grepai-mcp-cursor

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

GrepAI MCP Integration with Cursor

GrepAI与Cursor的MCP集成

This skill covers integrating GrepAI with Cursor IDE using the Model Context Protocol (MCP).

本技能介绍如何通过模型上下文协议（MCP）将GrepAI与Cursor IDE集成。

When to Use This Skill

何时使用此技能

Setting up GrepAI in Cursor
Enabling semantic search for Cursor AI
Configuring MCP for Cursor
Troubleshooting Cursor integration

在Cursor中设置GrepAI
为Cursor AI启用语义搜索
为Cursor配置MCP
排查Cursor集成问题

What is Cursor?

什么是Cursor？

Cursor is an AI-powered IDE that supports MCP for external tools. GrepAI integration gives Cursor's AI:

Semantic code search beyond simple text matching
Call graph analysis for understanding dependencies
Index-based code navigation

Cursor是一款支持通过MCP接入外部工具的AI驱动IDE。集成GrepAI后，Cursor的AI将具备以下能力：

超越简单文本匹配的语义代码搜索
用于理解依赖关系的调用图分析
基于索引的代码导航

Prerequisites

前置条件

GrepAI installed
Ollama running (or other embedding provider)
Project indexed (
```
grepai watch
```
)
Cursor IDE installed

已安装GrepAI
Ollama正在运行（或使用其他嵌入模型提供商）
项目已建立索引（执行
```
grepai watch
```
）
已安装Cursor IDE

Configuration

配置步骤

Step 1: Create MCP Config File

步骤1：创建MCP配置文件

Create

.cursor/mcp.json

in your project root:

json

{
  "mcpServers": {
    "grepai": {
      "command": "grepai",
      "args": ["mcp-serve"]
    }
  }
}

在项目根目录创建

.cursor/mcp.json

文件：

json

{
  "mcpServers": {
    "grepai": {
      "command": "grepai",
      "args": ["mcp-serve"]
    }
  }
}

Step 2: Restart Cursor

步骤2：重启Cursor

Close and reopen Cursor for the config to take effect.

关闭并重新打开Cursor，使配置生效。

Step 3: Verify

步骤3：验证配置

Ask Cursor's AI:

"Search the codebase for authentication"

Cursor should use the

grepai_search

tool.

向Cursor的AI提问：

"Search the codebase for authentication"

Cursor应调用

grepai_search

工具。

Global Configuration

全局配置

For GrepAI in all Cursor projects, use global config:

若要在所有Cursor项目中使用GrepAI，请使用全局配置：

Location

配置文件位置

macOS:
```
~/.cursor/mcp.json
```
Linux:
```
~/.cursor/mcp.json
```
Windows:
```
%APPDATA%\Cursor\mcp.json
```

macOS:
```
~/.cursor/mcp.json
```
Linux:
```
~/.cursor/mcp.json
```
Windows:
```
%APPDATA%\Cursor\mcp.json
```

Content

配置内容

json

{
  "mcpServers": {
    "grepai": {
      "command": "grepai",
      "args": ["mcp-serve"]
    }
  }
}

json

{
  "mcpServers": {
    "grepai": {
      "command": "grepai",
      "args": ["mcp-serve"]
    }
  }
}

Per-Project Configuration

项目专属配置

For project-specific settings:

json

{
  "mcpServers": {
    "grepai": {
      "command": "grepai",
      "args": ["mcp-serve"],
      "cwd": "/absolute/path/to/project"
    }
  }
}

针对特定项目的配置：

json

{
  "mcpServers": {
    "grepai": {
      "command": "grepai",
      "args": ["mcp-serve"],
      "cwd": "/absolute/path/to/project"
    }
  }
}

Available Tools

可用工具

Once configured, Cursor has access to:

Tool	Description
`grepai_search`	Semantic code search
`grepai_trace_callers`	Find function callers
`grepai_trace_callees`	Find function callees
`grepai_trace_graph`	Build call graphs
`grepai_index_status`	Check index health

配置完成后，Cursor可使用以下工具：

工具	描述
`grepai_search`	语义代码搜索
`grepai_trace_callers`	查找函数调用方
`grepai_trace_callees`	查找函数被调用方
`grepai_trace_graph`	生成调用图
`grepai_index_status`	检查索引健康状态

Usage Examples

使用示例

Finding Code

查找代码

Ask Cursor:

"Find code that handles user login"

Cursor uses

grepai_search

to find semantically related code.

向Cursor提问：

"查找处理用户登录的代码"

Cursor会使用

grepai_search

工具查找语义相关的代码。

Understanding Dependencies

理解依赖关系

Ask Cursor:

"What functions call validateToken?"

Cursor uses

grepai_trace_callers

to show all callers.

向Cursor提问：

"哪些函数调用了validateToken？"

Cursor会使用

grepai_trace_callers

工具显示所有调用方。

Code Navigation

代码导航

Ask Cursor:

"Show me the call graph for processPayment"

Cursor uses

grepai_trace_graph

to display dependencies.

向Cursor提问：

"展示processPayment的调用图"

Cursor会使用

grepai_trace_graph

工具展示依赖关系。

Cursor Settings Integration

Cursor设置集成

Enable MCP in Settings

在设置中启用MCP

Open Cursor Settings (
```
Cmd+,
```
/
```
Ctrl+,
```
)
Search for "MCP"
Ensure MCP is enabled

打开Cursor设置（
```
Cmd+,
```
/
```
Ctrl+,
```
）
搜索"MCP"
确保MCP已启用

Verify MCP Status

验证MCP状态

Open Command Palette (
```
Cmd+Shift+P
```
/
```
Ctrl+Shift+P
```
)
Search "MCP"
Check connected servers

打开命令面板（
```
Cmd+Shift+P
```
/
```
Ctrl+Shift+P
```
）
搜索"MCP"
查看已连接的服务器

Windsurf Configuration

Windsurf配置

Windsurf uses the same MCP format as Cursor:

Windsurf使用与Cursor相同的MCP格式：

Location

配置文件位置

Create

.windsurf/mcp.json

json

{
  "mcpServers": {
    "grepai": {
      "command": "grepai",
      "args": ["mcp-serve"]
    }
  }
}

创建

.windsurf/mcp.json

文件：

json

{
  "mcpServers": {
    "grepai": {
      "command": "grepai",
      "args": ["mcp-serve"]
    }
  }
}

Multiple Projects Setup

多项目设置

Option 1: Separate Configs

选项1：独立配置

Each project has its own

.cursor/mcp.json

with appropriate

cwd

每个项目拥有自己的

.cursor/mcp.json

文件，并设置合适的

cwd

。

Option 2: Workspaces

选项2：工作区

bash

undefined

bash

undefined

Create workspace

创建工作区

grepai workspace create dev grepai workspace add dev /path/to/project1 grepai workspace add dev /path/to/project2


```json
{
  "mcpServers": {
    "grepai": {
      "command": "grepai",
      "args": ["mcp-serve", "--workspace", "dev"]
    }
  }
}

grepai workspace create dev grepai workspace add dev /path/to/project1 grepai workspace add dev /path/to/project2


```json
{
  "mcpServers": {
    "grepai": {
      "command": "grepai",
      "args": ["mcp-serve", "--workspace", "dev"]
    }
  }
}

Environment Variables

环境变量

If GrepAI uses environment variables (like API keys):

json

{
  "mcpServers": {
    "grepai": {
      "command": "grepai",
      "args": ["mcp-serve"],
      "env": {
        "OPENAI_API_KEY": "sk-..."
      }
    }
  }
}

Better: Set environment variables in your shell profile instead.

如果GrepAI需要使用环境变量（如API密钥）：

json

{
  "mcpServers": {
    "grepai": {
      "command": "grepai",
      "args": ["mcp-serve"],
      "env": {
        "OPENAI_API_KEY": "sk-..."
      }
    }
  }
}

更优方案： 在Shell配置文件中设置环境变量。

Troubleshooting

故障排查

MCP Not Recognized

MCP未被识别

❌ Problem: Cursor doesn't see GrepAI tools

✅ Solutions:

Check file location:
```
.cursor/mcp.json
```
in project root
Verify JSON syntax (no trailing commas)
Restart Cursor completely
Check
```
grepai
```
is in PATH

❌ 问题： Cursor无法识别GrepAI工具

✅ 解决方案：

检查文件位置：项目根目录下的
```
.cursor/mcp.json
```
验证JSON语法（无尾随逗号）
完全重启Cursor
确认
```
grepai
```
已添加到系统PATH中

Search Returns Nothing

搜索无结果

❌ Problem: Empty search results

✅ Solutions:

Ensure index exists:
```
grepai status
```
Run
```
grepai watch
```
first
Verify working directory

❌ 问题： 搜索结果为空

✅ 解决方案：

确认索引已存在：执行
```
grepai status
```
先执行
```
grepai watch
```
验证工作目录是否正确

Connection Errors

连接错误

❌ Problem: MCP connection failed

✅ Solutions:

Test manually:
```
grepai mcp-serve
```
Check Ollama:
```
curl http://localhost:11434/api/tags
```
Look at Cursor's developer console for errors

❌ 问题： MCP连接失败

✅ 解决方案：

手动测试：执行
```
grepai mcp-serve
```
检查Ollama状态：执行
```
curl http://localhost:11434/api/tags
```
在Cursor开发者控制台查看错误信息

Wrong Results

结果错误

❌ Problem: Results from wrong project

✅ Solutions:

Set explicit
```
cwd
```
in config
Check you opened the right folder in Cursor
Use
```
grepai_index_status
```
to verify

❌ 问题： 返回错误项目的结果

✅ 解决方案：

在配置中设置明确的
```
cwd
```
确认在Cursor中打开了正确的文件夹
使用
```
grepai_index_status
```
验证索引

Performance Tips

性能优化建议

Background daemon: Keep
```
grepai watch --background
```
running
Use compact mode: MCP tools use compact by default
Limit results: AI will request appropriate limits
Index regularly: Especially after git pull

后台守护进程： 保持
```
grepai watch --background
```
运行
使用紧凑模式： MCP工具默认使用紧凑模式
限制结果数量： AI会自动请求合适的结果数量
定期更新索引： 尤其是在执行git pull之后

Comparison: Cursor vs Claude Code

对比：Cursor vs Claude Code

Feature	Cursor	Claude Code
Config location	`.cursor/mcp.json`	`~/.claude/mcp.json`
Setup command	Manual JSON	`claude mcp add`
Project scope	Per-project or global	Global
IDE integration	Native	Terminal

特性	Cursor	Claude Code
配置文件位置	`.cursor/mcp.json`	`~/.claude/mcp.json`
设置命令	手动编写JSON	`claude mcp add`
项目范围	项目专属或全局	全局
IDE集成	原生集成	终端集成

Best Practices

最佳实践

Version control: Add
```
.cursor/mcp.json
```
to git (without secrets)
Team setup: Document MCP config in README
Keep index fresh: Run watch daemon
Test locally: Verify
```
grepai mcp-serve
```
works first
Use workspaces: For multi-project setups

版本控制： 将
```
.cursor/mcp.json
```
添加到git中（不含敏感信息）
团队设置： 在README中记录MCP配置方法
保持索引更新： 运行watch守护进程
本地测试： 先验证
```
grepai mcp-serve
```
可正常运行
使用工作区： 适用于多项目场景

Removing Integration

移除集成

Delete

.cursor/mcp.json

and restart Cursor.

Or remove just GrepAI:

json

{
  "mcpServers": {
    // Remove grepai entry
  }
}

删除

.cursor/mcp.json

并重启Cursor。

或仅移除GrepAI：

json

{
  "mcpServers": {
    // 移除grepai条目
  }
}

Output Format

输出格式

Successful Cursor setup:

✅ GrepAI MCP Integration for Cursor

   Config: .cursor/mcp.json
   Server: grepai mcp-serve
   Status: Ready

   Available tools:
   - grepai_search
   - grepai_trace_callers
   - grepai_trace_callees
   - grepai_trace_graph
   - grepai_index_status

   Cursor AI can now search your code semantically!

   Test: Ask Cursor "search for authentication code"

Cursor设置成功后的输出：

✅ GrepAI MCP Integration for Cursor

   Config: .cursor/mcp.json
   Server: grepai mcp-serve
   Status: Ready

   Available tools:
   - grepai_search
   - grepai_trace_callers
   - grepai_trace_callees
   - grepai_trace_graph
   - grepai_index_status

   Cursor AI can now search your code semantically!

   Test: Ask Cursor "search for authentication code"