mcp-tool

mcp-tool is an agent for Cursor from jamesjfoong/github-pr-review-mcp. It costs 23 tokens per session (403 once invoked), scanned A, original, MIT.

An agent that manages the structure and registration of MCP tools, which are callable functions an AI assistant can use.

In plain words
What is it for?
Adding, changing, or debugging GitHub-related MCP tools across the schema, service code, server entry point, and README.
Why use it?
It helps keep each tool's input rules, implementation, registration, responses, and documentation aligned.

Agent for Cursor

Install

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.

agentmods
npx agentmods add agents/jamesjfoong/github-pr-review-mcp/mcp-tool
Clone the repo
git clone --depth 1 https://github.com/jamesjfoong/github-pr-review-mcp

Made for: Cursor.

Wrote 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.

agentmods badge for mcp-tool

README.md
[![agentmods](https://agentmods.dev/badge/agents/jamesjfoong/github-pr-review-mcp/mcp-tool.svg)](https://agentmods.dev/agents/jamesjfoong/github-pr-review-mcp/mcp-tool)
Your own site
<a href="https://agentmods.dev/agents/jamesjfoong/github-pr-review-mcp/mcp-tool"><img src="https://agentmods.dev/badge/agents/jamesjfoong/github-pr-review-mcp/mcp-tool.svg" alt="Measured on agentmods" height="20"></a>
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 403 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00023 $0.00403
Opus 5 $0.00012 $0.00201
Sonnet 5 $0.00005 $0.00081
Haiku 4.5 $0.00002 $0.00040

Measured 5d ago against content hash 44b09efe5991, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

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 5d 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.

.cursor/agents/mcp-tool.md · 70 lines

What it actually says

MCP Tool Agent

Purpose: Manages MCP tool registration and ensures proper tool structure.

Responsibilities

  • Follow 3-step process for adding tools (schema → service → registration)
  • Ensure proper tool descriptions
  • Verify parameter schemas match service method parameters
  • Check tool responses are properly formatted
  • Update README.md tool table when adding tools

When to Use

When adding new MCP tools, modifying existing tools, or debugging tool issues.

Key Rules

  1. Define schema in src/types.ts
  2. Add service method in src/github-service.ts
  3. Register tool in src/index.ts
  4. Update README.md tool table
  5. Export both schema and type from types.ts

3-Step Process

Step 1: Define Schema (src/types.ts)

export const NewToolSchema = z.object({
  owner: z.string().describe("Repository owner"),
  repo: z.string().describe("Repository name"),
});
// Explicit type (preferred over z.infer<typeof>)
export interface NewToolParams {
  owner: string;
  repo: string;
  prNumber: number;
}

Step 2: Add Service Method (src/github-service.ts)

async newMethod(params: NewToolParams): Promise<ResultType> {
  // Implementation using this.octokit
}

Step 3: Register Tool (src/index.ts)

server.addTool({
  name: "new_tool",
  description: "Clear description",
  parameters: NewToolSchema,
  execute: async (params) => {
    const result = await githubService.newMethod(params);
    return {
      content: [{ type: "text", text: JSON.stringify(result, null, 2) }],
    };
  },
});
Changes

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.

  1. 5d ago First seen · 70 lines · 23 tokens per session scan A 44b09efe5991

Subscribe to this mod's changes

mcp-tool is an agent published in the GitHub repository jamesjfoong/github-pr-review-mcp (1 stars, last pushed 6mo ago), licensed MIT. It adds 23 tokens to every session and 403 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 2026-08-31.