Agentic Research MCP Server
agentic-research-engine-oss The best $0 research agent that runs on a laptop. Open-source end-to-end, reproducible, privacy-preserving. No cloud dependency by default; no telemetry; every LLM call, every source, and every verification decision is visible. It runs locally over stdio via the published package.
People who work with agent framework, agentic ai and langgraph and want it reachable from Claude, Cursor, VS Code, or another MCP client. The project is written in Python.
VERIFIED ACTIVE
LAST COMMIT 2026-04-21 · ★ 2 · #83 OF 106 MAINTAINED AI & ML · VERIFIED 2026-09-18
MIT · Python servers · how we verify → /methodology
01 · Install Agentic Research
before you install - you'll need
Set OPENAI_BASE_URL, OPENAI_API_KEY, MODEL_SYNTHESIZER, SEARXNG_URL, MODEL_PLANNER, LOCAL_CORPUS_PATH before connecting.
Claude Code
claude mcp add theaisingularity-agentic-research-engine -- uvx agentic-research-engine Claude Desktop / Cursor / VS Code - add to config
{
"mcpServers": {
"theaisingularity-agentic-research-engine": {
"command": "uvx",
"args": [
"agentic-research-engine"
]
}
}
} Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.
Using another client? Same JSON, different key
Claude Desktop · mcpServers
Cursor · mcpServers
VS Code · servers
Windsurf · mcpServers
Zed · context_servers
Cline · mcpServers
Roo Code · mcpServers
Continue · mcpServers
LibreChat · mcpServers
Gemini CLI · mcpServers
Codex CLI · mcp_servers
Full setup guides: every client.
02 · Evidence
Security posture
What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.
runs as local process (stdio) - runs on your machine with your user's permissions
license MIT - declared in the repository
pypi package agentic-research-engine - check the name against the project README before installing (PyPI has no namespace ownership)
registry namespace io.github.TheAiSingularity is GitHub-verified and matches the repo owner
03 · What Agentic Research can do
Prose above is summarized from the project's README and registry record - no invented capabilities.
Latest releases
v0.1.3 · 2026-04-20
Discovery infrastructure · Three changes that unlock indexing across the five community directories: · 1. Standalone prompt-only skill: verify-answer · Pure Chain-of-Verification in one Markdown file. Works in any…
v0.1.2 · 2026-04-20
Hotfix · Unblocks the mcp-publisher publish call. The registry requires an · ownership marker in the PyPI-hosted README to prove the PyPI package · and the MCP-registry entry share an owner. · Fixed · Added mcp-name…
v0.1.1 · 2026-04-20
PyPI-ready. Marketplace submission artifacts in place. · No new user-facing features. One naming fix + the infrastructure needed to publish to PyPI, the MCP registry, and the Anthropic Claude plugin marketplace.…
04 · Who maintains Agentic Research
agentic-research is maintained by theaisingularity. It's the only MCP server we track from this author; the repo dates to Apr 2026.
05 · Facts
- category
- AI & ML - ranked #83 of 106 actively-maintained AI & ML servers as of 2026-09-18.
- registry
- io.github.TheAiSingularity/agentic-research (active, first published 2026-04-20 · 2 versions)
- packages
- pypi:agentic-research-engine
06 · Agentic Research FAQ
What is Agentic Research?
agentic-research-engine-oss The best $0 research agent that runs on a laptop. Open-source end-to-end, reproducible, privacy-preserving. No cloud dependency by default; no telemetry; every LLM call, every source, and every verification decision is visible. It runs locally over stdio via the published package.
Is Agentic Research still maintained?
Yes - as of 2026-09-18, its last commit was 2026-04-21. We re-verify nightly.
How do I install Agentic Research?
Run `uvx agentic-research-engine`. The README documents 6 environment variables (OPENAI_BASE_URL, OPENAI_API_KEY, MODEL_SYNTHESIZER…) to set first. Set OPENAI_BASE_URL, OPENAI_API_KEY, MODEL_SYNTHESIZER, SEARXNG_URL, MODEL_PLANNER, LOCAL_CORPUS_PATH before connecting. You can also paste the ready-made client config above.
Does Agentic Research run locally?
Yes - it's a stdio server: it runs on your machine (via uvx) with your user's permissions. Your data stays local unless the server itself calls external APIs.
07 · Alternatives to Agentic Research
Alternatives to Agentic Research
Maintained AI & ML servers if Agentic Research isn't the fit.
- Fun ASR Transcribe local audio with FunASR and SenseVoice using private, on-device inference. ★ 20,411 · 2026-09-18
- Auto TS Automated time series forecasting with model search, anomaly detection, and event risk analysis ★ 1,428 · 2026-08-25
- Haiku RAG Local-first agentic RAG with citations - hybrid search, reranking, multimodal document retrieval ★ 609 · 2026-09-17
- Plan Exe MCP server for generating rough-draft project plans from natural-language prompts. ★ 401 · 2026-09-13
- Local RAG (shinpr) Easy-to-setup local RAG server with minimal configuration ★ 398 · 2026-09-18
- PageIndex MCP Reasoning-based RAG system for chatting with long PDFs. Supports local and online files. ★ 388 · 2026-07-25
Pairs well with
Servers that cover what Agentic Research doesn't - only shown when the pairing reason fits the companion.
More AI & ML MCP servers · Glassbox Framework · Lacuna Research MCP · Reftrixmcp · Dashclaw · Snaprender
More Python MCP servers · Emfirge · Mneme (thegoatpsy) · Costco · Psquare · Winsight · see all