MCP Tools DirectoryAbout this integration
Local research agent that verifies its own answers. Runs on Gemma 3 4B + Ollama, $0/query.
- Transport
- stdio
- Authentication
- unknown
- Initial setup
- unknown
- Runtime
- unattended
- Evidence
- documented
- Version
- 0.1.3
- Package
- agentic-research-engine
- Last compatibility test
- Not independently tested
Connect your agent
agentic-research-enginePublisher README and Python manifest reviewed. Package, models, search services, and endpoints were not executed. Publisher benchmark and verification claims remain publisher-documented and are not independently validated here.
Capabilities: Run cited research workflows, Use domain presets and local document corpora, Inspect and reset local research memory
Connected profiles
Additional details
io.github.TheAiSingularity/agentic-research
Source ↗ · Checked 2026-09-170.1.3
Source ↗ · Checked 2026-09-17CC0-1.0; package licenses are separate
Source ↗ · Checked 2026-09-17pypi
Source ↗ · Checked 2026-09-17agentic-research-engine
Source ↗ · Checked 2026-09-200.1.3
Source ↗ · Checked 2026-09-20The Python package declares a console entry point for its MCP server, and the publisher documents a module-based stdio configuration.
Source ↗ · Checked 2026-09-20Authentication varies by the selected OpenAI-compatible inference endpoint: local Ollama uses a non-secret sentinel, while cloud endpoints require the chosen provider's API key; search and local model services are separate prerequisites.
Source ↗ · Checked 2026-09-20A local MCP client runs python -m engine.mcp.server over stdio and supplies model and SearXNG configuration through environment variables.
Source ↗ · Checked 2026-09-20Publisher documentation reviewed; package and integration endpoint not executed or independently security-audited.
Source ↗ · Checked 2026-09-20