Alimenter votre agent
La commande propre à l'éditeur. Ce n'est pas un endpoint PlugMCP.
Host a copy with our keys and logs.
uvx jaimenbell-rag-mcp==0.1.0Claude Code n'a pas de lien d'installation pour une commande locale. Copiez la commande ci-dessous et exécutez-la dans un terminal.
claude mcp add io.github.jaimenbell-rag-mcp -- uvx jaimenbell-rag-mcp==0.1.0À exécuter dans un terminal.
{ "mcpServers": { "io.github.jaimenbell-rag-mcp": { "command": "uvx", "args": [ "jaimenbell-rag-mcp==0.1.0" ] } }}claude_desktop_config.json
URL distante ou commande sur votre machine ? Ce qui distingue les deux installations
Exécuter sur PlugMCP
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
LancerDe l'éditeur
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.
Minimal RAG-over-a-corpus MCP retrieval: search_knowledge returns cited chunks. Local embeddings.
Built to slot into the mcp-factory manifest model. Fully local + $0 (no paid embedding API).
source + heading + chunk_index... traversal) are refused.k is clamped to [1, 20]; empty queries are rejected.requirements.txt).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:
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.
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 script
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):
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.
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.
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.
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.
python -m pytest # 272 passed
This 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.
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)
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
Minimal RAG-over-a-corpus MCP retrieval: search_knowledge returns cited chunks. Local embeddings.
{ "mcpServers": { "io.github.jaimenbell-rag-mcp": { "command": "uvx", "args": [ "jaimenbell-rag-mcp==0.1.0" ] } }}Outils
Pas encore de liste d'outils. Les serveurs distants en obtiennent une après le premier contrôle d'état.
FAQ
Copiez sur cette page la configuration stdio pour Cursor, Claude Desktop, Claude Code ou VS Code. Elle utilise l'installation de l'éditeur, pas un proxy PlugMCP.
Aucune variable d'environnement requise n'est indiquée sur cette fiche.
Rag s'exécute en local via stdio.
Dernière vérification : 2026-11-09. Minimal RAG-over-a-corpus MCP retrieval: search_knowledge returns cited chunks. Local embeddings.