Ajay Krishnan
b4e863562c
context-docs was previously spawned per call as a fresh stdio container,
which meant every MCP request paid full cold-start cost (embedding model
load + Chroma open) and concurrent clients raced for the same Chroma
writer. The 50+ orphan container build-up I saw during the publish audit
was the visible symptom.
This refactor runs docs-mcp as one long-lived service:
- compose: docs-mcp leaves the 'mcp' profile, gets container_name,
restart: unless-stopped, healthcheck, and a host port (127.0.0.1:8776
by default). Runs as the host UID/GID so bind mounts don't end up
root-owned.
- docker image: adds mcp-proxy (0.12.0) and an entrypoint that fronts
llms-txt-mcp's stdio as Streamable HTTP. Reads sources from a flat
file mounted at /etc/context-kit/docs-sources.txt. Disables eager
preindex by default; callers refresh on demand via the docs_refresh
tool. Set CONTEXT_KIT_DOCS_PREINDEX=1 to restore eager behavior.
- bin/context-kit: 'start' brings up the docs service alongside SearXNG,
generates the sources file from CONTEXT_KIT_DOCS_SOURCES, and waits
for the HTTP endpoint to become ready (up to 180s for first-run model
download). 'docs' still works for stdio-only clients but is now a
thin mcp-proxy bridge onto the shared HTTP service. 'doctor' and
'status' both surface the new endpoint.
- install snippets: context-docs is now 'type: remote'/'type: http'
pointing at ${CONTEXT_KIT_DOCS_HTTP_URL}. HTTP-capable MCP clients
bypass the bridge entirely. snippets/*.json and the install command
output stay byte-identical.
- docs and .env.example updated for new vars (CONTEXT_KIT_DOCS_PORT,
CONTEXT_KIT_DOCS_HTTP_URL, CONTEXT_KIT_DOCS_PREINDEX) and the new
24h TTL default (down from 7d; the long-lived service makes shorter
defaults cheap).
Verified end-to-end:
- compose config -q, bash -n, sh -n all clean
- HTTP /status returns 200
- stdio bridge returns initialize + tools/list with the same 3 tools
(docs_sources, docs_refresh, docs_query)
- doctor passes all 10 checks including the new HTTP probe
- web-search and repomix MCP handshakes still work
- redaction-check clean
- install JSON valid for both targets + --absolute
33 lines
1.2 KiB
Plaintext
33 lines
1.2 KiB
Plaintext
# Copy to .env to override local defaults.
|
|
|
|
# Where Context Kit stores docs indexes and model caches.
|
|
# Default: $HOME/.local/share/context-kit
|
|
# CONTEXT_KIT_DATA_DIR=/path/to/context-kit-data
|
|
|
|
# Docker Compose project name. This controls the Docker network name.
|
|
CONTEXT_KIT_COMPOSE_PROJECT=context-kit
|
|
|
|
# Local SearXNG port. Bound to 127.0.0.1 only.
|
|
CONTEXT_KIT_SEARXNG_PORT=8099
|
|
|
|
# Local-only SearXNG secret. Set this to any random string if you expose SearXNG
|
|
# beyond localhost, which the default setup does not do.
|
|
CONTEXT_KIT_SEARXNG_SECRET=change-me-local-only
|
|
|
|
# Long-lived context-docs HTTP MCP service. Bound to 127.0.0.1 only.
|
|
CONTEXT_KIT_DOCS_PORT=8776
|
|
# Override only if you proxy the service behind another hostname or path.
|
|
# CONTEXT_KIT_DOCS_HTTP_URL=http://127.0.0.1:8776/mcp
|
|
|
|
# Docs indexing defaults.
|
|
CONTEXT_KIT_DOCS_TTL=24h
|
|
CONTEXT_KIT_DOCS_MAX_GET_BYTES=75000
|
|
CONTEXT_KIT_DOCS_EMBED_MODEL=BAAI/bge-small-en-v1.5
|
|
|
|
# Eagerly index every source on container start. Off by default so startup is
|
|
# fast; call the docs_refresh MCP tool when you want to populate the index.
|
|
# CONTEXT_KIT_DOCS_PREINDEX=1
|
|
|
|
# One or more source files, separated by spaces.
|
|
CONTEXT_KIT_DOCS_SOURCES=config/sources.default.txt
|