Claude Skill

mcp-operations

Operate and maintain the local MCP server for this project. Use when creating MCP host config, troubleshooting tool connectivity, modifying tool domains, or adjusting safety policy flags.

LLM Mart · 0 points · 9 views 0 listing impressions 0 install-command copies
Virus-scanned Reviewed automatically before listing.

Full trust report

Download hoangsonww-claude-code-agent-monitor-.claude_skills_mcp-operations-83d4df5.zip · 2 KB
Part of hoangsonww/claude-code-agent-monitor — 86 skills

Install

skills CLI npx skills add https://github.com/hoangsonww/Claude-Code-Agent-Monitor/tree/master/.claude/skills/mcp-operations
Claude Code claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install hoangsonww-claude-code-agent-monitor@llmmart
Git git clone https://github.com/hoangsonww/Claude-Code-Agent-Monitor.git

The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole hoangsonww/claude-code-agent-monitor collection as a plugin from our marketplace. Git is the plain clone.

Skill manifest

MCP Operations

Use this skill whenever work touches mcp/ behavior or MCP host integration.

Core workflow

  • Confirm dashboard API is running (/api/health).
  • Confirm MCP server build status.
  • Validate env flags for mutation/destructive modes.
  • Verify host configuration path and command.

Safe operations policy

  • Default to read-only mode (MCP_DASHBOARD_ALLOW_MUTATIONS=false).
  • Enable mutations only for explicit admin tasks.
  • Enable destructive mode only transiently and require explicit confirmation token.

Required verification for code changes

  • npm run mcp:typecheck
  • npm run test:mcp
  • npm run mcp:build

Catalog invariant

  • Add tools only through mcp/src/tools/domains/ and registerAllTools.
  • Protocol transports and REPL must use the same declarations and schemas.
  • Update .agents/skills/mcp-maintainer/references/tool-domain-map.md when a domain changes.

References

  • Host config examples: references/host-config.md
  • Operations runbook: references/runbook.md
Files (claude-code-agent-monitor)
  • references
    • host-config.md 408 B
      # MCP Host Config
      
      ## Command
      - `node`
      
      ## Args
      - Absolute path to `mcp/build/index.js`
      
      ## Example env
      - `MCP_DASHBOARD_BASE_URL=http://127.0.0.1:4820`
      - `MCP_DASHBOARD_ALLOW_MUTATIONS=false`
      - `MCP_DASHBOARD_ALLOW_DESTRUCTIVE=false`
      - `MCP_LOG_LEVEL=info`
      
      ## Common mistakes
      - Relative path to MCP build entry.
      - Dashboard not running while MCP starts.
      - Mutating tools used while mutation flag is false.
      
    • runbook.md 1.1 KB
      # MCP Runbook
      
      ## Read-only daily mode
      - Keep both mutation flags false.
      - Use read tools for observability and reporting.
      
      ## Admin mode
      - Set `MCP_DASHBOARD_ALLOW_MUTATIONS=true`.
      - Run maintenance/pricing operations.
      - Reset mutation flag to false after completion.
      
      ## Destructive mode
      - Set both mutation and destructive flags true.
      - Execute destructive command only with explicit confirmation token.
      - Immediately disable destructive flag after operation.
      
      ## Process and session lifecycle
      - A stdio server exits on its own when its host dies (stdin end/close, or re-parenting away from the ppid it started with). Seeing `shutting down orphaned stdio server` in stderr with a `reason` is expected, not a fault.
      - HTTP sessions end on `DELETE /mcp`, on SSE disconnect, or via the idle sweep at `MCP_HTTP_SESSION_TIMEOUT_MS` (default 30 min, `0` disables).
      - `curl -s http://127.0.0.1:8819/health` reports `activeSessions`; a count that only ever climbs means clients are dropping without terminating.
      
      ## Verification commands
      - `npm run mcp:typecheck`
      - `npm run mcp:build`
      
    • tool-domain-map.md 1.2 KB
      # MCP Tool Domain Map
      
      - `observability-tools.ts`: health, scoped stats/analytics, export, snapshots, Prometheus.
      - `session-tools.ts`: scoped session list/get/create/update.
      - `session-detail-tools.ts`: facets, stats, transcripts, transcript images, event facets.
      - `agent-tools.ts`: scoped agent list/get/create/update.
      - `event-tools.ts`: complete event filtering and hook ingestion.
      - `pricing-tools.ts`: Claude and GPT/Codex pricing CRUD plus scoped cost.
      - `workflow-tools.ts`: aggregate/session workflow data and Workflow-tool runs.
      - `alert-tools.ts`: fired alerts, acknowledgments, and alert-rule CRUD.
      - `webhook-tools.ts`: provider discovery, target CRUD, tests, and delivery history.
      - `import-tools.ts`: provider guides, rescan, path scan, multipart upload, export restore.
      - `config-tools.ts`: Claude and Codex discovery plus backup-backed allowlisted edits.
      - `run-tools.ts`: Run Agent discovery, launch, follow-up, inspection, and stop.
      - `remote-tools.ts`: remote source CRUD, probe, sync, and confirmed purge.
      - `settings-tools.ts`: updates, Claude/Codex homes, and hook installation.
      - `push-tools.ts`: push key, subscription lifecycle, and external notification send.
      - `maintenance-tools.ts`: cleanup, reimport, reinstall hooks, destructive clear.
      
  • SKILL.md 1.2 KB
    ---
    name: mcp-operations
    description: Operate and maintain the local MCP server for this project. Use when creating MCP host config, troubleshooting tool connectivity, modifying tool domains, or adjusting safety policy flags.
    ---
    
    # MCP Operations
    
    Use this skill whenever work touches `mcp/` behavior or MCP host integration.
    
    ## Core workflow
    - Confirm dashboard API is running (`/api/health`).
    - Confirm MCP server build status.
    - Validate env flags for mutation/destructive modes.
    - Verify host configuration path and command.
    
    ## Safe operations policy
    - Default to read-only mode (`MCP_DASHBOARD_ALLOW_MUTATIONS=false`).
    - Enable mutations only for explicit admin tasks.
    - Enable destructive mode only transiently and require explicit confirmation token.
    
    ## Required verification for code changes
    - `npm run mcp:typecheck`
    - `npm run test:mcp`
    - `npm run mcp:build`
    
    ## Catalog invariant
    - Add tools only through `mcp/src/tools/domains/` and `registerAllTools`.
    - Protocol transports and REPL must use the same declarations and schemas.
    - Update `.agents/skills/mcp-maintainer/references/tool-domain-map.md` when a domain changes.
    
    ## References
    - Host config examples: `references/host-config.md`
    - Operations runbook: `references/runbook.md`
    

Comments (0)

Sign in to join the conversation.

No comments yet.

Reviews (0)

No reviews yet.

Related