fix(health): a passing tools/list is live, not healthy
#104
@@ -397,7 +397,7 @@ name: home-automation
|
||||
proxyModel: default
|
||||
servers:
|
||||
- home-assistant
|
||||
- node-red
|
||||
- unifi-network
|
||||
```
|
||||
|
||||
Via CLI:
|
||||
|
||||
@@ -21,6 +21,13 @@ export interface SeedTemplate {
|
||||
version: string;
|
||||
description: string;
|
||||
packageName?: string;
|
||||
/**
|
||||
* Package runner: 'node' (npx) or 'python' (uvx). McpTemplate has had this
|
||||
* column all along, but the upsert below never wrote it, so a template
|
||||
* declaring `runtime: python` seeded as null and every server created from
|
||||
* it silently got the node runner.
|
||||
*/
|
||||
runtime?: string;
|
||||
dockerImage?: string;
|
||||
transport: 'STDIO' | 'SSE' | 'STREAMABLE_HTTP';
|
||||
repositoryUrl?: string;
|
||||
@@ -45,6 +52,7 @@ export async function seedTemplates(
|
||||
version: tpl.version,
|
||||
description: tpl.description,
|
||||
packageName: tpl.packageName ?? null,
|
||||
runtime: tpl.runtime ?? null,
|
||||
dockerImage: tpl.dockerImage ?? null,
|
||||
transport: tpl.transport,
|
||||
repositoryUrl: tpl.repositoryUrl ?? null,
|
||||
@@ -60,6 +68,7 @@ export async function seedTemplates(
|
||||
version: tpl.version,
|
||||
description: tpl.description,
|
||||
packageName: tpl.packageName ?? null,
|
||||
runtime: tpl.runtime ?? null,
|
||||
dockerImage: tpl.dockerImage ?? null,
|
||||
transport: tpl.transport,
|
||||
repositoryUrl: tpl.repositoryUrl ?? null,
|
||||
|
||||
79
src/mcpd/tests/templates.test.ts
Normal file
79
src/mcpd/tests/templates.test.ts
Normal file
@@ -0,0 +1,79 @@
|
||||
/**
|
||||
* The shipped `templates/*.yaml` are seeded into mcpd and are what `mcpctl
|
||||
* create server --from-template` builds from, so drift there ships broken
|
||||
* servers. The unifi-network template had drifted on every field that
|
||||
* mattered — python runtime for an npm package, an env contract
|
||||
* (UNIFI_HOST/USERNAME/PASSWORD) the package doesn't read, and a comment
|
||||
* disabling its health check for a reason that had stopped being true — and
|
||||
* nothing caught it because no test ever read the files.
|
||||
*/
|
||||
import { describe, it, expect } from 'vitest';
|
||||
import { readdirSync, readFileSync } from 'node:fs';
|
||||
import { join } from 'node:path';
|
||||
import { fileURLToPath } from 'node:url';
|
||||
import yaml from 'js-yaml';
|
||||
import { CreateTemplateSchema } from '../src/validation/template.schema.js';
|
||||
|
||||
const TEMPLATES_DIR = fileURLToPath(new URL('../../../templates', import.meta.url));
|
||||
|
||||
const files = readdirSync(TEMPLATES_DIR).filter((f) => f.endsWith('.yaml') || f.endsWith('.yml'));
|
||||
|
||||
interface RawTemplate {
|
||||
name?: string;
|
||||
runtime?: string;
|
||||
packageName?: string;
|
||||
dockerImage?: string;
|
||||
externalUrl?: string;
|
||||
healthCheck?: { tool?: string };
|
||||
env?: Array<{ name?: string }>;
|
||||
}
|
||||
|
||||
function load(file: string): RawTemplate {
|
||||
return yaml.load(readFileSync(join(TEMPLATES_DIR, file), 'utf-8')) as RawTemplate;
|
||||
}
|
||||
|
||||
describe('shipped templates', () => {
|
||||
it('ships at least one template', () => {
|
||||
expect(files.length).toBeGreaterThan(0);
|
||||
});
|
||||
|
||||
it.each(files)('%s validates against CreateTemplateSchema', (file) => {
|
||||
const parsed = CreateTemplateSchema.safeParse(load(file));
|
||||
expect(parsed.success ? null : parsed.error.issues).toBeNull();
|
||||
});
|
||||
|
||||
it.each(files)('%s declares a runner the orchestrator knows', (file) => {
|
||||
const tpl = load(file);
|
||||
// `runtime` only means anything for package-based servers, and only
|
||||
// 'node' (npx) and 'python' (uvx) are wired in buildRuntimeSpawnCmd.
|
||||
if (tpl.runtime !== undefined) {
|
||||
expect(['node', 'python']).toContain(tpl.runtime);
|
||||
}
|
||||
});
|
||||
|
||||
it.each(files)('%s says how to actually run the server', (file) => {
|
||||
const tpl = load(file);
|
||||
const runnable = tpl.packageName !== undefined
|
||||
|| tpl.dockerImage !== undefined
|
||||
|| tpl.externalUrl !== undefined;
|
||||
expect(runnable, `${file} has no packageName, dockerImage, or externalUrl`).toBe(true);
|
||||
});
|
||||
|
||||
it.each(files)('%s names a readiness probe tool, not a bare liveness probe', (file) => {
|
||||
const tpl = load(file);
|
||||
// Without a `tool`, an instance from this template can only ever report
|
||||
// `live` — nothing would ever check its upstream. See docs/reliability.md.
|
||||
expect(tpl.healthCheck?.tool, `${file} has no healthCheck.tool`).toBeTruthy();
|
||||
});
|
||||
|
||||
it.each(files)('%s declares uniquely-named env entries', (file) => {
|
||||
const names = (load(file).env ?? []).map((e) => e.name);
|
||||
expect(new Set(names).size).toBe(names.length);
|
||||
});
|
||||
|
||||
it('has no template for a retired server', () => {
|
||||
// node-red was retired 2026-08-09: it answered on neither its Tailscale
|
||||
// nor its LAN address and had no deployment anywhere.
|
||||
expect(files).not.toContain('node-red.yaml');
|
||||
});
|
||||
});
|
||||
@@ -4,8 +4,15 @@ description: Docmost MCP server for wiki/documentation page management and searc
|
||||
dockerImage: "mysources.co.uk/michal/docmost-mcp:latest"
|
||||
transport: STDIO
|
||||
repositoryUrl: https://github.com/MrMartiniMo/docmost-mcp
|
||||
# Health check disabled: STDIO health probe requires packageName (npm-based servers).
|
||||
# This server uses a custom dockerImage. Probe support for dockerImage STDIO servers is TODO.
|
||||
healthCheck:
|
||||
# get_workspace calls the Docmost API, so a pass proves URL + login. The old
|
||||
# "probe requires packageName" caveat here was true of the long-gone
|
||||
# docker-exec probe; readiness now goes through the MCP proxy, which works
|
||||
# the same for image-based STDIO servers. Verified against the live server.
|
||||
tool: get_workspace
|
||||
arguments: {}
|
||||
intervalSeconds: 60
|
||||
timeoutSeconds: 10
|
||||
env:
|
||||
- name: DOCMOST_API_URL
|
||||
description: Docmost API URL (e.g. http://100.88.157.6:3000/api)
|
||||
|
||||
@@ -1,6 +1,23 @@
|
||||
name: filesystem
|
||||
version: "1.0.0"
|
||||
version: "2.0.0"
|
||||
description: Filesystem MCP server for reading and writing files
|
||||
packageName: "@anthropic/filesystem-mcp"
|
||||
# Was "@anthropic/filesystem-mcp", which 404s on the npm registry — creating a
|
||||
# server from this template failed at install. This is the real package.
|
||||
packageName: "@modelcontextprotocol/server-filesystem"
|
||||
runtime: node
|
||||
transport: STDIO
|
||||
repositoryUrl: https://github.com/modelcontextprotocol/servers/tree/main/src/filesystem
|
||||
healthCheck:
|
||||
# Zero-arg and proves the server resolved its configured roots, which is the
|
||||
# only thing it can be misconfigured about.
|
||||
tool: list_allowed_directories
|
||||
arguments: {}
|
||||
intervalSeconds: 60
|
||||
timeoutSeconds: 10
|
||||
env:
|
||||
- name: ALLOWED_DIRECTORIES
|
||||
description: >-
|
||||
Space-separated directories the server may access. Passed as the
|
||||
package's positional arguments; without at least one the server exposes
|
||||
nothing.
|
||||
required: true
|
||||
|
||||
@@ -7,7 +7,18 @@ repositoryUrl: https://gitea.com/gitea/gitea-mcp
|
||||
# No command: the image's entrypoint IS the MCP server. mcpd attaches to PID 1
|
||||
# stdin/stdout (attach mode) rather than exec-ing a new process. The image is
|
||||
# distroless and has no node/shell, so exec-based STDIO would fail.
|
||||
# Health check disabled: STDIO health probe requires node in the container.
|
||||
healthCheck:
|
||||
# search_repos is a real Gitea API call, deliberately chosen over get_me:
|
||||
# get_me needs the `read:user` token scope, which a repo-scoped token won't
|
||||
# have, so it would fail for a bookkeeping reason rather than a real one.
|
||||
# (The "probe requires node in the container" caveat that used to sit here
|
||||
# described the old docker-exec probe; readiness goes through the MCP proxy
|
||||
# now, so a distroless image is fine.) Verified against the live server.
|
||||
tool: search_repos
|
||||
arguments:
|
||||
query: mcpctl
|
||||
intervalSeconds: 60
|
||||
timeoutSeconds: 10
|
||||
env:
|
||||
- name: GITEA_HOST
|
||||
description: Gitea instance URL (e.g. https://gitea.example.com)
|
||||
|
||||
@@ -1,16 +1,28 @@
|
||||
name: grafana
|
||||
version: "1.0.0"
|
||||
version: "1.1.0"
|
||||
description: Grafana MCP server for dashboards, datasources, and alerts
|
||||
packageName: "@leval/mcp-grafana"
|
||||
runtime: node
|
||||
transport: STDIO
|
||||
repositoryUrl: https://github.com/levalhq/mcp-grafana
|
||||
healthCheck:
|
||||
# Hits the Grafana API, so a pass proves URL + token + reachability. A
|
||||
# liveness probe (tools/list) cannot: it answers from the server's own tool
|
||||
# table and stays green while every Grafana call 403s.
|
||||
tool: list_datasources
|
||||
arguments: {}
|
||||
intervalSeconds: 60
|
||||
timeoutSeconds: 10
|
||||
env:
|
||||
- name: GRAFANA_URL
|
||||
description: Grafana instance URL (e.g. https://grafana.example.com)
|
||||
description: >-
|
||||
Grafana base URL. For a Grafana in this cluster use its ClusterIP
|
||||
(http://grafana.<namespace>.svc.cluster.local:3000) — NOT its public
|
||||
hostname. Reaching it over the public ingress hairpins the request back
|
||||
through the per-host Envoy L7 policy, which drops the caller's identity
|
||||
and answers a bare `Access denied` 403 even when the token is valid.
|
||||
required: true
|
||||
defaultValue: http://grafana.home-automation.svc.cluster.local:3000
|
||||
- name: GRAFANA_SERVICE_ACCOUNT_TOKEN
|
||||
description: Grafana service account token (glsa_...)
|
||||
required: true
|
||||
|
||||
@@ -1,16 +0,0 @@
|
||||
name: node-red
|
||||
version: "1.0.0"
|
||||
description: Node-RED MCP server for flow management and automation
|
||||
packageName: "mcp-node-red"
|
||||
transport: STDIO
|
||||
repositoryUrl: https://github.com/fx/mcp-node-red
|
||||
healthCheck:
|
||||
tool: get_settings
|
||||
arguments: {}
|
||||
env:
|
||||
- name: NODE_RED_URL
|
||||
description: Node-RED instance URL (e.g. http://nodered.local:1880)
|
||||
required: true
|
||||
- name: NODE_RED_TOKEN
|
||||
description: Node-RED access token (optional if no auth)
|
||||
required: false
|
||||
@@ -1,6 +0,0 @@
|
||||
name: terraform
|
||||
version: "1.0.0"
|
||||
description: Terraform MCP server for infrastructure documentation and state
|
||||
packageName: "@anthropic/terraform-mcp"
|
||||
transport: STDIO
|
||||
repositoryUrl: https://github.com/modelcontextprotocol/servers/tree/main/src/terraform
|
||||
@@ -1,25 +1,42 @@
|
||||
name: unifi-network
|
||||
version: "1.0.0"
|
||||
version: "2.0.0"
|
||||
description: UniFi Network MCP server for managing UniFi network devices, clients, and configuration
|
||||
packageName: "unifi-network-mcp"
|
||||
runtime: python
|
||||
runtime: node
|
||||
transport: STDIO
|
||||
repositoryUrl: https://github.com/sirkirby/unifi-mcp
|
||||
# Health check disabled: STDIO health probe requires packageName (npm-based servers).
|
||||
# This server uses the Python runner. Probe support for Python runner STDIO servers is TODO.
|
||||
healthCheck:
|
||||
# list_sites calls the controller (/api/self/sites), so a pass proves the
|
||||
# whole path: egress to the controller port, TLS, login, session. The old
|
||||
# template disabled the probe entirely on the belief that STDIO probes only
|
||||
# worked for npm packages — that stopped being true once readiness probes
|
||||
# started going through the MCP proxy, and the gap let this server sit at
|
||||
# "healthy" for months without ever reaching the controller.
|
||||
tool: list_sites
|
||||
arguments: {}
|
||||
intervalSeconds: 60
|
||||
timeoutSeconds: 15
|
||||
env:
|
||||
- name: UNIFI_HOST
|
||||
description: UniFi controller hostname or IP (e.g. unifi.example.com — without https://)
|
||||
- name: UNIFI_TARGETS
|
||||
description: >-
|
||||
JSON array of controllers. One object per controller:
|
||||
{"id", "base_url", "controller_type", "default_site", "auth":
|
||||
{"username","password"}, "verify_ssl"}.
|
||||
|
||||
controller_type is "classic" for a self-hosted UniFi Network controller
|
||||
(login /api/login, no path prefix) or "unifi_os" for a UDM/UniFi OS
|
||||
console (login /api/auth/login, API under /proxy/network). Choosing the
|
||||
wrong one sends every request to a path that 404s while the server still
|
||||
starts cleanly.
|
||||
|
||||
base_url must carry the real controller port — a self-hosted controller
|
||||
is usually :8443, and :443 on the same host is often an unrelated
|
||||
service. Note that MCP server pods only egress 80/443 by default, so any
|
||||
other port needs an explicit NetworkPolicy (Pulumi
|
||||
`mcpctl.serverEgressTargets`).
|
||||
required: true
|
||||
- name: UNIFI_USERNAME
|
||||
description: UniFi local admin username
|
||||
required: true
|
||||
- name: UNIFI_PASSWORD
|
||||
description: UniFi admin password
|
||||
required: true
|
||||
- name: UNIFI_NETWORK_PORT
|
||||
description: UniFi controller port (default 443, use 8443 for standalone UniFi Controller)
|
||||
required: false
|
||||
- name: UNIFI_NETWORK_VERIFY_SSL
|
||||
description: Verify SSL certificate (true/false, default true — set false for self-signed certs)
|
||||
required: false
|
||||
defaultValue: >-
|
||||
[{"id": "home", "base_url": "https://unifi.example.com:8443",
|
||||
"controller_type": "classic", "default_site": "default",
|
||||
"auth": {"username": "CHANGE_ME", "password": "CHANGE_ME"},
|
||||
"verify_ssl": false}]
|
||||
|
||||
Reference in New Issue
Block a user