Skip to main content
Glama

agentvet-mcp

@mukundakatta/agentvet 的 MCP 服务器。 让 Claude Desktop、Cursor、Cline、Windsurf、Zed 或任何其他 MCP 客户端能够在执行前验证 LLM 生成的工具调用参数,并在出现问题时生成对 LLM 友好的重试消息。

npx -y @mukundakatta/agentvet-mcp

包含三个工具:

  • validate_tool_args — 根据小型形状规范检查参数;返回 { valid, error?, retry_hint? },其中 retry_hint 是可直接发送给 LLM 的反馈消息。

  • lint_tool_definition — 对工具定义进行健全性检查,以发现可能影响 LLM 工具使用准确性的常见错误。

  • generate_retry_message — 给定验证错误,使用 agentvet 的 ToolArgError.toLLMFeedback() 格式构建规范的面向 LLM 的重试消息。

添加到您的客户端

Claude Desktop

编辑 ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) 或 %APPDATA%\Claude\claude_desktop_config.json (Windows):

{
  "mcpServers": {
    "agentvet": {
      "command": "npx",
      "args": ["-y", "@mukundakatta/agentvet-mcp"]
    }
  }
}

Cursor (~/.cursor/mcp.json)、Cline、Windsurf、Zed 的配置格式相同。

Related MCP server: Echo MCP

工具示例

validate_tool_args

{
  "tool_name": "send_email",
  "args": { "to": "a@b.com" },
  "shape": { "to": "string", "subject": "string", "body": "string" }
}

返回:

{
  "valid": false,
  "error": "missing required field: subject",
  "retry_hint": "send_email rejected your args: missing required field: subject. Please call again with the corrected arguments."
}

lint_tool_definition

{
  "tool": {
    "name": "BadName",
    "inputSchema": { "type": "object", "properties": { "x": { "type": "string" } } }
  }
}

返回关于非 snake_case 名称、缺少描述、缺少字段描述以及没有必填字段的警告。

generate_retry_message

{
  "tool_name": "send_email",
  "validation_error": "missing required field: subject",
  "attempted_args": { "to": "a@b.com" }
}

返回运行时调用者看到的规范重试反馈字符串——这样您可以在实时代理循环之外准备重试文本。

为什么需要单独的 MCP 服务器

@mukundakatta/agentvet 是一个零依赖的 JavaScript 库。此 MCP 服务器使任何支持 MCP 的 AI 助手都能访问其验证原语。这对于快速审计工具注册表,或者在不离开聊天界面的情况下询问助手“这个参数对象对于我的 send_email 工具是否有效?”非常有用。

若要在代理循环中进行运行时参数验证,请直接在您的 Node 进程中使用 @mukundakatta/agentvet(它会包装您的工具函数并同步抛出 ToolArgError)。

同系列 MCP 服务器

属于 agent-stack 系列:

许可证

MIT

Install Server
A
license - permissive license
A
quality
C
maintenance

Maintenance

Maintainers
Response time
Release cycle
Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Servers

  • A
    license
    Not graded
    quality
    F
    maintenance
    A MCP server that exposes OpenAPI schema information to LLMs like Claude. This server allows an LLM to explore and understand large OpenAPI schemas through a set of specialized tools, without needing to load the whole schema into the context
    113
    50
    MIT
  • A
    license
    Not graded
    quality
    D
    maintenance
    A lightweight server that enables AI agents to emit and validate structured messages through MCP tool call returns. It facilitates reliable programmatic consumption of agent outputs by echoing validated payloads against predefined schemas.
    8
    MIT
  • A
    license
    Not graded
    quality
    D
    maintenance
    An MCP server that wraps Spectral to lint OpenAPI specifications, enabling LLMs to validate and fix API definitions.
    1
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    MCP server that routes natural language requests to structured tool calls using a LoRA-tuned small language model, with built-in validation, retry, and fallback recovery.
    MIT

View all related MCP servers

Related MCP Connectors

  • MCP server providing access to the Scorecard API to evaluate and optimize LLM systems.

  • MCP server for AI agents to plan, verify, and deploy Cloudflare-native apps.

  • MCP server for secureFlows: token-free URL builders and integration-linting tools for AI agents.

View all MCP Connectors

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/MukundaKatta/agentvet-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server