How do I use RegistryTools?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@RegistryTools search for tools related to file conversion" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

RegistryTools

by GeerMrc

Overview Schema Related Servers Score Discussions

Python

Hybrid

RegistryTools

版本: v0.2.1 更新日期: 2026-01-11 独立 MCP Tool Registry Server - 通用工具搜索与发现服务

Python Version License MCP

简介

RegistryTools 是一个独立的 MCP Tool Registry Server，提供通用的工具搜索和发现能力。它可以被任何支持 MCP 协议的客户端（如 DeepThinking Agent、Cursor IDE、Claude Desktop）使用。

核心价值

减少 Token 消耗 85%: 从 ~77K 降至 ~8.7K（按需加载工具）
提升准确率: 工具选择准确率从 49% 提升至 74%
解耦复用: 独立部署，任何 MCP 客户端都可连接

Related MCP server: UTCP-MCP Bridge

快速开始

安装

# 从 PyPI 安装（推荐）
pip install registry-tools

# 或使用 uvx 无需安装
uvx registry-tools

# 本地开发环境（从源码安装）
cd RegistryTools
pip install -e .

注意:
生产环境: 使用 pip install registry-tools 或 uvx registry-tools
本地开发: 使用 pip install -e . 安装后，直接使用 registry-tools 命令

传输协议

RegistryTools 支持多种 MCP 传输协议:

协议	适用场景	配置方式
STDIO	本地 CLI 集成 (默认)	`registry-tools`
Streamable HTTP	远程服务部署	`registry-tools --transport http`

STDIO 模式 (默认)

适用于 Claude Desktop、本地脚本等本地集成场景。

Claude Desktop 配置:

在 Claude Desktop 配置文件中添加:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%/Claude/claude_desktop_config.json Linux: ~/.config/Claude/claude_desktop_config.json

本地开发配置 (用于开发):

{
  "mcpServers": {
    "RegistryTools": {
      "command": "registry-tools",
      "args": ["--data-path", "~/.RegistryTools"]
    }
  }
}

生产环境配置 (推荐用于生产):

{
  "mcpServers": {
    "RegistryTools": {
      "command": "uvx",
      "args": ["registry-tools", "--data-path", "~/.RegistryTools"]
    }
  }
}

Streamable HTTP 模式 (远程部署)

适用于远程服务、容器化部署、多客户端共享等场景。

启动 HTTP 服务器:

# 使用默认参数 (127.0.0.1:8000)
registry-tools --transport http

# 自定义主机和端口
registry-tools --transport http --host 0.0.0.0 --port 8000

# 自定义路径
registry-tools --transport http --port 8000 --path /api/mcp

客户端连接示例:

{
  "mcpServers": {
    "RegistryTools": {
      "url": "http://localhost:8000/mcp"
    }
  }
}

存储后端选择

RegistryTools 支持两种存储后端用于持久化工具元数据：

存储类型	适用场景	配置方式
JSON	小规模工具集（< 1000 工具），默认	`registry-tools`
SQLite	大规模工具集（> 1000 工具），高性能	`export REGISTRYTOOLS_STORAGE_BACKEND=sqlite`

默认行为：使用 JSON 文件存储，适合大多数场景。

何时使用 SQLite：

工具数量超过 1000 个
需要高性能查询和过滤
需要支持并发访问
需要 ACID 事务保证

环境变量配置：

# 使用 SQLite 存储
export REGISTRYTOOLS_STORAGE_BACKEND=sqlite
registry-tools

# 或使用 CLI 参数
registry-tools --storage-backend sqlite

完整配置示例：

{
  "mcpServers": {
    "RegistryTools": {
      "command": "registry-tools",
      "env": {
        "REGISTRYTOOLS_STORAGE_BACKEND": "sqlite"
      }
    }
  }
}

性能对比：

操作	JSON 存储	SQLite 存储
加载 1000 工具	~75ms	~18ms (76% 提升)
按标签过滤	~15ms	~4ms (73% 提升)
内存占用	~15MB	~6MB (60% 减少)

详见存储选择指南。

fastmcp.json 配置

使用 fastmcp.json 进行声明式配置 (推荐):

# 使用配置文件启动
fastmcp run fastmcp.json

# 或直接运行 (自动检测当前目录的 fastmcp.json)
fastmcp run

fastmcp.json 示例:

{
  "$schema": "https://gofastmcp.com/public/schemas/fastmcp.json/v1.json",
  "source": {
    "path": "src/registrytools/__main__.py",
    "entrypoint": "main"
  },
  "deployment": {
    "transport": "http",
    "host": "0.0.0.0",
    "port": 8000,
    "path": "/mcp"
  }
}

详见: fastmcp.json (STDIO 默认配置) 详见: fastmcp.http.json (HTTP 配置示例)

Claude Code (VSCode) 配置

Claude Code 是 Anthropic 官方的 VSCode AI 助手，支持通过 MCP 协议集成 RegistryTools。

方式 1：CLI 命令（推荐）

使用 Claude Code CLI 命令快速配置：

STDIO 本地服务器：

本地开发配置 (用于开发):

# 基础配置（直接使用已安装的命令）
claude mcp add --transport stdio RegistryTools -- registry-tools

# 带环境变量
claude mcp add --transport stdio RegistryTools \
  --env REGISTRYTOOLS_LOG_LEVEL=INFO \
  -- registry-tools

生产环境配置 (推荐用于生产):

# 基础配置（使用 uvx）
claude mcp add --transport stdio RegistryTools -- uvx registry-tools

# 带环境变量
claude mcp add --transport stdio RegistryTools \
  --env REGISTRYTOOLS_LOG_LEVEL=INFO \
  -- uvx registry-tools

Streamable HTTP 远程服务器：

# 无认证
claude mcp add --transport http RegistryTools-Remote http://localhost:8000/mcp

# 使用 API Key 认证
# 1. 先启用认证并创建 API Key
registry-tools --transport http --enable-auth
registry-tools api-key create "Claude Code" --permission read

# 2. 添加服务器（使用 API Key）
claude mcp add --transport http RegistryTools-Remote \
  http://localhost:8000/mcp \
  --header "X-API-Key: rtk_your_api_key_here"

管理命令：

claude mcp list              # 列出所有服务器
claude mcp get RegistryTools  # 查看详情
claude mcp remove RegistryTools  # 删除服务器

配置范围：

# 项目级配置（可版本控制）
# 本地开发环境
claude mcp add --scope project --transport stdio RegistryTools -- registry-tools
# PyPI 发布后
claude mcp add --scope project --transport stdio RegistryTools -- uvx registry-tools

# 用户级配置（跨项目使用）
# 本地开发环境
claude mcp add --scope user --transport stdio RegistryTools -- registry-tools
# PyPI 发布后
claude mcp add --scope user --transport stdio RegistryTools -- uvx registry-tools

方式 2：配置文件

创建 .claude/config.json（项目级）或 ~/.claude/config.json（用户级）：

本地开发配置 (用于开发):

{
  "mcpServers": {
    "RegistryTools": {
      "command": "registry-tools",
      "env": {
        "REGISTRYTOOLS_DATA_PATH": "~/.RegistryTools",
        "REGISTRYTOOLS_LOG_LEVEL": "INFO"
      }
    }
  }
}

生产环境配置 (推荐用于生产):

{
  "mcpServers": {
    "RegistryTools": {
      "command": "uvx",
      "args": ["registry-tools"],
      "env": {
        "REGISTRYTOOLS_DATA_PATH": "~/.RegistryTools",
        "REGISTRYTOOLS_LOG_LEVEL": "INFO"
      }
    }
  }
}

方式 3：JSON 配置命令 (add-json)

使用 claude mcp add-json 命令直接通过 JSON 配置添加 MCP 服务器：

快速配置（单行）

STDIO 模式：

claude mcp add-json "RegistryTools" '{"command":"uvx","args":["registry-tools"]}' --scope user

HTTP 模式：

claude mcp add-json "RegistryTools-Remote" '{"url":"http://localhost:8000/mcp"}' --scope user

STDIO 模式完整配置

本地开发配置 (用于开发):

# 基础配置
claude mcp add-json "RegistryTools" '{"command":"registry-tools"}' --scope user

# 完整配置（所有环境变量）
claude mcp add-json "RegistryTools" '{
  "command": "registry-tools",
  "env": {
    "REGISTRYTOOLS_DATA_PATH": "~/.RegistryTools",
    "REGISTRYTOOLS_TRANSPORT": "stdio",
    "REGISTRYTOOLS_LOG_LEVEL": "INFO",
    "REGISTRYTOOLS_ENABLE_AUTH": "false",
    "REGISTRYTOOLS_SEARCH_METHOD": "bm25",
    "REGISTRYTOOLS_STORAGE_BACKEND": "json",
    "REGISTRYTOOLS_DEVICE": "cpu",
    "REGISTRYTOOLS_DESCRIPTION": "统一的 MCP 工具注册与搜索服务"
  }
}' --scope user

生产环境配置 (推荐用于生产):

# 基础配置（使用 uvx）
claude mcp add-json "RegistryTools" '{"command":"uvx","args":["registry-tools"]}' --scope user

# 完整配置（所有环境变量）
claude mcp add-json "RegistryTools" '{
  "command": "uvx",
  "args": ["registry-tools"],
  "env": {
    "REGISTRYTOOLS_DATA_PATH": "~/.RegistryTools",
    "REGISTRYTOOLS_TRANSPORT": "stdio",
    "REGISTRYTOOLS_LOG_LEVEL": "INFO",
    "REGISTRYTOOLS_ENABLE_AUTH": "false",
    "REGISTRYTOOLS_SEARCH_METHOD": "bm25",
    "REGISTRYTOOLS_STORAGE_BACKEND": "json",
    "REGISTRYTOOLS_DEVICE": "cpu",
    "REGISTRYTOOLS_DESCRIPTION": "统一的 MCP 工具注册与搜索服务"
  }
}' --scope user

HTTP 模式完整配置

无认证：

claude mcp add-json "RegistryTools-Remote" '{
  "url": "http://localhost:8000/mcp"
}' --scope user

使用 API Key 认证：

claude mcp add-json "RegistryTools-Remote" '{
  "url": "http://localhost:8000/mcp",
  "headers": {
    "X-API-Key": "rtk_your_api_key_here"
  }
}' --scope user

参数分类说明

参数	STDIO	HTTP	说明
`REGISTRYTOOLS_DATA_PATH`	✓	✓	数据存储目录
`REGISTRYTOOLS_TRANSPORT`	✓	-	传输协议
`REGISTRYTOOLS_LOG_LEVEL`	✓	✓	日志级别
`REGISTRYTOOLS_ENABLE_AUTH`	✓	✓	API Key 认证
`REGISTRYTOOLS_STORAGE_BACKEND`	✓	✓	存储后端
`REGISTRYTOOLS_SEARCH_METHOD`	✓	✓	搜索方法
`REGISTRYTOOLS_DEVICE`	✓	✓	Embedding 设备
`REGISTRYTOOLS_DESCRIPTION`	✓	✓	服务器描述

配置范围

# 项目级配置（可版本控制）
claude mcp add-json "RegistryTools" '{...}' --scope project

# 用户级配置（跨项目使用，默认）
claude mcp add-json "RegistryTools" '{...}' --scope user

# 本地级配置（项目特定，gitignored）
claude mcp add-json "RegistryTools" '{...}' --scope local

配置选项

RegistryTools 支持灵活的配置方式。完整配置说明请参见配置指南。

完整配置参数表格

环境变量	描述	默认值	可选值
`REGISTRYTOOLS_DATA_PATH`	数据目录路径	`~/.RegistryTools`	任意有效路径
`REGISTRYTOOLS_TRANSPORT`	传输协议	`stdio`	`stdio`, `http`
`REGISTRYTOOLS_LOG_LEVEL`	日志级别	`INFO`	`DEBUG`, `INFO`, `WARNING`, `ERROR`
`REGISTRYTOOLS_ENABLE_AUTH`	启用 API Key 认证	`false`	`true`, `false`, `1`, `0`, `yes`, `no`
`REGISTRYTOOLS_SEARCH_METHOD`	默认搜索方法	`bm25`	`regex`, `bm25`, `embedding`
`REGISTRYTOOLS_STORAGE_BACKEND`	存储后端类型	`json`	`json`, `sqlite`
`REGISTRYTOOLS_DEVICE`	Embedding 模型计算设备	`cpu`	`cpu`, `gpu:0`, `gpu:1`, `auto`
`REGISTRYTOOLS_DESCRIPTION`	MCP 服务器描述	统一的 MCP 工具注册与搜索服务...	任意有效字符串

完整配置示例

Claude Desktop 完整配置 (JSON 格式):

{
  "mcpServers": {
    "RegistryTools": {
      "command": "uvx",
      "args": ["registry-tools"],
      "env": {
        "REGISTRYTOOLS_DATA_PATH": "~/.RegistryTools",
        "REGISTRYTOOLS_TRANSPORT": "stdio",
        "REGISTRYTOOLS_LOG_LEVEL": "INFO",
        "REGISTRYTOOLS_ENABLE_AUTH": "false",
        "REGISTRYTOOLS_SEARCH_METHOD": "bm25",
        "REGISTRYTOOLS_STORAGE_BACKEND": "json",
        "REGISTRYTOOLS_DEVICE": "cpu",
        "REGISTRYTOOLS_DESCRIPTION": "统一的 MCP 工具注册与搜索服务"
      }
    }
  }
}

Claude Code add-json 配置: 参见上方方式 3：JSON 配置命令章节的完整配置示例。

快速示例:

# 自定义数据路径
export REGISTRYTOOLS_DATA_PATH=/custom/path
registry-tools

# HTTP 模式 + 认证
export REGISTRYTOOLS_TRANSPORT=http
export REGISTRYTOOLS_ENABLE_AUTH=true
registry-tools --host 0.0.0.0 --port 8000

# Embedding 搜索 + GPU
export REGISTRYTOOLS_SEARCH_METHOD=embedding
export REGISTRYTOOLS_DEVICE=gpu:0
registry-tools

配置优先级: 环境变量 > CLI 参数 > 默认值

详细配置: 参见配置指南

Embedding 搜索配置（可选）

Embedding 搜索提供语义理解能力，但需要额外的依赖和资源。

安装依赖:

pip install registry-tools[embedding]

环境变量:

REGISTRYTOOLS_SEARCH_METHOD=embedding - 启用语义搜索
REGISTRYTOOLS_DEVICE=gpu:0 - 使用 GPU 加速（可选）
- cpu - 使用 CPU（默认）
- gpu:0 / gpu:1 - 使用指定 GPU
- auto - 自动选择 GPU 或 CPU

性能对比:

方法	速度	准确率	内存占用
regex	最快	高	~50MB
bm25	快	高	~50MB
embedding	慢	最高	~550MB

GPU 内存需求:

模型	GPU 内存	CPU 内存
paraphrase-multilingual-MiniLM-L12-v2 (默认)	~500MB	~1GB
all-MiniLM-L6-v2	~100MB	~300MB

高级功能

API Key 认证

# 创建 API Key
registry-tools api-key create "My Key" --permission read

# 列出 API Key
registry-tools api-key list

# 删除 API Key
registry-tools api-key delete <key-id>

详细文档请参考:

使用示例

# 搜索工具
search_tools("github create pull request", "bm25", 5)

# 获取工具定义
get_tool_definition("github.create_pull_request")

# 按类别列出工具
list_tools_by_category("github", 20)

# 动态注册工具
register_tool(
    name="my.custom.tool",
    description="A custom tool for specific purpose"
)

功能特性

搜索算法

算法	描述	速度	适用场景
Regex	正则表达式精确匹配	最快	精确名称匹配
BM25	BM25 关键词搜索（支持中文分词）	快	关键词搜索（推荐）
Embedding	语义搜索（支持中英文）	中	语义理解和模糊匹配（可选依赖）

MCP 工具接口

search_tools - 搜索可用的 MCP 工具（支持 regex/bm25/embedding）
search_hot_tools - 快速搜索热工具（性能优化，仅搜索高频工具）
get_tool_definition - 获取工具的完整定义
list_tools_by_category - 按类别列出工具
register_tool - 动态注册新工具

性能提示: 对于大型工具集，使用 search_hot_tools 可提升搜索速度 40-60%。

MCP 资源接口

registry://stats - 工具注册表统计信息
registry://categories - 所有工具类别

架构设计

MCP Clients (任何支持 MCP 的应用)
    │
    ▼
RegistryTools (独立 MCP Server)
    │
    ├── Tool Registry (工具注册表)
    │   └── 管理所有工具的元数据和索引
    │
    ├── Search Engine (搜索引擎)
    │   ├── Regex 搜索 (精确匹配)
    │   ├── BM25 搜索 (关键词)
    │   └── Embedding 搜索 (语义)
    │
    └── Storage Layer (存储层)
        ├── JSON 文件存储
        └── SQLite 存储

详见 ARCHITECTURE.md

开发

环境设置

# 克隆项目
git clone https://github.com/maric/RegistryTools.git
cd RegistryTools

# 创建虚拟环境
python -m venv venv
source venv/bin/activate  # Linux/Mac
# venv\Scripts\activate  # Windows

# 安装开发依赖
pip install -e ".[dev]"

运行测试

# 运行所有测试
pytest

# 查看覆盖率
pytest --cov=RegistryTools --cov-report=html

代码格式化

# 格式化代码
black src/registrytools/ tests/

# 代码检查
ruff check src/registrytools/ tests/

贡献指南

请参阅 CONTRIBUTING.md

文档

架构设计 - 系统架构说明
API 文档 - API 接口文档
使用示例 - 代码示例
开发流程规范 - 开发流程规范
任务追踪 - 项目任务追踪
变更日志 - 版本变更记录

性能指标

指标	目标值
搜索响应时间	< 200ms (1000+ 工具)
内存占用	< 100MB (1000+ 工具)
索引构建时间	< 2s (1000+ 工具)

路线图

v0.2.1 (当前 - 2026-01-11)

✅ 所有 v0.1.1 功能
✅ 搜索引擎全局配置（REGISTRYTOOLS_SEARCH_METHOD 环境变量）
✅ search_method 参数可选（默认使用环境变量）
✅ search_hot_tools 自动回退机制（不支持 embedding 时自动使用 bm25）

v0.3.0 (计划中)

⏳ 分布式工具注册
⏳ 工具依赖管理
⏳ Web UI 管理界面

许可证

MIT License - 详见 LICENSE 文件

致谢

Anthropic - MCP 协议设计
FastMCP - MCP 服务器框架
rank-bm25 - BM25 算法实现

项目维护者: Maric 项目主页: GitHub

Available Tools

6 tools

get_tool_definitionA

获取指定工具的完整定义

返回工具的完整元数据，包括输入输出 Schema。

ParametersJSON Schema

Name	Required	Description	Default
`tool_name`	Yes	工具名称

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

A3.6/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the burden of behavioral disclosure. It states that it returns 'complete metadata including input and output Schema', which implies a read-only operation and clarifies the return content. However, it does not disclose behavior for nonexistent tool names, error cases, or any side effects. The disclosure is adequate for a simple getter but remains minimal.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise: two lines, the first stating the primary purpose and the second detailing the return value. It is front-loaded and contains no filler words, earning a perfect conciseness score.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with a single parameter, a true output schema, and no annotations, the description adequately conveys the tool's purpose and return value. It does not cover edge cases or error handling, but given the simplicity of the operation and the presence of an output schema, it is sufficiently complete without requiring additional explanation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema already documents the single parameter 'tool_name' with a description '工具名称'. The description adds no additional semantic meaning beyond referencing the 'specified tool' in the first sentence. With 100% schema description coverage, the baseline of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's action and target: '获取指定工具的完整定义' (get the complete definition of the specified tool). This is a specific verb+resource pairing, and it distinguishes from sibling tools like search_tools (which search) and list_tools_by_category (which list) by focusing on retrieving a single tool's full definition.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. It does not mention, for example, that this is for fetching a specific tool's metadata while search_tools is for discovering tools. No exclusions or alternative suggestions are given.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

list_tools_by_categoryB

按类别列出工具

列出指定类别下的所有工具。

ParametersJSON Schema

Name	Required	Description	Default
`limit`	No	返回结果数量，默认 20
`category`	Yes	工具类别，使用 "all" 列出所有类别

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

B3.4/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden, but it only states the purpose. It does not disclose behavior for edge cases like invalid categories, the effect of the limit parameter, or the structure of the returned tool list.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise with two sentences, but the second sentence is largely redundant with the first. It is front-loaded and contains no fluff, though it could be condensed further.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is relatively simple, but the description misses key context such as the special 'all' category value and how the limit parameter interacts. Since the schema covers these details, the description is minimally sufficient but not rich enough for a complex tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema already provides complete descriptions for both parameters (100% coverage). The tool description adds no extra semantic value beyond the schema, so it relies entirely on the schema's parameter descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool lists tools by category, using a specific verb and resource. It distinguishes from sibling tools like search_tools by focusing on category-based listing. The second sentence adds specificity about 'all tools under the specified category'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies the tool is for listing tools by category but provides no explicit guidance on when to choose this over search_tools or get_tool_definition. The schema hints at using 'all' for all categories, but the description itself does not offer alternatives or exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

register_toolB

动态注册新工具

向工具注册表中添加一个新的工具元数据。

ParametersJSON Schema

Name	Required	Description
`name`	Yes	工具名称（唯一标识符）
`tags`	No	工具标签列表（可选）
`category`	No	工具类别（可选）
`description`	Yes	工具描述

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

B3/5.0

Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description must carry the full burden of behavioral disclosure. However, it only restates the tool's purpose ('add new tool metadata') without explaining side effects, uniqueness constraints, overwrite behavior, or requiring special permissions. This is a significant gap for a mutation tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two short, focused sentences with no filler or repetition. It achieves maximum clarity with minimal words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Although an output schema exists, the description omits critical context for a write operation: validation behavior, error conditions, idempotency, or consequences of registering duplicate tool names. This incompleteness could lead to misuse or uncertainty for an agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so all parameters are documented in the schema. The description adds no extra semantic detail, but the baseline of 3 is appropriate since the schema handles parameter explanation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses specific verbs ('添加', '注册') and a clear resource ('工具注册表'), making the tool's function immediately obvious. It distinguishes itself from sibling tools like unregister_tool and search_tools by focusing on the act of registration.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives, nor are any prerequisites or exclusions mentioned. The description simply states the action without context for decision-making.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

search_hot_toolsA

快速搜索热工具（性能优化）

仅搜索热工具和温工具，跳过冷工具以提升搜索性能。热工具是高频使用的工具，温工具是中等频率使用的工具。

ParametersJSON Schema

Name	Required	Description
`limit`	No	返回结果数量，默认 5
`query`	Yes	搜索查询字符串
`search_method`	No	搜索方法 (regex/bm25)，默认使用环境变量配置

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

A4.2/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the burden of behavioral disclosure. It clearly states the key behavior of skipping cold tools and defines hot/warm tools. It does not mention side effects, but for a search tool, read-only behavior is implied. The added context about frequency categories goes beyond the name.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a brief, well-structured paragraph. It first states the purpose, then explains the scope and definitions, with no redundant sentences or filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description is complete for a search tool with an output schema: it clearly defines the filtering scope and motivation. It could be slightly more explicit about the relationship to the sibling 'search_tools', but the 'only' phrasing already communicates that it is a subset.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% because all three parameters have descriptions. The tool description does not add any additional parameter-level meaning, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states 'quick search hot tools' and explicitly defines that it only searches hot and warm tools while skipping cold tools. This clearly distinguishes it from the sibling 'search_tools' tool by specifying the scope and performance motivation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explains that this tool is for performance optimization by skipping cold tools, which implies it should be used when you only need hot/warm tools. However, it does not explicitly name the alternative 'search_tools' for full searches, so there is clear context but no explicit exclusion.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

search_toolsB

搜索可用的 MCP 工具

根据查询字符串在已注册的工具中搜索匹配项。

ParametersJSON Schema

Name	Required	Description
`limit`	No	返回结果数量，默认 5
`query`	Yes	搜索查询字符串
`search_method`	No	搜索方法 (regex/bm25/embedding)，默认使用环境变量配置

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

B3.1/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries full responsibility for behavioral disclosure. It does not state whether the operation is read-only, describe the return structure, or explain how search_method affects behavior—significant gaps for a search tool with no annotation coverage.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two concise sentences, front-loaded with the action and a brief elaboration. Every word earns its place, with no redundancy or filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is a straightforward search operation with an output schema and fully described parameters, but the description lacks behavioral context such as safety profile, return details, and search_method implications. It is minimally complete but leaves gaps that annotations would normally fill.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

All three parameters have descriptive schema entries covering 100% of the schema, so the baseline is 3. The description only mentions the query string and adds no additional meaning beyond what the schema already provides for limit or search_method.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool searches registered MCP tools using a query string, giving a specific verb (search) and resource (registered MCP tools). It distinguishes from siblings like search_hot_tools by emphasizing 'registered tools' but does not explicitly name alternatives or exclusion criteria.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus siblings such as search_hot_tools or list_tools_by_category. It only states what the tool does without context or exclusions, leaving the agent to infer appropriate use.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

unregister_toolA

注销工具

从工具注册表中移除指定的工具。

ParametersJSON Schema

Name	Required	Description	Default
`tool_name`	Yes	工具名称

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

A3.7/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. The description clearly states a destructive removal action, but it does not disclose side effects, reversibility, or any prerequisites. For a simple removal this is adequate but lacks depth.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is very short and gets to the point. The second sentence provides the actual meaning. The first line '注销工具' is slightly redundant with the tool name but acts as a heading. No unnecessary words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (1 parameter, no nested objects) and the presence of an output schema, the description sufficiently covers the core action. It does not address error cases or expected output, but for a basic unregister operation this is acceptable.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% (only param tool_name is described). The description adds little beyond the schema, just referring to '指定的工具' (the specified tool). It does not elaborate on what valid tool_names are or where to find them.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description explicitly states the tool removes a specified tool from the tool registry. The verb '移除' (remove) and resource '工具注册表' (tool registry) are clear and distinguish it from siblings like register_tool.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied: use this when you need to remove a tool from the registry. However, there is no explicit mention of when not to use it or alternatives (e.g., if you only need to view definitions, use get_tool_definition). No exclusions are stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

6 tool updatesv0.2.1Aug 9, 2026
- First observedget_tool_definition
- First observedlist_tools_by_category
- First observedregister_tool
- First observedsearch_hot_tools
- First observedsearch_tools
- First observedunregister_tool

Install Server

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A3.5/5.0

Disambiguation3/5

Most tools have distinct purposes, but search_tools and search_hot_tools overlap significantly. An agent could easily choose the wrong one, especially since search_hot_tools only searches a subset of tools.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern (get_, search_, list_, register_, unregister_). The two search tools are clearly named with a descriptive modifier, maintaining predictable structure.

Tool Count5/5

With 6 tools, the server is well-scoped for a tool registry. Each tool covers a core registry operation without unnecessary bloat or missing essentials.

Completeness3/5

The registry covers basic CRUD (register, get, unregister) and search/list capabilities, but there is no update tool and no way to list all tools without filtering by category. This leaves notable gaps for managing and exploring the full registry.

Maintenance

ActivityInactive

ResponsivenessNo issues

Resources

GitHub Repository

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

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

Related MCP Connectors

Anagent A
io.github.jaytahir
A registry of AI agent tools — MCP servers, APIs, CLIs, SDKs — kept current by automated ingestion.
Agent Orchestration Developer Tools
21
Remote MCP A
com.remote-mcp.mcp
The Remote MCP server acts as a standardized bridge between LLM applications (like Claude, ChatGPT, and Cursor) and external services, enabling AI agents to access external tools and resources. Its primary capability is providing a centralized search tool to discover other MCP servers and their respective tools. Unlike local implementations, it runs remotely with OAuth authentication and permission controls for security.
Developer Tools Search Agent Orchestration
13
registry A
com.policylayer
The MCP server that vets MCP servers: identity, risk grade and per-tool risk before you install.
Security Developer Tools
521
strata
ai.klavis
MCP server for progressive tool usage at any scale (see https://klavis.ai)
Agent Orchestration Autonomous Agents Developer Tools
25,748

Related MCP Servers

Awesome MCP FastAPI
RAG Systems Agent Orchestration Developer Tools
MR-GREEN1337
F
license
Not graded
quality
F
maintenance
A production-ready MCP server built with FastAPI, providing an enhanced tool registry for creating, managing, and documenting AI tools for Large Language Models (LLMs).
Updated 2 years ago (2025-02-22 13:17 UTC)
34
-
UTCP-MCP Bridgeofficial
Developer Tools App Automation
universal-tool-calling-protocol
A
license
A
quality
F
maintenance
A universal MCP server that exposes all UTCP-registered tools to MCP clients while providing a web interface for tool management.
Updated 4 months ago (2026-05-03 19:52 UTC)
7
29
203
MIT
mcp-toolselect
Developer Tools Autonomous Agents RAG Systems
Aegis-AI-Cooperative
A
license
Not graded
quality
F
maintenance
An MCP server that recommends specific tools for tasks by learning from usage patterns and historical success rates. It enables users to register tool capabilities and provides ranked recommendations that adapt based on feedback and execution data.
Updated 7 months ago (2026-02-05 03:46 UTC)
MIT
mcp-server-find
Developer Tools Search Agent Orchestration
daedalus
A
license
Not graded
quality
C
maintenance
A discovery tool for AI agents to search, evaluate, and install MCP servers from multiple registries.
Updated 4 months ago (2026-04-26 05:24 UTC)
1
MIT

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

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/GeerMrc/RegistryTools'

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

RegistryTools

简介

核心价值

快速开始

安装

传输协议

STDIO 模式 (默认)

Streamable HTTP 模式 (远程部署)

存储后端选择

fastmcp.json 配置

Claude Code (VSCode) 配置

方式 1：CLI 命令（推荐）

方式 2：配置文件

方式 3：JSON 配置命令 (add-json)

快速配置（单行）

STDIO 模式完整配置

HTTP 模式完整配置

参数分类说明

配置范围

配置选项

完整配置参数表格

完整配置示例

Embedding 搜索配置（可选）

高级功能

API Key 认证

使用示例

功能特性

搜索算法

MCP 工具接口

MCP 资源接口

架构设计

开发

环境设置

运行测试

代码格式化

贡献指南

文档

性能指标

路线图

v0.2.1 (当前 - 2026-01-11)

v0.3.0 (计划中)

相关文档

用户文档

技术文档

开发文档

项目管理

许可证

致谢

Available Tools

Output Schema

Output Schema

Output Schema

Output Schema

Output Schema

Output Schema

Tool Schema Changelog

Maintenance

Resources

Looking for Admin?

Related MCP Connectors

Related MCP Servers

UTCP-MCP Bridgeofficial

Latest Blog Posts

MCP directory API