mcp-server-reviewer
Reviews MCP servers for quality, security, and best practices, providing scores and improvement plans.
README
MCP Server Reviewer π
μΌλ° μ¬μ©μκ° λ§λ MCP(Model Context Protocol) μλ²μ νμ§μ μ’ ν© κ²ν νλ MCP μλ²μ λλ€.
νκ° μμ (μ΄ 100μ )
| μμ | λ°°μ | ν΅μ¬ νκ° νλͺ© |
|---|---|---|
| κΈ°μ μ ꡬν νμ§ | 25μ | Tool μ μ, νλΌλ―Έν°, μλ¬ νΈλ€λ§, Transport |
| μ€λ¬΄ νμ© κ°μΉ | 25μ | λ¬Έμ ν΄κ²°λ ₯, μ°¨λ³μ , Tool granularity |
| 보μ λ° μμ μ± | 20μ | μΈμ¦, μΈμ μ λ°©μ§, Secrets κ΄λ¦¬ |
| μ½λ νμ§ | 15μ | SDK νμ©, λ¬Έμν, ν μ€νΈ, νμ μμ μ± |
| ν΅ν©μ± λ° νμ₯μ± | 15μ | ν΄λΌμ΄μΈνΈ νΈν, λ°°ν¬, νμ₯ μ©μ΄μ± |
λ±κΈ 체κ³
- S (90+): νλ‘λμ λ λ, λͺ¨λ² μ¬λ‘ μμ€
- A (80-89): μ°μ, μμ κ°μ μ λ§ μ‘΄μ¬
- B (70-79): μνΈ, μΌλΆ μμ κ°μ νμ
- C (60-69): 보ν΅, μλΉν κ°μ νμ
- D (60 λ―Έλ§): λ―Έν‘, ν΅μ¬ μμ μ¬μμ νμ
μ 곡 λꡬ (Tools)
1. review_mcp_server
MCP μλ² μ 체 μ½λλ₯Ό μ’ ν© κ²ν ν©λλ€.
- 리ν¬νΈ λͺ¨λ: μ μνλ νκ°ν + κ°μ κΆκ³ 리ν¬νΈ
- μ½μΉ λͺ¨λ: λνν λ¨κ³λ³ νΌλλ°±
2. review_tool_definition
κ°λ³ Tool μ μμ νμ§μ μ§μ€ κ²ν ν©λλ€.
- Tool name 컨벀μ μ€μ μ¬λΆ
- Descriptionμ LLM μΉνμ±
- inputSchema μ€κ³ μ μ μ±
3. review_security
보μ μΈ‘λ©΄λ§ μ§μ€ κ²ν ν©λλ€.
- νλμ½λ©λ μν¬λ¦Ώ νμ§
- μΈμ μ μν λΆμ
- λ°μ΄ν° λ ΈμΆ μν νκ°
4. compare_mcp_servers
λ MCP μλ²λ₯Ό λΉκ΅ λΆμν©λλ€.
- λμΌ λͺ©μ μλ² κ° νμ§ λΉκ΅
- κ°κ°μ κ°μ /μ½μ λμ‘°
5. generate_improvement_plan
μ°μ μμλ³ κ°μ λ‘λλ§΅μ μμ±ν©λλ€.
- Critical/High/Medium/Low λΆλ₯
- ꡬ체μ μ‘μ μμ΄ν + μμ μμ μκ°
μ€μΉ λ° μ€ν
μ€μΉ
cd mcp-server-reviewer
pip install -e .
μ€ν (μ§μ )
python -m mcp_server_reviewer.server
Amazon Quickμμ μ¬μ©
Settings β Capabilities β MCP Serversμμ μΆκ°:
{
"mcp-server-reviewer": {
"command": "python",
"args": ["-m", "mcp_server_reviewer.server"],
"cwd": "C:\\Users\\ktaewoo\\Desktop\\Workspace2026\\mcp-server-reviewer\\src"
}
}
Claude Desktopμμ μ¬μ©
claude_desktop_config.json:
{
"mcpServers": {
"mcp-server-reviewer": {
"command": "python",
"args": ["-m", "mcp_server_reviewer.server"],
"cwd": "C:\\Users\\ktaewoo\\Desktop\\Workspace2026\\mcp-server-reviewer\\src"
}
}
}
μ¬μ© μμ
μ’ ν© κ²ν
"μ΄ MCP μλ² μ½λλ₯Ό κ²ν ν΄μ€" + μμ€μ½λ 첨λΆ
보μ μ§μ€ κ²ν
"μ΄ MCP μλ²μ 보μ μ·¨μ½μ μ λΆμν΄μ€"
λ μλ² λΉκ΅
"A μλ²μ B μλ² μ€ μ΄λ€ κ²μ΄ λ λμμ§ λΉκ΅ν΄μ€"
κ°μ κ³ν μ립
"μ΄ MCP μλ²λ₯Ό 2μ£Ό μμ κ°μ νλ λ‘λλ§΅μ λ§λ€μ΄μ€"
νμ 곡μ
μ΄ MCP μλ²λ₯Ό νμμ νκ²½μ μ€μΉνλ©΄ λμΌν κ²ν κΈ°λ₯μ μ¬μ©ν μ μμ΅λλ€:
- μ΄ ν΄λλ₯Ό 곡μ νκ±°λ Git 리ν¬μ§ν λ¦¬λ‘ κ΄λ¦¬
- κ° νμμ΄
pip install -e .μ€ν - Amazon Quick λλ Claude Desktop μ€μ μ μλ² μΆκ°
κΈ°μ μ€ν
- Python 3.10+
- MCP SDK (stdio transport)
- μ μ λΆμ κΈ°λ° μ½λ κ²ν (regex pattern matching)
λΌμ΄μ μ€
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.