rag-mcp
This server exposes a single MCP tool, search_knowledge, for cited natural-language retrieval over a local knowledge corpus.
Search a configured knowledge base with a natural-language query.
Control result count with
k(default 5, bounded to 1–20).Receive passage text plus a citation (source, heading, chunk index) for traceability.
Results are auth-scoped to the corpus root; failures return structured errors instead of crashing.
Optionally filter to a document class (
noteorhandoff) per the README interface.
rag-mcp
A minimal, honest RAG-over-a-corpus MCP retrieval tool. One tool,
search_knowledge(query, k, doc_class=None), that embeds a query, vector-searches a local corpus, and returns passages with citations (source + heading + chunk index) so answers are traceable.
Built to slot into the mcp-factory manifest model. Fully local + $0 (no paid embedding API).
Why it's safe to put in front of a real corpus
Cited - every hit carries
source+heading+chunk_index.Auth-scoped - results are confined to the configured corpus root; sources that escape it (absolute paths,
..traversal) are refused.Fail-soft - a down or empty store returns a structured error, never an exception that crashes the calling agent.
Bounded -
kis clamped to[1, 20]; empty queries are rejected.Version-pinned deps (
requirements.txt).
Related MCP server: kb-mcp-server
Stack
Layer | Choice |
Embeddings | local ONNX |
Vector store | ChromaDB embedded |
Server |
|
Protocol revision
Pinned to mcp==2.0.0, the first SDK release implementing MCP protocol revision
2026-07-28. The server serves both eras on the same stdio connection -- the
client's first frame picks:
Client opens with | Negotiated revision | Notes |
a per-request |
| stateless per-request envelope; no |
the classic |
| handshake era caps here -- expected, not a downgrade |
2026-07-28 is not reachable via the initialize handshake; it is a "modern"
revision reached through server/discover or an inline _meta version stamp. Era
selection is automatic and per-connection -- there is no server-side flag.
tests/test_protocol_version.py asserts both paths end-to-end, so a dependency
rollback that silently drops the server to an older revision fails CI instead of
passing quietly.
Quick start
python -m venv .venv && .venv/Scripts/python -m pip install -r requirements.txt
# Ingest a corpus (markdown). Incremental by default: only files whose content
# changed since the last run are re-embedded.
python -m rag_mcp.cli ingest path/to/docs --db ./store.chroma
# Force a rebuild in place (ignore the manifest, re-embed everything)
python -m rag_mcp.cli ingest path/to/docs --db ./store.chroma --full
# One-off query (corpus root = the auth scope)
python -m rag_mcp.cli query "your question" --db ./store.chroma --corpus path/to/docs -k 5
# Same, restricted to one doc_class ("note" or "handoff" -- see "Filtering by
# document class" below)
python -m rag_mcp.cli query "your question" --db ./store.chroma --corpus path/to/docs --doc-class note
# Run as an MCP server (stdio); configure via env first
# RAG_MCP_CORPUS_ROOT, RAG_MCP_DB_PATH, RAG_MCP_COLLECTION, RAG_MCP_EMBEDDER
python run_server.py # operational entrypoint (referenced by mcp.yaml)
python -m rag_mcp # same server, via the packaged console entry point
rag-mcp # after `pip install jaimenbell-rag-mcp` -- console scriptKeeping the index fresh (incremental ingest)
Ingest is incremental by default. A manifest inside the store dir records a SHA-256 of each file's decoded text; a run re-embeds only what actually changed, and prunes what upsert alone never could (chunks of deleted/renamed notes, and trailing chunks of notes that got shorter).
Measured on a live 2808-file / 26.6 MiB corpus (bge, CPU):
Run | Cost |
tick with no changes | ~0.7s (walk + read + hash everything) |
full re-embed | ~2h33m (50,109 chunks at ~5.5 chunks/sec) |
That is what makes a frequent schedule affordable: reingest.bat is meant to run
every 15 minutes instead of once daily at 03:00, which had left a note written
at 03:05 invisible to search_knowledge for nearly 24 hours.
The manifest is only trusted when the run identity matches -- embedder, embedding dimension, collection and chunking parameters. Change any of them and every file is re-embedded, so an embedder swap can never be silently half-applied. A missing, corrupt, or mismatched manifest, or a manifest against an empty store, all degrade to a full rebuild; nothing degrades to a wrong skip.
Snapshot de-duplication
The manifest's skip is a whole-file hash, so it cannot see the duplication that
actually hurts retrieval: a daily snapshot series (fleet-health-2026-07-23.md and
friends) repeats yesterday's paragraphs verbatim inside a file whose hash still
changed. Measured on the live vault, one ## RED Bots status line took five
distinct values across fifteen consecutive files and crowded a top-10 with
byte-identical copies of itself, burying the document that explained it at rank 16.
Ingest therefore also de-duplicates at chunk level, but only within a dated
series and only against the immediately preceding snapshot. The first occurrence
is always embedded and keeps its own date as its source; later verbatim repeats
are not embedded, and instead extend the survivor's repeat_dates metadata, which
search_knowledge returns as snapshot_date / also_unchanged_on /
snapshots_covered. So "what did this say on date X" is still answerable -- that is
why the series is de-duplicated rather than excluded. A value that changes and later
returns is kept, because it is a new fact rather than a repeat.
Scope is narrow and stated with the rule in rag_mcp/snapshots.py: filename ending
in -YYYY-MM-DD, at least 3 such files sharing a directory and stem, byte-identical
under an identical heading. On the live corpus that is 316 of 2,814 files and
collapses 842 of 50,428 chunks (17.5% of series chunks, 1.67% corpus-wide) while
touching zero ordinary notes. Disable with --no-snapshot-dedupe.
--full rebuilds in place (ignores the manifest, keeps the store); --clean
deletes the store first. Both still WRITE a manifest, so the next run is cheap.
reingest-clean.bat (weekly) remains a belt-and-braces reset.
As an MCP server
Register via mcp.yaml (validated against mcp-factory's Manifest loader). The tool is
search_knowledge(query, k, doc_class=None); it reads the store configured by the
RAG_MCP_* env vars.
Filtering by document class
Every chunk's metadata carries a doc_class, set at ingest time. It is "handoff" when
the doc's YAML frontmatter has type: handoff or a tags entry of handoff
(case-insensitive), or -- since a doc's frontmatter is optional and the session mirrors
this exists to flag often carry none -- when the file sits directly under a
handoff_mirror_dir (default context/, configurable via ingest()'s
handoff_mirror_dir=/handoff_mirror_basenames= params or the CLI's
--handoff-mirror-dir/--handoff-mirror-basename flags) and is named handoff.md /
active.md / resume.md, or matches an anchored "handoff" filename token (e.g.
handoff-2026-09-03.md, morning-dispatch-handoff.md) -- never a bare substring, so a
title that merely mentions the word (handoff-skill-redesign-spec.md) stays "note".
Everything else defaults to "note". Pass doc_class to scope a query to one class, e.g.
to keep an agent's own session/handoff bookkeeping out of a knowledge lookup:
from rag_mcp.search import search_knowledge
search_knowledge(
"what did we decide about X", k=5, store=store, corpus_root=root, doc_class="note",
)doc_class is a validated, case-sensitive enum -- "note" or "handoff" (see
rag_mcp.search.ALLOWED_DOC_CLASSES) -- or omitted for no filter. A value outside that
set (wrong case, a typo, any other type) returns a structured invalid_doc_class error,
same shape as invalid_query. A syntactically valid doc_class that simply has no
matches in the current store still fails soft to an empty, ok: true result.
An incremental ingest run backfills doc_class (and any other metadata-schema change) onto
already-embedded, content-unchanged chunks WITHOUT re-embedding them -- see
ingest.CURRENT_METADATA_VERSION. A store that predates this feature entirely gets the
correct doc_class on every chunk after exactly one incremental run, not a full --clean
rebuild.
Tests
python -m pytest # 272 passedThis count is the total collected, CI-enforced against the live pytest summary
(scripts/check_readme_counts.py, wired into .github/workflows/ci.yml). One
test is platform-conditional -- WINDOWS_ONLY in
tests/test_reindex_handle_release.py only runs on Windows -- so Linux CI
reports 271 passed, 1 skipped for the same 272-test suite; the gate compares
passed-plus-skipped against this claim, not passed alone, so that expected
skip does not read as drift.
Layout
rag_mcp/
chunking.py heading-scoped, overlapping markdown chunks
store.py VectorStore (Chroma) + Embedder protocol (MiniLM default + BgeEmbedder opt-in + offline HashEmbedder)
ingest.py idempotent ingest pipeline with source/heading/chunk-index metadata; incremental by default
manifest.py per-file content hashes -> skip unchanged files, prune stale chunks
search.py search_knowledge: cited, auth-scoped, fail-soft, bounded
server.py MCP stdio server exposing search_knowledge
config.py env-driven Config
cli.py ingest + query CLI
__main__.py console entrypoint (`python -m rag_mcp` / `rag-mcp` script); fails loud on missing config
run_server.py operational MCP entrypoint (referenced by mcp.yaml)
mcp.yaml manifest (mcp-factory model)Commercial support
Maintained by Jaimen Bell. For production MCP integrations, custom servers, or agent-reliability work, see jaimenbell.dev.
Building your own MCP server? The MCP Starter Kit has templates, a build playbook, and packaging war-stories from shipping this one.
mcp-name: io.github.jaimenbell/rag-mcp
Available Tools
1 toolsearch_knowledgeA
Retrieve the most relevant passages from the configured knowledge corpus for a natural-language query. Returns the passage text plus a CITATION (source file + heading + chunk index) for each hit so answers are traceable. Auth-scoped to the corpus root and fail-soft: a down/empty store returns a structured error, never an exception. Use when asked to look something up in the knowledge base / docs.
Inputs: query (required), k.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 1 tool
The single tool has a clear, distinct purpose (retrieving relevant passages). With no other tools to differentiate, there is no possibility of ambiguous selection.
The tool name 'search_knowledge' follows a clear verb_noun convention, which would be consistent even if more tools were added. As a single tool, it sets a predictable pattern.
With only one tool, the server feels too thin for the 'rag' domain, which typically requires additional operations like listing sources or ingesting content. The single tool is not trivial but is insufficient for a well-scoped RAG server.
The tool surface covers only search/retrieval. There are no tools for managing the knowledge corpus (e.g., list sources, add/update/delete documents), leaving significant gaps that would require external intervention for many workflows.
Maintenance
Related MCP Connectors
Cloud or self-hosted knowledge for AI agents: hybrid search, reranking, GraphRAG, scoped MCP tools.
Ask your own documents and get answers that cite the source passage. Workspace knowledge bases over MCP for Cursor, Claude and any MCP client.
Private, multimodal knowledge store for agents: hybrid search with cited, provenance-backed results.
Read-only hosted MCP over CanonicAI's cited Answers corpus on canonicai.com.
Related MCP Servers
- AlicenseAqualityDmaintenanceLocal-first RAG indexing and semantic search MCP server. Enables document retrieval and context-aware queries using local embedding models.38 npmMIT
- FlicenseNot gradedqualityDmaintenanceEnables semantic search over a local knowledge base using MCP tools, allowing AI clients to retrieve relevant document chunks via the search_knowledge tool.2-

devitway-rag-starterofficial
FlicenseNot gradedqualityDmaintenanceMinimal local RAG stack with an MCP server that provides document search for any agent.1-- AlicenseNot gradedqualityDmaintenanceEnables retrieval-augmented generation over a local markdown corpus, allowing grounded, cited answers via an MCP tool or CLI.MIT