InnerVault

agentic-research

Stale Official MCP Registry, io.github.TheAiSingularity

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

Open the source (opens github.com) https://github.com/theaisingularity/agentic-research-engine-oss

Before you use it

  • Runs on your computer with your permissions. Read what it can do before connecting it to an agent.
  • Needs credentials: OPENAI_API_KEY. Use a key with the least access you can.

What it is

MCP servers from io.github.TheAiSingularity.

The problem it solves and who it suits haven't been reviewed by InnerVault. The description above is the source's own.

How to get it

pypi package (stdio)

agentic-research-engine@0.1.3

From the server's entry in the official MCP Registry

Settings it asks for

  • OPENAI_BASE_URL · Any OpenAI-compatible endpoint. Default: OpenAI cloud. Use http://localhost:11434/v1 for Ollama.
  • OPENAI_API_KEY secret · 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'.

Related

  1. Join voluntary research studies and record how AI assistants choose local businesses.

    Stale Official MCP Registry, com.pickedbyagents Updated 42 days ago 1 note

  2. Paid MCP web research for agents: search, extraction, citations, and x402 payment discovery.

    Stale Official MCP Registry, io.github.jnilrac Updated 5 months ago 1 note

  3. AI agents collaborate on open biomedical problems, citing sources that are machine-checked.

    Stale Official MCP Registry, io.github.SecondStageTurbine Updated 3 months ago 1 note

  4. mache

    MCP servers

    IDE-style navigation for structured data — code, JSON, YAML. Jump to definitions, find callers, follow references. Available as an MCP server or a mounted folder.

    Stale GitHub, agentic-research 46 ★Apache-2.0Updated 4 days ago

    git clone https://github.com/agentic-research/mache.git
  5. hyperresearch

    MCP servers

    Convert Claude Code or Codex into the most intelligent Deep Research Agent. Collect, search, and synthesize web research into a persistent, searchable wiki that builds on itself. Hosted API + MCP: hyperresearch.ai

    Stale GitHub, jordan-gibbs 4,145 ★MITUpdated 21 days ago

    git clone https://github.com/jordan-gibbs/hyperresearch.git
  6. flexreport-mcp

    MCP servers

    MCP server for real-time equity research: real-time market events, 13F ownership, earnings transcripts, fundamentals, estimates & insider filings on 2,900+ companies for Claude and other AI agents.

    Indexed GitHub, cbecks1212 27 ★Updated today

    git clone https://github.com/cbecks1212/flexreport-mcp.git