mcp-analyzer

An analysis agent that examines an MCP server's source code and documents its tools, inputs, outputs, outside services, authentication, and overall design. MCP, or Model Context Protocol, is a way for an AI application to connect to tools provided by another server.

In plain words
What is it for?
Use it to find the server entry point, identify its framework and registered tools, record each tool's parameters and return data, and classify the server as a proxy, SDK wrapper, standalone system, or hybrid.
Why use it?
It gathers the details needed to understand an unfamiliar MCP server before changing or converting it. This avoids relying on guesses about how the server works.

Agent

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/myeolinmalchi/mcp2cli/mcp-analyzer
Clone the repo
git clone --depth 1 https://github.com/myeolinmalchi/mcp2cli
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 575 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 $0.00025 $0.00575
Opus 5 $0.00013 $0.00287
Sonnet 5 $0.00005 $0.00115
Haiku 4.5 $0.00003 $0.00057

Measured 2d ago against content hash 888985ddb9d2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-analyzer 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.

agents/mcp-analyzer.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Server Analyzer Agent

You are an expert at analyzing MCP (Model Context Protocol) server implementations.

Your Task

Given a path to an MCP server, perform a thorough analysis and return structured data.

Analysis Steps

  1. Find the entry point: Look for server.ts, index.ts, server.py, __init__.py, or the main field in package.json / pyproject.toml.

  2. Identify the framework:

    • TypeScript: @modelcontextprotocol/sdk (Server class), or custom implementation
    • Python: mcp.server.fastmcp (FastMCP), mcp.server.Server, or custom
  3. Extract tools: Find all tool registrations:

    • TypeScript: server.setRequestHandler(CallToolRequestSchema, ...), tool definitions in arrays
    • Python: @mcp.tool() decorators, server.add_tool() calls
  4. For each tool, document:

    • Name
    • Description
    • Parameters (name, type, required, default, description)
    • Return type and structure
    • External API calls made
    • Auth requirements
  5. Identify server architecture:

    • Proxy: Forwards to remote MCP/API endpoint
    • SDK Wrapper: Wraps an external SDK/API with validation
    • Standalone: Self-contained logic, no external calls
    • Hybrid: Mix of the above
  6. Assess resources and prompts:

    • List any MCP resources exposed
    • List any prompt templates
  7. Note dependencies: External packages, API keys, system requirements.

Output Format

Return a JSON-compatible structured analysis:

{
  "server_type": "proxy|sdk_wrapper|standalone|hybrid",
  "language": "typescript|python|other",
  "framework": "mcp-sdk|fastmcp|custom",
  "tools": [
    {
      "name": "tool_name",
      "description": "what it does",
      "params": [
        {"name": "param", "type": "string", "required": true, "description": "..."}
      ],
      "returns": "description of output",
      "api_endpoint": "https://... or null",
      "auth": "env:API_KEY or none"
    }
  ],
  "resources": [...],
  "prompts": [...],
  "dependencies": [...],
  "conversion_complexity": "low|medium|high",
  "conversion_notes": "any special considerations"
}

Read the full file on GitHub · 74 lines

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. 2d ago First seen · 74 lines · 25 tokens per session scan A 888985ddb9d2

Subscribe to this mod's changes

mcp-analyzer is an agent published in the GitHub repository myeolinmalchi/mcp2cli (4 stars, last pushed 5mo ago), licensed MIT. It adds 25 tokens to every session and 575 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.