Versions across org

VERSIONS

Available versions (2)

Version	Published
0.1.3	Apr 20, 2026
0.1.2	Apr 20, 2026

FAQ

Frequently asked questions

Who maintains Agentic Research Engine?: Agentic Research Engine is maintained by theaisingularity, which publishes 1 MCP server (2 total versions) tracked on MCP Toplist.
Is Agentic Research Engine listed on the Official MCP Registry?: Yes — Agentic Research Engine is listed on the Official MCP Registry, alongside PulseMCP.
How many versions does Agentic Research Engine have?: MCP Toplist tracks 2 versions of Agentic Research Engine, most recently published on Apr 20, 2026.
Where can I find the source code for Agentic Research Engine?: The source code for Agentic Research Engine is hosted at github.com/theaisingularity/agentic-research-engine-oss.

Used in projects

Do you run this server?

Add to a project

Community projects list the MCP servers behind real agents and apps. Publish yours and this page will link to it.

EXPLORE

All MCP Servers Official MCP Servers GitHub MCP Servers Best MCP Servers Most Active MCP Servers New MCP Servers Best New MCP Servers