Relace MCP Server
Enables AI-powered instant code merging at 10,000+ tokens/sec and agentic codebase search with natural language queries through the Relace API.
README
<p align="right"> <strong>English</strong> | <a href="README.zh-CN.md">简体中文</a> </p>
Unofficial Relace MCP Server
Unofficial — Personal project, not affiliated with Relace.
Built with AI — Developed entirely with AI assistance (Antigravity, Codex, Cursor, Github Copilot, Windsurf).
MCP server providing AI-powered code editing and intelligent codebase exploration tools.
| Without | With fast_search + fast_apply |
|---|---|
| Manual grep, misses related files | Ask naturally, get precise locations |
| Edits break imports elsewhere | Traces imports and call chains |
| Full rewrites burn tokens | Describe changes, no line numbers |
| Line number errors corrupt code | 10,000+ tokens/sec merging |
Features
- Fast Apply — Apply code edits at 10,000+ tokens/sec via Relace API
- Fast Search — Agentic codebase exploration with natural language queries
- Cloud Sync — Upload local codebase to Relace Cloud for semantic search
- Cloud Search — Semantic code search over cloud-synced repositories
- Dashboard — Real-time terminal UI for monitoring operations
Quick Start
Prerequisites: uv, git, ripgrep (recommended)
Get your API key from Relace Dashboard, then add to your MCP client:
<details> <summary><strong>Cursor</strong></summary>
~/.cursor/mcp.json
{
"mcpServers": {
"relace": {
"command": "uv",
"args": ["tool", "run", "relace-mcp"],
"env": {
"RELACE_API_KEY": "rlc-your-api-key",
"MCP_BASE_DIR": "/absolute/path/to/your/project"
}
}
}
}
</details>
<details> <summary><strong>Claude Code</strong></summary>
claude mcp add relace \
--env RELACE_API_KEY=rlc-your-api-key \
--env MCP_BASE_DIR=/absolute/path/to/your/project \
-- uv tool run relace-mcp
</details>
<details> <summary><strong>Windsurf</strong></summary>
~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"relace": {
"command": "uv",
"args": ["tool", "run", "relace-mcp"],
"env": {
"RELACE_API_KEY": "rlc-your-api-key",
"MCP_BASE_DIR": "/absolute/path/to/your/project"
}
}
}
}
</details>
<details> <summary><strong>VS Code</strong></summary>
.vscode/mcp.json
{
"mcp": {
"servers": {
"relace": {
"type": "stdio",
"command": "uv",
"args": ["tool", "run", "relace-mcp"],
"env": {
"RELACE_API_KEY": "rlc-your-api-key",
"MCP_BASE_DIR": "${workspaceFolder}"
}
}
}
}
}
</details>
<details> <summary><strong>Codex CLI</strong></summary>
~/.codex/config.toml
[mcp_servers.relace]
command = "uv"
args = ["tool", "run", "relace-mcp"]
[mcp_servers.relace.env]
RELACE_API_KEY = "rlc-your-api-key"
MCP_BASE_DIR = "/absolute/path/to/your/project"
</details>
Configuration
| Variable | Required | Description |
|---|---|---|
RELACE_API_KEY |
✅ | API key from Relace Dashboard |
RELACE_CLOUD_TOOLS |
❌ | Set to 1 to enable cloud tools |
MCP_BASE_DIR |
❌ | Project root (auto-detected via MCP Roots → Git → CWD) |
MCP_LOGGING |
❌ | Set to 1 to enable file logging |
MCP_DOTENV_PATH |
❌ | Path to .env file for centralized config |
For .env usage, encoding settings, custom LLM providers, and more, see docs/advanced.md.
Tools
Core tools (fast_apply, fast_search) are always available. Cloud tools require RELACE_CLOUD_TOOLS=1.
For detailed parameters, see docs/tools.md.
Dashboard
Real-time terminal UI for monitoring operations.
pip install relace-mcp[tools]
relogs
For detailed usage, see docs/dashboard.md.
Platform Support
| Platform | Status | Notes |
|---|---|---|
| Linux | ✅ Fully supported | Primary development platform |
| macOS | ✅ Fully supported | All features available |
| Windows | ⚠️ Partial | bash tool unavailable; use WSL for full functionality |
Troubleshooting
| Error | Solution |
|---|---|
RELACE_API_KEY is not set |
Set the key in your environment or MCP config |
NEEDS_MORE_CONTEXT |
Include 1–3 anchor lines before/after target block |
FILE_TOO_LARGE |
File exceeds 1MB; split or increase limit |
ENCODING_ERROR |
Set RELACE_DEFAULT_ENCODING explicitly |
AUTH_ERROR |
Verify API key is valid and not expired |
RATE_LIMIT |
Too many requests; wait and retry |
Development
git clone https://github.com/possible055/relace-mcp.git
cd relace-mcp
uv sync --extra dev
uv run pytest
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。