mcp-local-rag
mcpkey · packageio.github.shinpr/mcp-local-rag · v0.22.1
Easy-to-setup local RAG server with minimal configuration
run it
on your own machines, one way per deploy methodgenerated from the record, not tested yet
# once, as root:
# as_mcp DIR COMMAND...: runs COMMAND as the mcp user in DIR, its home, sandboxed as the
# units are: a package's install scripts can write to DIR only, as the server later can
as_mcp() {
local dir="$1"; shift
systemd-run --quiet --wait --pipe --collect --uid=mcp --gid=mcp \
-p WorkingDirectory="$dir" -p Environment=HOME="$dir" -p ReadWritePaths="$dir" \
-p NoNewPrivileges=true -p ProtectSystem=strict -p ProtectHome=true -p PrivateTmp=true \
-- "$@" </dev/null
}
install -d -m 0750 -o mcp -g mcp /var/lib/mcp/local-rag
# local-rag: its packages, installed whole before its unit starts (no session installs)
# npx takes a half-installed tree for installed: a rerun starts them afresh
systemctl stop mcp-my-agent-local-rag.service 2>/dev/null || true
as_mcp /var/lib/mcp/local-rag rm -rf /var/lib/mcp/local-rag/.npm/_npx
as_mcp /var/lib/mcp/local-rag npx --yes [email protected] -- true
as_mcp /var/lib/mcp/local-rag npx --yes --package=supergateway@4 -- true
#!/usr/bin/env bash
# local-rag (io.github.shinpr/mcp-local-rag), recipe baremetal (generated).
# Generated by Hub for toolset "my-agent"; started by mcp-my-agent-local-rag.service.
set -euo pipefail
export HOST=127.0.0.1 PORT=8101
exec npx -y supergateway@4 --stdio 'npx -y [email protected]' --outputTransport streamableHttp --stateful --host 127.0.0.1 --port 8101 --streamableHttpPath /mcp --healthEndpoint /healthz
[Unit]
Description=MCP server local-rag (toolset my-agent), generated by Hub
After=network-online.target
Wants=network-online.target
[Service]
Type=simple
User=mcp
Group=mcp
EnvironmentFile=/etc/mcp/my-agent.env
Environment=HOME=/var/lib/mcp/local-rag
WorkingDirectory=/var/lib/mcp/local-rag
ExecStart=/opt/mcp/my-agent/bin/local-rag.sh
Restart=on-failure
RestartSec=5
NoNewPrivileges=true
ProtectSystem=strict
ProtectHome=true
PrivateTmp=true
ReadWritePaths=/var/lib/mcp/local-rag
[Install]
WantedBy=multi-user.target
generated from the record, not tested yet
docker run --rm -p 127.0.0.1:8101:8000 -e BASE_DIR -e BASE_DIRS -e DB_PATH -e CACHE_DIR -e HF_ENDPOINT -e MODEL_NAME -e MAX_FILE_SIZE -e RAG_MAX_DISTANCE -e RAG_GROUPING -e RAG_MAX_FILES -e CHUNK_MIN_LENGTH -e STORE_IMAGES -e EMBED_TITLE_PREFIX -e EMBED_HEADING_PREFIX -e RAG_DEVICE -e RAG_DTYPE -e RAG_HYBRID_WEIGHT -e RAG_RERANK_CMD -e RAG_RERANK_TIMEOUT_MS node:22-alpine sh -c 'npx -y supergateway@4 --stdio '"'"'npx -y [email protected]'"'"' --outputTransport streamableHttp --stateful --host 0.0.0.0 --port 8000 --streamableHttpPath /mcp --healthEndpoint /healthz'
generated from the record, not tested yet
# Generated by Hub for toolset "my-agent" (2026-10-18T18:20:57+00:00).
# Each package server runs behind a stdio->HTTP bridge and listens on localhost only.
# cp .env.example .env # fill the ${VAR}s
# docker compose up -d && bash smoke.sh
# Remote servers are not here: clients reach them directly (see clients/).
name: mcp-my-agent
services:
local-rag:
image: node:22-alpine
command:
- sh
- -c
- npx -y supergateway@4 --stdio 'npx -y [email protected]' --outputTransport streamableHttp --stateful
--host 0.0.0.0 --port 8000 --streamableHttpPath /mcp --healthEndpoint /healthz
ports:
- 127.0.0.1:8101:8000
volumes:
- npm-cache:/root/.npm
healthcheck:
test:
- CMD-SHELL
- wget -qO- http://127.0.0.1:8000/healthz || exit 1
interval: 30s
timeout: 5s
retries: 5
start_period: 2m
restart: unless-stopped
environment:
BASE_DIR: ${BASE_DIR}
BASE_DIRS: ${BASE_DIRS}
DB_PATH: ${DB_PATH}
CACHE_DIR: ${CACHE_DIR}
HF_ENDPOINT: ${HF_ENDPOINT}
MODEL_NAME: ${MODEL_NAME}
MAX_FILE_SIZE: ${MAX_FILE_SIZE}
RAG_MAX_DISTANCE: ${RAG_MAX_DISTANCE}
RAG_GROUPING: ${RAG_GROUPING}
RAG_MAX_FILES: ${RAG_MAX_FILES}
CHUNK_MIN_LENGTH: ${CHUNK_MIN_LENGTH}
STORE_IMAGES: ${STORE_IMAGES}
EMBED_TITLE_PREFIX: ${EMBED_TITLE_PREFIX}
EMBED_HEADING_PREFIX: ${EMBED_HEADING_PREFIX}
RAG_DEVICE: ${RAG_DEVICE}
RAG_DTYPE: ${RAG_DTYPE}
RAG_HYBRID_WEIGHT: ${RAG_HYBRID_WEIGHT}
RAG_RERANK_CMD: ${RAG_RERANK_CMD}
RAG_RERANK_TIMEOUT_MS: ${RAG_RERANK_TIMEOUT_MS}
volumes:
npm-cache: {}
uv-cache: {}
generated from the record, not tested yet
# Generated by Hub for toolset "my-agent" (2026-10-18T18:20:57+00:00).
# kubectl create namespace mcp
# kubectl -n mcp create secret generic mcp-credentials --from-env-file=.env
# kubectl apply -f kubernetes.yaml
# Services are cluster-internal: <name>.mcp.svc.cluster.local:8000/mcp. Put an ingress
# with auth in front before exposing any of them.
apiVersion: v1
kind: Namespace
metadata:
name: mcp
---
apiVersion: apps/v1
kind: Deployment
metadata:
name: local-rag
namespace: mcp
labels: &id001
app: local-rag
spec:
replicas: 1
selector:
matchLabels: *id001
template:
metadata:
labels: *id001
spec:
containers:
- name: local-rag
image: node:22-alpine
ports:
- containerPort: 8000
name: http
env:
- name: BASE_DIR
valueFrom:
secretKeyRef:
name: mcp-credentials
key: BASE_DIR
- name: BASE_DIRS
valueFrom:
secretKeyRef:
name: mcp-credentials
key: BASE_DIRS
- name: DB_PATH
valueFrom:
secretKeyRef:
name: mcp-credentials
key: DB_PATH
- name: CACHE_DIR
valueFrom:
secretKeyRef:
name: mcp-credentials
key: CACHE_DIR
- name: HF_ENDPOINT
valueFrom:
secretKeyRef:
name: mcp-credentials
key: HF_ENDPOINT
- name: MODEL_NAME
valueFrom:
secretKeyRef:
name: mcp-credentials
key: MODEL_NAME
- name: MAX_FILE_SIZE
valueFrom:
secretKeyRef:
name: mcp-credentials
key: MAX_FILE_SIZE
- name: RAG_MAX_DISTANCE
valueFrom:
secretKeyRef:
name: mcp-credentials
key: RAG_MAX_DISTANCE
- name: RAG_GROUPING
valueFrom:
secretKeyRef:
name: mcp-credentials
key: RAG_GROUPING
- name: RAG_MAX_FILES
valueFrom:
secretKeyRef:
name: mcp-credentials
key: RAG_MAX_FILES
- name: CHUNK_MIN_LENGTH
valueFrom:
secretKeyRef:
name: mcp-credentials
key: CHUNK_MIN_LENGTH
- name: STORE_IMAGES
valueFrom:
secretKeyRef:
name: mcp-credentials
key: STORE_IMAGES
- name: EMBED_TITLE_PREFIX
valueFrom:
secretKeyRef:
name: mcp-credentials
key: EMBED_TITLE_PREFIX
- name: EMBED_HEADING_PREFIX
valueFrom:
secretKeyRef:
name: mcp-credentials
key: EMBED_HEADING_PREFIX
- name: RAG_DEVICE
valueFrom:
secretKeyRef:
name: mcp-credentials
key: RAG_DEVICE
- name: RAG_DTYPE
valueFrom:
secretKeyRef:
name: mcp-credentials
key: RAG_DTYPE
- name: RAG_HYBRID_WEIGHT
valueFrom:
secretKeyRef:
name: mcp-credentials
key: RAG_HYBRID_WEIGHT
- name: RAG_RERANK_CMD
valueFrom:
secretKeyRef:
name: mcp-credentials
key: RAG_RERANK_CMD
- name: RAG_RERANK_TIMEOUT_MS
valueFrom:
secretKeyRef:
name: mcp-credentials
key: RAG_RERANK_TIMEOUT_MS
args:
- sh
- -c
- npx -y supergateway@4 --stdio 'npx -y [email protected]' --outputTransport streamableHttp
--stateful --host 0.0.0.0 --port 8000 --streamableHttpPath /mcp --healthEndpoint /healthz
readinessProbe:
httpGet:
path: /healthz
port: http
initialDelaySeconds: 10
---
apiVersion: v1
kind: Service
metadata:
name: local-rag
namespace: mcp
spec:
selector:
app: local-rag
ports:
- port: 8000
targetPort: http
name: http
generated from the record, not tested yet
# Generated by Hub for toolset "my-agent" (2026-10-18T18:20:57+00:00).
# Credentials come from the Secret 'mcp-credentials' (kubectl create secret generic ... --from-env-file=.env).
# Each server under `servers` is one Deployment + Service; the keys after it configure
# upstream charts a worker verified.
servers:
local-rag:
enabled: true
replicas: 1
port: 8000
path: /mcp
container:
name: local-rag
image: node:22-alpine
ports:
- containerPort: 8000
name: http
env:
- name: BASE_DIR
valueFrom:
secretKeyRef:
name: mcp-credentials
key: BASE_DIR
- name: BASE_DIRS
valueFrom:
secretKeyRef:
name: mcp-credentials
key: BASE_DIRS
- name: DB_PATH
valueFrom:
secretKeyRef:
name: mcp-credentials
key: DB_PATH
- name: CACHE_DIR
valueFrom:
secretKeyRef:
name: mcp-credentials
key: CACHE_DIR
- name: HF_ENDPOINT
valueFrom:
secretKeyRef:
name: mcp-credentials
key: HF_ENDPOINT
- name: MODEL_NAME
valueFrom:
secretKeyRef:
name: mcp-credentials
key: MODEL_NAME
- name: MAX_FILE_SIZE
valueFrom:
secretKeyRef:
name: mcp-credentials
key: MAX_FILE_SIZE
- name: RAG_MAX_DISTANCE
valueFrom:
secretKeyRef:
name: mcp-credentials
key: RAG_MAX_DISTANCE
- name: RAG_GROUPING
valueFrom:
secretKeyRef:
name: mcp-credentials
key: RAG_GROUPING
- name: RAG_MAX_FILES
valueFrom:
secretKeyRef:
name: mcp-credentials
key: RAG_MAX_FILES
- name: CHUNK_MIN_LENGTH
valueFrom:
secretKeyRef:
name: mcp-credentials
key: CHUNK_MIN_LENGTH
- name: STORE_IMAGES
valueFrom:
secretKeyRef:
name: mcp-credentials
key: STORE_IMAGES
- name: EMBED_TITLE_PREFIX
valueFrom:
secretKeyRef:
name: mcp-credentials
key: EMBED_TITLE_PREFIX
- name: EMBED_HEADING_PREFIX
valueFrom:
secretKeyRef:
name: mcp-credentials
key: EMBED_HEADING_PREFIX
- name: RAG_DEVICE
valueFrom:
secretKeyRef:
name: mcp-credentials
key: RAG_DEVICE
- name: RAG_DTYPE
valueFrom:
secretKeyRef:
name: mcp-credentials
key: RAG_DTYPE
- name: RAG_HYBRID_WEIGHT
valueFrom:
secretKeyRef:
name: mcp-credentials
key: RAG_HYBRID_WEIGHT
- name: RAG_RERANK_CMD
valueFrom:
secretKeyRef:
name: mcp-credentials
key: RAG_RERANK_CMD
- name: RAG_RERANK_TIMEOUT_MS
valueFrom:
secretKeyRef:
name: mcp-credentials
key: RAG_RERANK_TIMEOUT_MS
args:
- sh
- -c
- npx -y supergateway@4 --stdio 'npx -y [email protected]' --outputTransport streamableHttp --stateful
--host 0.0.0.0 --port 8000 --streamableHttpPath /mcp --healthEndpoint /healthz
readinessProbe:
httpGet:
path: /healthz
port: http
initialDelaySeconds: 10
# helm install my-agent helm/my-agent -n mcp
in the cloud
one click: the provider's deploy form opens filled in, in your own account- koyeb
-
The form opens with CHANGE_ME for each value you supply: BASE_DIR, BASE_DIRS, DB_PATH, CACHE_DIR, HF_ENDPOINT, MODEL_NAME, MAX_FILE_SIZE, RAG_MAX_DISTANCE, RAG_GROUPING, RAG_MAX_FILES, CHUNK_MIN_LENGTH, STORE_IMAGES, EMBED_TITLE_PREFIX, EMBED_HEADING_PREFIX, RAG_DEVICE, RAG_DTYPE, RAG_HYBRID_WEIGHT, RAG_RERANK_CMD, RAG_RERANK_TIMEOUT_MS. Fill them in before you deploy.
Clients connect to the service's https://…koyeb.app address plus /mcp.
- azure
-
A Container Apps environment with one app per server, each with HTTPS ingress and one replica. The portal asks for each value you supply as a secure parameter; the deployment's outputs list the endpoints.
connect to it
copy what your client needsnpx -y [email protected] # env: BASE_DIR, BASE_DIRS, DB_PATH, CACHE_DIR, HF_ENDPOINT, MODEL_NAME, MAX_FILE_SIZE, RAG_MAX_DISTANCE, RAG_GROUPING, RAG_MAX_FILES, CHUNK_MIN_LENGTH, STORE_IMAGES, EMBED_TITLE_PREFIX, EMBED_HEADING_PREFIX, RAG_DEVICE, RAG_DTYPE, RAG_HYBRID_WEIGHT, RAG_RERANK_CMD, RAG_RERANK_TIMEOUT_MS
{
"mcpServers": {
"local-rag": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"BASE_DIR": "${BASE_DIR}",
"BASE_DIRS": "${BASE_DIRS}",
"DB_PATH": "${DB_PATH}",
"CACHE_DIR": "${CACHE_DIR}",
"HF_ENDPOINT": "${HF_ENDPOINT}",
"MODEL_NAME": "${MODEL_NAME}",
"MAX_FILE_SIZE": "${MAX_FILE_SIZE}",
"RAG_MAX_DISTANCE": "${RAG_MAX_DISTANCE}",
"RAG_GROUPING": "${RAG_GROUPING}",
"RAG_MAX_FILES": "${RAG_MAX_FILES}",
"CHUNK_MIN_LENGTH": "${CHUNK_MIN_LENGTH}",
"STORE_IMAGES": "${STORE_IMAGES}",
"EMBED_TITLE_PREFIX": "${EMBED_TITLE_PREFIX}",
"EMBED_HEADING_PREFIX": "${EMBED_HEADING_PREFIX}",
"RAG_DEVICE": "${RAG_DEVICE}",
"RAG_DTYPE": "${RAG_DTYPE}",
"RAG_HYBRID_WEIGHT": "${RAG_HYBRID_WEIGHT}",
"RAG_RERANK_CMD": "${RAG_RERANK_CMD}",
"RAG_RERANK_TIMEOUT_MS": "${RAG_RERANK_TIMEOUT_MS}"
}
}
}
}
#!/usr/bin/env bash
# Registers every server with Claude Code (run once; `claude mcp list` to check).
set -euo pipefail
set -a; [ -f .env ] && source .env; set +a
claude mcp add local-rag -e "BASE_DIR=${BASE_DIR}" -e "BASE_DIRS=${BASE_DIRS}" -e "DB_PATH=${DB_PATH}" -e "CACHE_DIR=${CACHE_DIR}" -e "HF_ENDPOINT=${HF_ENDPOINT}" -e "MODEL_NAME=${MODEL_NAME}" -e "MAX_FILE_SIZE=${MAX_FILE_SIZE}" -e "RAG_MAX_DISTANCE=${RAG_MAX_DISTANCE}" -e "RAG_GROUPING=${RAG_GROUPING}" -e "RAG_MAX_FILES=${RAG_MAX_FILES}" -e "CHUNK_MIN_LENGTH=${CHUNK_MIN_LENGTH}" -e "STORE_IMAGES=${STORE_IMAGES}" -e "EMBED_TITLE_PREFIX=${EMBED_TITLE_PREFIX}" -e "EMBED_HEADING_PREFIX=${EMBED_HEADING_PREFIX}" -e "RAG_DEVICE=${RAG_DEVICE}" -e "RAG_DTYPE=${RAG_DTYPE}" -e "RAG_HYBRID_WEIGHT=${RAG_HYBRID_WEIGHT}" -e "RAG_RERANK_CMD=${RAG_RERANK_CMD}" -e "RAG_RERANK_TIMEOUT_MS=${RAG_RERANK_TIMEOUT_MS}" -- npx -y [email protected]
{
"mcpServers": {
"local-rag": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"BASE_DIR": "${BASE_DIR}",
"BASE_DIRS": "${BASE_DIRS}",
"DB_PATH": "${DB_PATH}",
"CACHE_DIR": "${CACHE_DIR}",
"HF_ENDPOINT": "${HF_ENDPOINT}",
"MODEL_NAME": "${MODEL_NAME}",
"MAX_FILE_SIZE": "${MAX_FILE_SIZE}",
"RAG_MAX_DISTANCE": "${RAG_MAX_DISTANCE}",
"RAG_GROUPING": "${RAG_GROUPING}",
"RAG_MAX_FILES": "${RAG_MAX_FILES}",
"CHUNK_MIN_LENGTH": "${CHUNK_MIN_LENGTH}",
"STORE_IMAGES": "${STORE_IMAGES}",
"EMBED_TITLE_PREFIX": "${EMBED_TITLE_PREFIX}",
"EMBED_HEADING_PREFIX": "${EMBED_HEADING_PREFIX}",
"RAG_DEVICE": "${RAG_DEVICE}",
"RAG_DTYPE": "${RAG_DTYPE}",
"RAG_HYBRID_WEIGHT": "${RAG_HYBRID_WEIGHT}",
"RAG_RERANK_CMD": "${RAG_RERANK_CMD}",
"RAG_RERANK_TIMEOUT_MS": "${RAG_RERANK_TIMEOUT_MS}"
}
}
}
}
{
"servers": {
"local-rag": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"BASE_DIR": "${BASE_DIR}",
"BASE_DIRS": "${BASE_DIRS}",
"DB_PATH": "${DB_PATH}",
"CACHE_DIR": "${CACHE_DIR}",
"HF_ENDPOINT": "${HF_ENDPOINT}",
"MODEL_NAME": "${MODEL_NAME}",
"MAX_FILE_SIZE": "${MAX_FILE_SIZE}",
"RAG_MAX_DISTANCE": "${RAG_MAX_DISTANCE}",
"RAG_GROUPING": "${RAG_GROUPING}",
"RAG_MAX_FILES": "${RAG_MAX_FILES}",
"CHUNK_MIN_LENGTH": "${CHUNK_MIN_LENGTH}",
"STORE_IMAGES": "${STORE_IMAGES}",
"EMBED_TITLE_PREFIX": "${EMBED_TITLE_PREFIX}",
"EMBED_HEADING_PREFIX": "${EMBED_HEADING_PREFIX}",
"RAG_DEVICE": "${RAG_DEVICE}",
"RAG_DTYPE": "${RAG_DTYPE}",
"RAG_HYBRID_WEIGHT": "${RAG_HYBRID_WEIGHT}",
"RAG_RERANK_CMD": "${RAG_RERANK_CMD}",
"RAG_RERANK_TIMEOUT_MS": "${RAG_RERANK_TIMEOUT_MS}"
}
}
}
}
name: my-agent target: local servers: - hub: io.github.shinpr/mcp-local-rag
- not probed yet: tools unpinned, ingest lists them
tools
Not probed yetThe tools appear once the hub or its worker has listed this entry. Running it still works: your client lists them on first start.