LabscoMCP early access ↗
Kos-MMCP SERVER · OFFICIAL PROJECT

ACG MCP

Every claim in an answer carries a marker pointing at the exact chunk of the exact source — and a tool that re-fetches the source to check it.

by Kos-M ↗Vector Stores & RAG Retrieval✓ Official

LABSCO SUMMARY

Verification here means re-reading the source, not asking the model again.

Most citation features stop at attaching a URL, which proves nothing about whether the sentence is in it. Re-fetching the page and fuzzy-matching each claim against the actual text is a different and much stronger guarantee — a claim either survives that check or it does not. The confidence tier is the practical companion: it tells you whether the index can answer before you spend a fetch. If large indexes start reporting LOW confidence wrongly, the candidate cap is the setting to raise.

What it is

An MCP server for grounded retrieval with verification attached. You index URLs into MongoDB; answers built from that index carry inline claim markers naming the source fingerprint and the chunk within it. A separate tool re-fetches each cited source and fuzzy-matches the claim against the real text, so verification is an independent check rather than the model's own opinion.

What you get

  • acg_run_workflow runs the whole pipeline in one call — search, auto-index if confidence is low and a URL was supplied, ground, verify, audit — and returns the answer with per-claim verification results and an audit footer
  • acg_check_indexed returns a confidence tier of HIGH, MEDIUM or LOW before any network call, so you only fetch a new page when the index genuinely cannot answer
  • acg_index_url fetches, chunks by sentence, embeds and stores a page; acg_crawl_and_index does a whole documentation site with background task support, tracked by acg_crawl_status and acg_crawl_list_tasks
  • acg_search_sources returns matching chunks with scores for building your own answer; acg_list_sources and acg_count_sources inspect the index
  • acg_generate_grounded_text attaches claim markers to text, and acg_verify_claims checks marked text against the cited sources — which makes a verify-only pass over text generated elsewhere possible
  • acg_build_var emits the machine-readable audit record, listing every claim, its source fingerprint and the relationships between claims
  • acg_reset_database clears everything, and requires an explicit confirmation flag

Requirements

Python 3.11 or higher and a MongoDB instance, local or Atlas. Install into a virtual environment with pip install -e ., which puts acg-mcp on the path; MCP clients should be pointed at the absolute path of that binary rather than relying on the shell. MONGO_URI is required, MONGO_DB defaults to acg_protocol, and ACG_VECTOR_MAX_CANDIDATES caps how many embedded chunks a query scans — raise it if a large index starts returning false LOW confidence. Atlas Vector Search is optional; without an embedding model it falls back to keyword search. A one-shot CLI mode runs the full pipeline without any MCP client.

Setup effort

Build from source — git clone https://github.com/Kos-M/acg_mcp.git

See installation options