ModelsAtlas
Explore
Atlas / MCP servers / gobinfan / Agentdocs

AgentdocsSAFE

mcp/gobinfan/agentdocs
MCP server by gobinfan · agent · llm · mcp · Audited 2026-10-07
⚑ Report / re-scanSource ↗

支持查询主流agent框架技术文档的MCP server(支持stdio和sse两种传输协议), 支持 langchain、llama-index、autogen、agno、openai-agents-sdk、mcp-doc、camel-ai 和 crew-ai

Verdict
SAFE
Grade
B
Trust score
89 /100
Exposed tools
1 1r · 0w · 0d
Transport
stdio
License
—
Stars
153
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

[](https://mseep.ai/app/gobinfan-python-mcp-server-client)

中文 | English

简介

MCP Server 是实现模型上下文协议(MCP)的服务器,旨在为 AI 模型提供一个标准化接口,连接外部数据源和工具,例如文件系统、数据库或 API。

MCP 的优势

在 MCP 出现前,AI 调用工具基本通过 Function Call 完成,存在以下问题:

  1. 不同的大模型厂商 Function Call 格式不一致
  2. 大量 API 工具的输入和输出格式不一致,封装管理繁琐

MCP 相当于一个统一的 USB-C,不仅统一了不同大模型厂商的 Function Call 格式,也对相关工具的封装进行了统一。

MCP 传输协议

目前 MCP 支持两种主要的传输协议:

  1. Stdio 传输协议
  2. 针对本地使用
  3. 需要在用户本地安装命令行工具
  4. 对运行环境有特定要求
  1. SSE(Server-Sent Events)传输协议
  2. 针对云服务部署
  3. 基于 HTTP 长连接实现

项目结构

MCP Server

  • Stdio 传输协议(本地)
  • SSE 传输协议(远程)

MCP Client(客户端)

  • 自建客户端(Python)
  • Cursor
  • Cline

环境配置

1. 安装 UV 包

MacOS/Linux:

curl -LsSf https://astral.sh/uv/install.sh | sh

Windows:

powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"

2. 初始化项目

# 创建项目目录
uv init mcp-server
cd mcp-server

# 创建并激活虚拟环境
uv venv
source .venv/bin/activate  # Windows: .venv\Scripts\activate

# 安装依赖
uv add "mcp[cli]" httpx

# 创建服务器实现文件
touch main.py

构建工具函数

为了让大模型能访问市面上主流框架的技术文档,我们主要通过用户输入的 query,结合指定 site 特定域名的谷歌搜索进行搜索相关网页,并对相关网页进行解析提取网页文本并返回。

1. 构建相关文档映射字典

docs_urls = {
"langchain": "python.langchain.com/docs",
"llama-index": "docs.llamaindex.ai/en/stable",
"autogen": "microsoft.github.io/autogen/stable",
"agno": "docs.agno.com",
"openai-agents-sdk": "openai.github.io/openai-agents-python",
"mcp-doc": "modelcontextprotocol.io",
"camel-ai": "docs.camel-ai.org",
"crew-ai": "docs.crewai.com"
}

##

Read from source at commit 02576a3562a1OBSERVED · 2026-10-07
02

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.

claude-code
claude mcp add mcp-server --env OPENAI_API_KEY=${OPENAI_API_KEY} --env SERPER_API_KEY=${SERPER_API_KEY} -- uvx mcp-server
claude-desktop
{
  "mcpServers": {
    "mcp-server": {
      "command": "uvx",
      "args": [
        "mcp-server"
      ],
      "env": {
        "OPENAI_API_KEY": "${OPENAI_API_KEY}",
        "SERPER_API_KEY": "${SERPER_API_KEY}"
      }
    }
  }
}
03

Exposed tools (1)

1 read · 0 write · 0 destructive.

ToolRiskDescription
get_docsread
04

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codePASS
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
none-observed
Network
declared (4 observation(s))
Shell
none-observed
Dependencies
pinned
Secrets in source
none-found

Findings (7)

LOWInventory / provenance · inv.no_license · CWE-1104
Why it matters. no LICENSE file and no repo licence
Fix. add a licence
LOWNetwork egress · net.raw_ip · CWE-200, CWE-319
README.md:641
uv run client.py http://0.0.0.0:8020/sse
LOWNetwork egress · net.raw_ip · CWE-200, CWE-319
README_EN.md:623
uv run client.py http://0.0.0.0:8020/sse
INFOPrompt injection · prompt.credential_read · CWE-94, CWE-1427
README.md:492
load_dotenv()  # load environment variables from .env
Why it matters. asks the agent to read credentials
INFOPrompt injection · prompt.credential_read · CWE-94, CWE-1427
README_EN.md:472
load_dotenv()  # load environment variables from .env
Why it matters. asks the agent to read credentials
INFOSupply chain · prompt.pipe_to_shell · CWE-829, CWE-1357
README.md:56
curl -LsSf https://astral.sh/uv/install.sh | sh
INFOSupply chain · prompt.pipe_to_shell · CWE-829, CWE-1357
README_EN.md:52
curl -LsSf https://astral.sh/uv/install.sh | sh

Gates applied: no_behavioural_pass, no_license.

Audited 2026-10-07 · audit v0.4.1 · source sha 02576a3562a1full audit observations/trust-audit/mcp-server/gobinfan__agentdocs.json · Report an issue / request a re-scan
05

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

DateSourceVerdictGradeScoreChange
2026-10-0702576a3562a1SAFEB89first audit
06

Questions

What is the Agentdocs MCP server?

支持查询主流agent框架技术文档的MCP server(支持stdio和sse两种传输协议), 支持 langchain、llama-index、autogen、agno、openai-agents-sdk、mcp-doc、camel-ai 和 crew-ai

What tools does Agentdocs expose?

1 in total: 1 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.

Is Agentdocs safe to connect to an agent?

The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.

What credentials does Agentdocs need?

It reads OPENAI_API_KEY and SERPER_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.

How does Agentdocs run?

It speaks stdio, so it runs as a local process your client starts. It is published on PyPI as mcp-server.

How current is this page?

The grade is for one exact copy of the source (02576a3562a1), read on 2026-10-07. The repository is watched and re-audited when it changes.

Advertisement