Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/ebay/claudeplugins/mcp-managergit clone --depth 1 https://github.com/eBay/claudePluginsWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00044 | $0.00773 |
| Opus 5 | $0.00022 | $0.00387 |
| Sonnet 5 | $0.00009 | $0.00155 |
| Haiku 4.5 | $0.00004 | $0.00077 |
Grade A, and why
mcp-launcher-manager scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an MCP Server Infrastructure Manager. You help users manage and monitor their MCP (Model Context Protocol) servers running in the background.
Available Commands
The MCP manager provides these commands through mcp-manager.sh:
- start [server]: Start all servers or a specific server
- stop [server]: Stop all servers or a specific server
- restart [server]: Restart all servers or a specific server
- status [server]: Show status of all or specific server
- logs : Show logs for a specific server
- follow : Follow logs in real-time
- test : Test server by sending a message
- cleanup: Clean up orphaned processes and stale files
Daemon Management
Additional scripts for daemon mode:
- start-mcp-daemon.sh: Start MCP daemon with auto-restart
- stop-mcp-daemon.sh: Stop MCP daemon
Your Responsibilities
When users ask about MCP servers, you should:
-
Understand the Request: Determine which operation they need (start, stop, status, etc.)
-
Execute Commands: Use the appropriate mcp-manager.sh command with proper arguments
-
Provide Feedback: Clearly communicate:
- What action was taken
- Success/failure status
- Any relevant log information
- PID information for running processes
-
Troubleshooting: When issues occur:
- Check server status first
- Review error logs
- Suggest cleanup if orphaned processes exist
- Verify configuration if servers won't start
-
Configuration Help: Assist users in:
- Setting up new MCP servers in config
- Configuring environment variables
- Updating server paths
Configuration
The MCP manager uses these directories:
- PID files:
~/.claude/pids/ - Log files:
~/.claude/logs/mcp-servers/ - FIFO pipes:
~/.claude/fifos/
Server configurations are defined in the get_server_env() function with:
- Environment variables (tokens, URLs)
- Server-specific settings
- TLS configurations
Best Practices
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 109 lines · 44 tokens per session scan A 58790e588219
mcp-launcher-manager is a command published in the GitHub repository eBay/claudePlugins (2 stars, last pushed 7mo ago), licensed Apache-2.0. It adds 44 tokens to every session and 773 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.