Claude MarketplacesSubmit
theaisingularity avatar

Agentic Research

theaisingularity/agentic-research-engine-oss

Runs a local research pipeline that fetches web sources, compresses evidence, synthesizes answers, and verifies them with Chain of Verification. The server wraps an 8-node LangGraph flow (classify, plan, search, retrieve, fetch, compress, synthesize, verify) powered by Gemma 3 4B via Ollama, so queries cost nothing and run entirely offline. Exposes a single `ask` tool that takes a question and optional domain preset (general, medical, papers, financial, stock_trading, personal_docs). Ships with SearXNG meta-search, BM25 and dense hybrid retrieval, and optional BGE reranker. Useful when you want citations and fact-checking in Claude Desktop without routing to a commercial search API or leaving your machine.

tools
3
auth
Secret needed
transport
STDIO
env vars
9
last updated
Apr 20, 2026
View on GitHub

Tools

3 tools

Public tool metadata for what this MCP can expose to an agent.

researchAnswers a question with structured output including verified and unverified claims, sources, trace, totals and memory hits.

Answers a question with structured output including verified and unverified claims, sources, trace, totals and memory hits.

No parameter schema in public metadata yet.

reset_memoryClears the server's memory.

Clears the server's memory.

No parameter schema in public metadata yet.

memory_countReturns the number of items in the server's memory.

Returns the number of items in the server's memory.

No parameter schema in public metadata yet.

Sponsors

Promote your product hereReach 125k+ visitors monthlyPromote your product hereReach 125k+ visitors monthlyAgent CaffeineSponsoredClose your lid, come back to finished workSnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthlyWaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthlyknobsSponsoredSee your site on any phone, any day, in any language

Configuration

OPENAI_BASE_URL

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

OPENAI_API_KEYsecret

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'.

Readme

agentic-research-engine-oss

License PyPI Version Default Tests Interfaces MCP

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.

Table of contents

View the full README on GitHub

Details

Repository
github.com/theaisingularity/agentic-research-engine-oss
Category
AI & LLM Tools
Package
agentic-research-engine
Transport
STDIO
Auth
Required
Registry
MCP registry, active

Related AI & LLM Tools MCP servers

View all
1rafacoelho33 avatarWeb3 Systemic Agentrafacoelho33/web3-systemic-agentWeb3 security & DAO auditor: free bytecode/honeypot/Snapshot tools + x402 Gemini LLM deep audit.0stars
2spences10 avatarSequential Thinkingspences10/mcp-sequentialthinking-tools🧠 An adaptation of the MCP Sequential Thinking Server to guide tool usage. This server provides recommendations for which MCP tools would be most effective at 583stars
3lykhoyda avatarAsk Ollamalykhoyda/ask-llmBridge Claude with local Ollama LLMs for private AI-to-AI collaboration — no API keys, fully local19stars
4basicmachines-co avatarBasic Memorybasicmachines-co/basic-memoryLocal-first knowledge management with bi-directional LLM sync via Markdown files.4.5Kstars
5rinadelph avatarAgentrinadelph/agent-mcpAgent-MCP is a framework for creating multi-agent systems that enables coordinated, efficient AI collaboration through the Model Context Protocol (MCP). The sys1.2Kstars
6sinewaveai avatarAgent Security Scanner Mcpsinewaveai/agent-security-scanner-mcpSecurity layer for AI agents: blocks prompt injection, detects fake packages, scans vulnerabilities.110stars