GrepAI MCP 工具使用指南：语义代码搜索与调用图追踪工具详解

grepai-mcp-tools by yoanbernabeu/grepai-skills

263 周安装量

15 GitHub Stars

GitHub

安装命令

npx skills add https://github.com/yoanbernabeu/grepai-skills --skill grepai-mcp-tools

AI/机器学习开发代码质量

🇨🇳中文介绍

GrepAI MCP 工具参考

此技能提供了通过 GrepAI 的 MCP 服务器可用的所有工具的完整参考。

何时使用此技能

了解可用的 MCP 工具
学习工具参数和选项
将 GrepAI 与 AI 助手集成
调试 MCP 工具使用

启动 MCP 服务器

grepai mcp-serve

服务器通过模型上下文协议暴露工具。

可用工具

1. grepai_search

使用嵌入进行语义代码搜索。

参数

参数	类型	必需	默认值	描述
`query`	string	是	-	描述要查找内容的搜索查询
`limit`

广告位招租

在这里展示您的产品或服务

触达数万 AI 开发者，精准高效

联系我们

2. grepai_trace_callers

查找调用指定符号的所有函数。

参数	类型	必需	默认值	描述
`symbol`	string	是	-	要追踪的函数/方法名称
`compact`	boolean	否	false	返回紧凑输出（无上下文）
`format`	string	否	"json"	输出格式："json" 或 "toon" (v0.26.0+)

{
  "tool": "grepai_trace_callers",
  "parameters": {
    "symbol": "Login",
    "compact": true
  }
}

响应（紧凑模式）

{
  "q": "Login",
  "m": "callers",
  "c": 3,
  "r": [
    {"f": "handlers/auth.go", "l": 42, "fn": "HandleAuth"},
    {"f": "handlers/auth_test.go", "l": 15, "fn": "TestLoginSuccess"},
    {"f": "cmd/main.go", "l": 88, "fn": "RunCLI"}
  ]
}

响应（完整模式）

{
  "query": "Login",
  "mode": "callers",
  "count": 3,
  "results": [
    {
      "file": "handlers/auth.go",
      "line": 42,
      "caller": "HandleAuth",
      "context": "user.Login(ctx, credentials)"
    }
  ]
}

3. grepai_trace_callees

查找指定符号调用的所有函数。

参数	类型	必需	默认值	描述
`symbol`	string	是	-	要追踪的函数/方法名称
`compact`	boolean	否	false	返回紧凑输出（无上下文）
`format`	string	否	"json"	输出格式："json" 或 "toon" (v0.26.0+)

{
  "tool": "grepai_trace_callees",
  "parameters": {
    "symbol": "ProcessOrder",
    "compact": true
  }
}

响应（紧凑模式）

{
  "q": "ProcessOrder",
  "m": "callees",
  "c": 4,
  "r": [
    {"f": "services/order.go", "l": 45, "fn": "validateOrder"},
    {"f": "services/order.go", "l": 48, "fn": "calculateTotal"},
    {"f": "services/order.go", "l": 51, "fn": "applyDiscount"},
    {"f": "services/order.go", "l": 55, "fn": "sendConfirmation"}
  ]
}

4. grepai_trace_graph

从符号开始构建完整的调用图。

参数	类型	必需	默认值	描述
`symbol`	string	是	-	图的根函数
`depth`	number	否	2	最大递归深度
`compact`	boolean	否	false	返回紧凑 JSON 格式
`format`	string	否	"json"	输出格式："json" 或 "toon" (v0.26.0+)

{
  "tool": "grepai_trace_graph",
  "parameters": {
    "symbol": "main",
    "depth": 3,
    "compact": true
  }
}

响应（紧凑模式）

{
  "q": "main",
  "d": 3,
  "r": {
    "n": "main",
    "c": [
      {
        "n": "initialize",
        "c": [
          {"n": "loadConfig"},
          {"n": "connectDB"}
        ]
      },
      {
        "n": "startServer",
        "c": [
          {"n": "registerRoutes"}
        ]
      }
    ]
  },
  "s": {"nodes": 6, "depth": 3}
}

响应（完整模式）

{
  "query": "main",
  "mode": "graph",
  "depth": 3,
  "root": {
    "name": "main",
    "file": "cmd/main.go",
    "line": 10,
    "children": [
      {
        "name": "initialize",
        "file": "cmd/main.go",
        "line": 15,
        "children": [...]
      }
    ]
  },
  "stats": {
    "nodes": 6,
    "max_depth": 3
  }
}

5. grepai_index_status

检查代码索引的健康状态和状态。

参数	类型	必需	默认值	描述
`verbose`	boolean	否	false	包含详细信息
`format`	string	否	"json"	输出格式："json" 或 "toon" (v0.26.0+)

{
  "tool": "grepai_index_status",
  "parameters": {
    "verbose": true
  }
}

{
  "status": "healthy",
  "project": "/path/to/project",
  "embedder": {
    "provider": "ollama",
    "model": "nomic-embed-text",
    "status": "connected"
  },
  "store": {
    "backend": "gob",
    "location": ".grepai/index.gob"
  },
  "index": {
    "files": 245,
    "chunks": 1234,
    "last_updated": "2025-01-28T10:30:00Z"
  },
  "daemon": {
    "running": true,
    "pid": 12345
  }
}

当 compact: true 时，响应使用缩写键：

完整键	紧凑键	描述
`query`	`q`	搜索查询或符号
`results`	`r`	结果数组
`total`	`t`	总数
`count`	`c`	计数
`score`	`s`	相似度分数
`file`	`f`	文件路径
`line`	`l`	行号
`mode`	`m`	追踪模式
`depth`	`d`	图深度
`name`	`n`	节点名称
`children`	`c`	子节点
`stats`	`s`	统计信息
`function`	`fn`	函数名称

紧凑模式显著减少令牌使用：

响应类型	完整模式	紧凑模式	节省
搜索（5个结果）	~800	~150	81%
追踪调用者（10个）	~600	~120	80%
追踪图（深度3）	~1200	~250	79%

{
  "error": "Index not found. Run 'grepai watch' first.",
  "code": "INDEX_NOT_FOUND"
}

嵌入器连接失败

{
  "error": "Cannot connect to embedding provider. Is Ollama running?",
  "code": "EMBEDDER_UNAVAILABLE"
}

{
  "error": "Symbol 'FunctionName' not found in index.",
  "code": "SYMBOL_NOT_FOUND"
}

{
  "error": "Parameter 'query' is required.",
  "code": "INVALID_PARAMETERS"
}

AI 集成最佳实践

使用紧凑模式： 减少约 80% 的令牌使用
限制结果： 仅请求所需内容
先检查状态： 在搜索前使用 grepai_index_status
处理错误： 检查错误响应
组合工具： 搜索 + 追踪以获得完整理解

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "grepai_search",
    "arguments": {
      "query": "authentication",
      "limit": 5,
      "compact": true
    }
  }
}

{
  "jsonrpc": "2.0",
  "id": 1,
  "result": {
    "content": [
      {
        "type": "text",
        "text": "{\"q\":\"authentication\",\"r\":[...],\"t\":5}"
      }
    ]
  }
}

MCP 工具参考摘要：

📚 GrepAI MCP 工具参考

可用工具：

1. grepai_search
   - 语义代码搜索
   - 参数：query*, limit, compact

2. grepai_trace_callers
   - 查找函数调用者
   - 参数：symbol*, compact

3. grepai_trace_callees
   - 查找函数被调用者
   - 参数：symbol*, compact

4. grepai_trace_graph
   - 构建调用图
   - 参数：symbol*, depth, compact

5. grepai_index_status
   - 检查索引健康状态
   - 参数：verbose

* = 必需参数

紧凑模式：约 80% 令牌减少

🇺🇸English

GrepAI MCP Tools Reference

This skill provides a complete reference for all tools available through GrepAI's MCP server.

When to Use This Skill

Understanding available MCP tools
Learning tool parameters and options
Integrating GrepAI with AI assistants
Debugging MCP tool usage

Starting the MCP Server

grepai mcp-serve

The server exposes tools via the Model Context Protocol.

Available Tools

1. grepai_search

Semantic code search using embeddings.

Parameters

Parameter	Type	Required	Default	Description
`query`	string	Yes	-	Search query describing what to find
`limit`	number	No	10	Maximum results to return
`compact`	boolean	No	false	Return compact output (no content)
`format`	string	No	"json"	Output format: "json" or "toon" (v0.26.0+)

Example Request

{
  "tool": "grepai_search",
  "parameters": {
    "query": "user authentication middleware",
    "limit": 5,
    "compact": true,
    "format": "toon"
  }
}

Response (Compact)

{
  "q": "user authentication middleware",
  "r": [
    {"s": 0.92, "f": "src/auth/middleware.go", "l": "15-45"},
    {"s": 0.85, "f": "src/auth/jwt.go", "l": "23-55"},
    {"s": 0.78, "f": "src/handlers/auth.go", "l": "10-40"}
  ],
  "t": 3
}

Response (Full)

{
  "query": "user authentication middleware",
  "results": [
    {
      "score": 0.92,
      "file": "src/auth/middleware.go",
      "start_line": 15,
      "end_line": 45,
      "content": "func AuthMiddleware() gin.HandlerFunc {\n    ..."
    }
  ],
  "total": 3
}

2. grepai_trace_callers

Find all functions that call a specified symbol.

Parameters

Parameter	Type	Required	Default	Description
`symbol`	string	Yes	-	Function/method name to trace
`compact`	boolean	No	false	Return compact output (no context)
`format`	string	No	"json"	Output format: "json" or "toon" (v0.26.0+)

Example Request

{
  "tool": "grepai_trace_callers",
  "parameters": {
    "symbol": "Login",
    "compact": true
  }
}

Response (Compact)

{
  "q": "Login",
  "m": "callers",
  "c": 3,
  "r": [
    {"f": "handlers/auth.go", "l": 42, "fn": "HandleAuth"},
    {"f": "handlers/auth_test.go", "l": 15, "fn": "TestLoginSuccess"},
    {"f": "cmd/main.go", "l": 88, "fn": "RunCLI"}
  ]
}

Response (Full)

{
  "query": "Login",
  "mode": "callers",
  "count": 3,
  "results": [
    {
      "file": "handlers/auth.go",
      "line": 42,
      "caller": "HandleAuth",
      "context": "user.Login(ctx, credentials)"
    }
  ]
}

3. grepai_trace_callees

Find all functions called by a specified symbol.

Parameters

Parameter	Type	Required	Default	Description
`symbol`	string	Yes	-	Function/method name to trace
`compact`	boolean	No	false	Return compact output (no context)
`format`	string	No	"json"	Output format: "json" or "toon" (v0.26.0+)

Example Request

{
  "tool": "grepai_trace_callees",
  "parameters": {
    "symbol": "ProcessOrder",
    "compact": true
  }
}

Response (Compact)

{
  "q": "ProcessOrder",
  "m": "callees",
  "c": 4,
  "r": [
    {"f": "services/order.go", "l": 45, "fn": "validateOrder"},
    {"f": "services/order.go", "l": 48, "fn": "calculateTotal"},
    {"f": "services/order.go", "l": 51, "fn": "applyDiscount"},
    {"f": "services/order.go", "l": 55, "fn": "sendConfirmation"}
  ]
}

4. grepai_trace_graph

Build a complete call graph starting from a symbol.

Parameters

Parameter	Type	Required	Default	Description
`symbol`	string	Yes	-	Root function for the graph
`depth`	number	No	2	Maximum recursion depth
`compact`	boolean	No	false	Return compact JSON format
`format`

Example Request

{
  "tool": "grepai_trace_graph",
  "parameters": {
    "symbol": "main",
    "depth": 3,
    "compact": true
  }
}

Response (Compact)

{
  "q": "main",
  "d": 3,
  "r": {
    "n": "main",
    "c": [
      {
        "n": "initialize",
        "c": [
          {"n": "loadConfig"},
          {"n": "connectDB"}
        ]
      },
      {
        "n": "startServer",
        "c": [
          {"n": "registerRoutes"}
        ]
      }
    ]
  },
  "s": {"nodes": 6, "depth": 3}
}

Response (Full)

{
  "query": "main",
  "mode": "graph",
  "depth": 3,
  "root": {
    "name": "main",
    "file": "cmd/main.go",
    "line": 10,
    "children": [
      {
        "name": "initialize",
        "file": "cmd/main.go",
        "line": 15,
        "children": [...]
      }
    ]
  },
  "stats": {
    "nodes": 6,
    "max_depth": 3
  }
}

5. grepai_index_status

Check the health and status of the code index.

Parameters

Parameter	Type	Required	Default	Description
`verbose`	boolean	No	false	Include detailed information
`format`	string	No	"json"	Output format: "json" or "toon" (v0.26.0+)

Example Request

{
  "tool": "grepai_index_status",
  "parameters": {
    "verbose": true
  }
}

Response

{
  "status": "healthy",
  "project": "/path/to/project",
  "embedder": {
    "provider": "ollama",
    "model": "nomic-embed-text",
    "status": "connected"
  },
  "store": {
    "backend": "gob",
    "location": ".grepai/index.gob"
  },
  "index": {
    "files": 245,
    "chunks": 1234,
    "last_updated": "2025-01-28T10:30:00Z"
  },
  "daemon": {
    "running": true,
    "pid": 12345
  }
}

Compact Format Reference

When compact: true, responses use abbreviated keys:

Full Key	Compact Key	Description
`query`	`q`	Search query or symbol
`results`	`r`	Results array
`total`	`t`	Total count
`count`

Token Efficiency

Compact mode reduces tokens significantly:

Response Type	Full	Compact	Savings
Search (5 results)	~800	~150	81%
Trace callers (10)	~600	~120	80%
Trace graph (depth 3)	~1200	~250	79%

Error Responses

Index Not Found

{
  "error": "Index not found. Run 'grepai watch' first.",
  "code": "INDEX_NOT_FOUND"
}

Embedder Connection Failed

{
  "error": "Cannot connect to embedding provider. Is Ollama running?",
  "code": "EMBEDDER_UNAVAILABLE"
}

Symbol Not Found

{
  "error": "Symbol 'FunctionName' not found in index.",
  "code": "SYMBOL_NOT_FOUND"
}

Invalid Parameters

{
  "error": "Parameter 'query' is required.",
  "code": "INVALID_PARAMETERS"
}

Best Practices for AI Integration

Use compact mode: Reduces token usage by ~80%
Limit results: Request only what you need
Check status first: Use grepai_index_status before searches
Handle errors: Check for error responses
Combine tools: Search + trace for full understanding

MCP Protocol Details

Request Format

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "grepai_search",
    "arguments": {
      "query": "authentication",
      "limit": 5,
      "compact": true
    }
  }
}

Response Format

{
  "jsonrpc": "2.0",
  "id": 1,
  "result": {
    "content": [
      {
        "type": "text",
        "text": "{\"q\":\"authentication\",\"r\":[...],\"t\":5}"
      }
    ]
  }
}

Output Format

MCP tools reference summary:

📚 GrepAI MCP Tools Reference

Tools available:

1. grepai_search
   - Semantic code search
   - Params: query*, limit, compact

2. grepai_trace_callers
   - Find function callers
   - Params: symbol*, compact

3. grepai_trace_callees
   - Find function callees
   - Params: symbol*, compact

4. grepai_trace_graph
   - Build call graph
   - Params: symbol*, depth, compact

5. grepai_index_status
   - Check index health
   - Params: verbose

* = required parameter

Compact mode: ~80% token reduction

Weekly Installs

263

Repository

yoanbernabeu/gr…i-skills

GitHub Stars

First Seen

Jan 28, 2026

Security Audits

Gen Agent Trust HubPass SocketPass SnykPass

Installed on

opencode217

codex211

gemini-cli194

github-copilot194

kimi-cli180

amp178

React 组合模式指南：Vercel 组件架构最佳实践，提升代码可维护性

106,200 周安装

GrepAI MCP 工具使用指南：语义代码搜索与调用图追踪工具详解

🇨🇳中文介绍

GrepAI MCP 工具参考

何时使用此技能

启动 MCP 服务器

可用工具

1. grepai_search

参数

相关 Skills

示例请求

响应（紧凑模式）

响应（完整模式）

2. grepai_trace_callers

参数

示例请求

响应（紧凑模式）

响应（完整模式）

3. grepai_trace_callees

参数

示例请求

响应（紧凑模式）

4. grepai_trace_graph

参数

示例请求

响应（紧凑模式）

响应（完整模式）

5. grepai_index_status

参数

示例请求

响应

紧凑格式参考

令牌效率

错误响应

索引未找到

嵌入器连接失败

符号未找到

无效参数

AI 集成最佳实践

MCP 协议详情

请求格式

响应格式

输出格式

🇺🇸English

GrepAI MCP Tools Reference

When to Use This Skill

Starting the MCP Server

Available Tools

1. grepai_search

Parameters

Example Request

Response (Compact)

Response (Full)

2. grepai_trace_callers

Parameters

Example Request

Response (Compact)

Response (Full)

3. grepai_trace_callees

Parameters

Example Request

Response (Compact)

4. grepai_trace_graph

Parameters

Example Request

Response (Compact)

Response (Full)

5. grepai_index_status

Parameters

Example Request

Response

Compact Format Reference

Token Efficiency

Error Responses

Index Not Found

Embedder Connection Failed

Symbol Not Found

Invalid Parameters

Best Practices for AI Integration

MCP Protocol Details

Request Format