laurentvv/agents-kit/agent-mcp

Claude Code and agent skill by laurentvv/agents-kit

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Manage and health-check the machine's MCP servers (mcp_agents.py CLI) - inventory the declared servers from user and repo configs, audit declared vs running via localhost probes, deep-probe one server (daemon reachability, corpus freshness via BUILT_AT-style globs, referenced paths in its config file), run the doctor CI gate, or start/stop/restart through declared lifecycle commands. Use when an MCP-dependent feature fails silently, before claiming a daemon is up, or on any session bootstrap that depends on local search/indexer daemons.

Install

npx vskill@latest install laurentvv/agents-kit/agent-mcp

SKILL.md

agent-mcp - MCP fleet health, locally

MCP servers fail silently: a localhost daemon dies and every fallback keeps working "on the surface", an indexer's config references directories that were renamed weeks ago, a corpus goes stale. This CLI makes all three visible and gives the lifecycle commands a single declared entry point.

Everything is driven by a local, git-ignored fleet descriptor (mcp-fleet.local.yml next to .agent/, template: template/mcp-fleet.template.yml in agents-kit). Machine paths never enter a repository.

Invocation

bash
uv run --no-project .agents/skills/agent-mcp/scripts/mcp_agents.py [--repo PATH] <command>
  • Standard library only, Python 3.11+: no install, no venv, works on fresh

clones and CI.

  • In the agents-kit repository the canonical copy is scripts/mcp_agents.py;

the copy shipped here is byte-identical (test-enforced mirror).

Commands

CommandEffect
inventory [--fleet ROOT]Parse MCP declarations: user-level configs (mcpServers or mcp.servers key) plus repo-level .mcp.json files under the fleet roots. Token-like values (token, key, secret, password) are masked.
auditDeclared vs running: run each descriptor entry probe (localhost HTTP URL, process name, or command) and report up / down / unknown. Exit 1 if any entry is down.
probe <name>Deep check of one entry: probe + freshness globs (e.g. **/BUILT_AT.txt, age budget) + every absolute path referenced by its declared config file must exist.
doctorAudit + freshness + referenced paths for every entry. Exit 0 only when everything is healthy - usable as a CI/local gate.
start <name> / stop <name> / restart <name>Run the lifecycle command declared in the descriptor (e.g. a start-*.cmd). restart falls back to the declared stop then start. These are the ONLY effectful commands.

Descriptor discovery: --config PATH > MCP_FLEET_CONFIG env var > <repo>/mcp-fleet.local.yml > upward walk from the repo root.

Safety rules

  • inventory, audit, probe and doctor never write anything.
  • Lifecycle commands run with the descriptor as the single source: nothing is

improvised on the command line. Machine-level rules (no shutdown, no restart of the machine itself) stay governed by the kit's common block.

  • No secret value is ever printed: masking is applied to every output,

including --json.

  • External effect (starting or stopping a daemon) is a machine state change:

report it, never hide it.

Workflow

  1. Before trusting any MCP-backed feature: doctor (or audit for the

network view only). Fix what is red before working around it.

  1. A down daemon: probe <name> for the why (process? stale corpus? missing

referenced directory?), then start <name> if the descriptor declares how, then probe <name> again to confirm.

  1. After renaming or deleting a repository: doctor flags the indexers whose

config still references the old path - fix the config, then restart the daemon through the declared lifecycle commands.

  1. A red doctor is a finding, not a nuisance: report it with the captured

output as evidence (paths redacted outside the machine).

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

See the full security report

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

See evaluation results

Source

Popularity

7-day trend score
0

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/laurentvv/agents-kit/agent-mcp/badge)](https://verified-skill.com/skills/laurentvv/agents-kit/agent-mcp)

Something wrong with this skill or its page? Tell us.