Borrowing it
Nothing to install: this file belongs to ruaan-deysel/unraid-management-agent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ruaan-deysel/unraid-management-agent/main/.github/prompts/Add MCP Tool.prompt.mdgit clone --depth 1 https://github.com/ruaan-deysel/unraid-management-agentWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/ruaan-deysel/unraid-management-agent/add-mcp-tool)<a href="https://agentmods.dev/commands/ruaan-deysel/unraid-management-agent/add-mcp-tool"><img src="https://agentmods.dev/badge/commands/ruaan-deysel/unraid-management-agent/add-mcp-tool/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/ruaan-deysel/unraid-management-agent/add-mcp-tool"><img src="https://agentmods.dev/badge/commands/ruaan-deysel/unraid-management-agent/add-mcp-tool.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00014 | $0.00315 |
| Opus 5 | $0.00007 | $0.00158 |
| Sonnet 5 | $0.00003 | $0.00063 |
| Haiku 4.5 | $0.00001 | $0.00032 |
Grade A, and why
Add MCP Tool 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 3d 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.
What it actually says
Add a New MCP Tool
Follow these steps to add a new tool to the MCP (Model Context Protocol) server.
Step 1: Identify the Tool
Decide what the tool should do:
- Monitoring tool: Returns system data (read-only)
- Control tool: Performs an action (start/stop/restart, etc.)
Step 2: Define the Tool
In daemon/services/mcp/server.go, register the new tool following existing patterns.
Tool Registration Pattern
Look at existing tools in server.go for the registration pattern. Each tool needs:
- A unique tool name (snake_case)
- A clear description of what it does
- Input schema (if it accepts parameters)
- Handler function
Step 3: Implement the Handler
The handler should:
- Parse and validate input parameters
- Call existing collector caches or controller methods
- Return a structured JSON response
For monitoring tools
Access cached data through the API server's cache fields.
For control tools
Use existing controllers in daemon/services/controllers/. Always validate input before executing.
Step 4: Test
- Add tests in
daemon/services/mcp/test files - Test valid inputs, invalid inputs, and edge cases
Step 5: Document
- Update MCP documentation in
docs/integrations/mcp.md - Update
CHANGELOG.md
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.
- 3d ago First seen · 55 lines · 14 tokens per session scan A 99cc32d5e627
Add MCP Tool is a command published in the GitHub repository ruaan-deysel/unraid-management-agent (53 stars, last pushed 2d ago), licensed MIT. It adds 14 tokens to every session and 315 once invoked, about $0.0001 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 2026-09-07.
Other commands, from other repositories
jaz-capabilities
What Jaz can do — the full operation map.
init
Initialize configurations for Supabase local development.
publish-api-docs
Generate interactive API documentation from blueprint specs (Swagger UI, Redoc, AsyncAPI).
flow-nexus-auth
Flow Nexus authentication and user management.
multi-backend
Backend-focused workflow (Research → Ideation → Plan → Execute → Optimize → Review), Codex-led.
checklist
Generate a custom checklist for the current feature based on user requirements.