Keeper Secrets Manager
mcpotherio.github.WYRE-AI/keeper-mcp · v1.0.3
Read-only multitenant Streamable HTTP bridge over Keeper Secrets Manager's MCP server.
run it
on your own machines, one way per deploy methodgenerated from the record, not tested yet
CHANGE_ME: check the image's README for its transport and port; this assumes streamable HTTP at :8000/mcp. If it speaks stdio only, use it from clients/mcp.json as a `docker run -i` command instead.
#!/usr/bin/env bash
# keeper (io.github.WYRE-AI/keeper-mcp), recipe docker (generated).
# Generated by Hub for toolset "my-agent"; started by mcp-my-agent-keeper.service.
set -euo pipefail
export HOST=127.0.0.1 PORT=8101
exec docker run --rm --name mcp-my-agent-keeper -p 127.0.0.1:${PORT}:8000 --env-file /etc/mcp/my-agent.env ghcr.io/wyre-ai/keeper-mcp:v1.0.3
[Unit]
Description=MCP server keeper (toolset my-agent), generated by Hub
After=network-online.target docker.service
Wants=network-online.target
[Service]
Type=simple
User=mcp
Group=mcp
SupplementaryGroups=docker
EnvironmentFile=/etc/mcp/my-agent.env
Environment=HOME=/var/lib/mcp/keeper
WorkingDirectory=/var/lib/mcp/keeper
ExecStart=/opt/mcp/my-agent/bin/keeper.sh
Restart=on-failure
RestartSec=5
NoNewPrivileges=true
ProtectSystem=strict
ProtectHome=true
PrivateTmp=true
ReadWritePaths=/var/lib/mcp/keeper
[Install]
WantedBy=multi-user.target
generated from the record, not tested yet
CHANGE_ME: check the image's README for its transport and port; this assumes streamable HTTP at :8000/mcp. If it speaks stdio only, use it from clients/mcp.json as a `docker run -i` command instead.
docker run --rm -p 127.0.0.1:8101:8000 -e PORT -e KSM_MCP_BIN -e CHILD_HOME -e IDLE_EVICT_MS -e SPAWN_TIMEOUT_MS ghcr.io/wyre-ai/keeper-mcp:v1.0.3
generated from the record, not tested yet
CHANGE_ME: check the image's README for its transport and port; this assumes streamable HTTP at :8000/mcp. If it speaks stdio only, use it from clients/mcp.json as a `docker run -i` command instead.
# Generated by Hub for toolset "my-agent" (2026-10-18T05:09:14+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:
keeper:
image: ghcr.io/wyre-ai/keeper-mcp:v1.0.3
ports:
- 127.0.0.1:8101:8000
restart: unless-stopped
x-note: 'CHANGE_ME: check the image''s README for its transport and port; this assumes streamable
HTTP at :8000/mcp. If it speaks stdio only, use it from clients/mcp.json as a `docker run -i` command
instead.'
environment:
PORT: ${PORT}
KSM_MCP_BIN: ${KSM_MCP_BIN}
CHILD_HOME: ${CHILD_HOME}
IDLE_EVICT_MS: ${IDLE_EVICT_MS}
SPAWN_TIMEOUT_MS: ${SPAWN_TIMEOUT_MS}
volumes:
npm-cache: {}
uv-cache: {}
generated from the record, not tested yet
CHANGE_ME: check the image's README for its transport and port; this assumes streamable HTTP at :8000/mcp. If it speaks stdio only, use it from clients/mcp.json as a `docker run -i` command instead.
# Generated by Hub for toolset "my-agent" (2026-10-18T05:09:14+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: keeper
namespace: mcp
labels: &id001
app: keeper
spec:
replicas: 1
selector:
matchLabels: *id001
template:
metadata:
labels: *id001
spec:
containers:
- name: keeper
image: ghcr.io/wyre-ai/keeper-mcp:v1.0.3
ports:
- containerPort: 8000
name: http
env:
- name: PORT
valueFrom:
secretKeyRef:
name: mcp-credentials
key: PORT
- name: KSM_MCP_BIN
valueFrom:
secretKeyRef:
name: mcp-credentials
key: KSM_MCP_BIN
- name: CHILD_HOME
valueFrom:
secretKeyRef:
name: mcp-credentials
key: CHILD_HOME
- name: IDLE_EVICT_MS
valueFrom:
secretKeyRef:
name: mcp-credentials
key: IDLE_EVICT_MS
- name: SPAWN_TIMEOUT_MS
valueFrom:
secretKeyRef:
name: mcp-credentials
key: SPAWN_TIMEOUT_MS
---
apiVersion: v1
kind: Service
metadata:
name: keeper
namespace: mcp
spec:
selector:
app: keeper
ports:
- port: 8000
targetPort: http
name: http
generated from the record, not tested yet
CHANGE_ME: check the image's README for its transport and port; this assumes streamable HTTP at :8000/mcp. If it speaks stdio only, use it from clients/mcp.json as a `docker run -i` command instead.
# Generated by Hub for toolset "my-agent" (2026-10-18T05:09:14+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:
keeper:
enabled: true
replicas: 1
port: 8000
path: /mcp
container:
name: keeper
image: ghcr.io/wyre-ai/keeper-mcp:v1.0.3
ports:
- containerPort: 8000
name: http
env:
- name: PORT
valueFrom:
secretKeyRef:
name: mcp-credentials
key: PORT
- name: KSM_MCP_BIN
valueFrom:
secretKeyRef:
name: mcp-credentials
key: KSM_MCP_BIN
- name: CHILD_HOME
valueFrom:
secretKeyRef:
name: mcp-credentials
key: CHILD_HOME
- name: IDLE_EVICT_MS
valueFrom:
secretKeyRef:
name: mcp-credentials
key: IDLE_EVICT_MS
- name: SPAWN_TIMEOUT_MS
valueFrom:
secretKeyRef:
name: mcp-credentials
key: SPAWN_TIMEOUT_MS
# 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: PORT, KSM_MCP_BIN, CHILD_HOME, IDLE_EVICT_MS, SPAWN_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 needsdocker run -i --rm -e PORT -e KSM_MCP_BIN -e CHILD_HOME -e IDLE_EVICT_MS -e SPAWN_TIMEOUT_MS ghcr.io/wyre-ai/keeper-mcp:v1.0.3
{
"mcpServers": {
"keeper": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"PORT",
"-e",
"KSM_MCP_BIN",
"-e",
"CHILD_HOME",
"-e",
"IDLE_EVICT_MS",
"-e",
"SPAWN_TIMEOUT_MS",
"ghcr.io/wyre-ai/keeper-mcp:v1.0.3"
],
"env": {
"PORT": "${PORT}",
"KSM_MCP_BIN": "${KSM_MCP_BIN}",
"CHILD_HOME": "${CHILD_HOME}",
"IDLE_EVICT_MS": "${IDLE_EVICT_MS}",
"SPAWN_TIMEOUT_MS": "${SPAWN_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 keeper -e "PORT=${PORT}" -e "KSM_MCP_BIN=${KSM_MCP_BIN}" -e "CHILD_HOME=${CHILD_HOME}" -e "IDLE_EVICT_MS=${IDLE_EVICT_MS}" -e "SPAWN_TIMEOUT_MS=${SPAWN_TIMEOUT_MS}" -- docker run -i --rm -e PORT -e KSM_MCP_BIN -e CHILD_HOME -e IDLE_EVICT_MS -e SPAWN_TIMEOUT_MS ghcr.io/wyre-ai/keeper-mcp:v1.0.3
{
"mcpServers": {
"keeper": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"PORT",
"-e",
"KSM_MCP_BIN",
"-e",
"CHILD_HOME",
"-e",
"IDLE_EVICT_MS",
"-e",
"SPAWN_TIMEOUT_MS",
"ghcr.io/wyre-ai/keeper-mcp:v1.0.3"
],
"env": {
"PORT": "${PORT}",
"KSM_MCP_BIN": "${KSM_MCP_BIN}",
"CHILD_HOME": "${CHILD_HOME}",
"IDLE_EVICT_MS": "${IDLE_EVICT_MS}",
"SPAWN_TIMEOUT_MS": "${SPAWN_TIMEOUT_MS}"
}
}
}
}
{
"servers": {
"keeper": {
"type": "stdio",
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"PORT",
"-e",
"KSM_MCP_BIN",
"-e",
"CHILD_HOME",
"-e",
"IDLE_EVICT_MS",
"-e",
"SPAWN_TIMEOUT_MS",
"ghcr.io/wyre-ai/keeper-mcp:v1.0.3"
],
"env": {
"PORT": "${PORT}",
"KSM_MCP_BIN": "${KSM_MCP_BIN}",
"CHILD_HOME": "${CHILD_HOME}",
"IDLE_EVICT_MS": "${IDLE_EVICT_MS}",
"SPAWN_TIMEOUT_MS": "${SPAWN_TIMEOUT_MS}"
}
}
}
}
name: my-agent target: local servers: - hub: io.github.WYRE-AI/keeper-mcp
- 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.