About
Acemcp is an MCP server that integrates ACE (Augment Context Engine) to provide semantic search capabilities across code repositories. It indexes local project files and enables natural language queries to find relevant code contexts through an external API. Key features of Acemcp: - Automatic incremental indexing that scans only new or modified files before each search, ensuring results stay current without manual intervention - Semantic code search that matches query intent to code meaning rather than simple keyword matching - Multi-encoding support for files using UTF-8, GBK, GB2312, Latin-1, and other formats with automatic detection - .gitignore integration that respects excluded patterns during the indexing process - Web management interface for configuration editing, real-time log monitoring via WebSocket, and built-in tool debugging - Configurable file type filtering with customizable text extensions and exclusion patterns
README
[](https://mseep.ai/app/qy527145-acemcp)
简体中文 | English
Acemcp
代码库索引和语义搜索的 MCP 服务器。
安装
作为工具安装(推荐)
# 安装到系统
uv tool install acemcp或临时运行(无需安装)
uvx acemcp
开发安装
# 克隆仓库
git clone https://github.com/qy527145/acemcp.git
cd acemcp安装依赖
uv sync运行
uv run acemcp
配置
配置文件会在首次运行时自动创建在 ~/.acemcp/settings.toml,包含默认值。
编辑 ~/.acemcp/settings.toml 进行配置:
BATCH_SIZE = 10
MAX_LINES_PER_BLOB = 800
BASE_URL = "https://your-api-endpoint.com"
TOKEN = "your-bearer-token-here"
TEXT_EXTENSIONS = [".py", ".js", ".ts", ...]
EXCLUDE_PATTERNS = [".venv", "node_modules", ".git", "__pycache__", "*.pyc", ...]
配置选项:
BATCH_SIZE: 每批上传的文件数量(默认:10)MAX_LINES_PER_BLOB: 大文件分割前的最大行数(默认:800)BASE_URL: API 端点 URLTOKEN: 认证令牌TEXT_EXTENSIONS: 要索引的文件扩展名列表EXCLUDE_PATTERNS: 要排除的模式列表(支持通配符如 *.pyc)您还可以通过以下方式配置:
--base-url、--tokenACEMCP_ 前缀)MCP 配置
将以下内容添加到您的 MCP 客户端配置中(例如 Claude Desktop):
基础配置
{
"mcpServers": {
"acemcp": {
"command": "uvx",
"args": [
"acemcp"
]
}
}
}
可用的命令行参数:
--base-url: 覆盖 BASE_URL 配置--token: 覆盖 TOKEN 配置--web-port: 在指定端口启用 Web 管理界面(例如 8080)启用 Web 管理界面的配置
要启用 Web 管理界面,添加 --web-port 参数:
{
"mcpServers": {
"acemcp": {
"command": "uvx",
"args": [
"acemcp",
"--web-port",
"8888"
]
}
}
}
然后访问管理界面:http://localhost:8888
Web 管理功能:
search_context 工具,输入项目路径和查询
- 查看格式化的结果和错误消息工具
search_context
基于查询搜索相关的代码上下文。此工具在搜索前自动执行增量索引,确保结果始终是最新的。它在您的代码库中执行语义搜索,并返回格式化的文本片段,显示相关代码的位置。
核心特性:
.gitignore 模式参数:
project_root_path(字符串):项目根目录的绝对路径/)作为路径分隔符
- Windows 示例:C:/Users/username/projects/myproject
- Linux/Mac 示例:/home/username/projects/myproject
query(字符串):用于查找相关代码上下文的自然语言搜索查询返回内容:
查询示例:
1. 查找配置代码:
{
"project_root_path": "C:/Users/username/projects/myproject",
"query": "日志配置 设置 初始化 logger"
}
返回:与日志设置、logger 初始化和配置相关的代码2. 查找认证逻辑:
{
"project_root_path": "C:/Users/username/projects/myproject",
"query": "用户认证 登录 密码验证"
}
返回:认证处理器、登录函数、密码验证代码3. 查找数据库代码:
{
"project_root_path": "C:/Users/username/projects/myproject",
"query": "数据库连接池 初始化"
}
返回:数据库连接设置、连接池配置、初始化代码4. 查找错误处理:
{
"project_root_path": "C:/Users/username/projects/myproject",
"query": "错误处理 异常 try catch"
}
返回:错误处理模式、异常处理器、try-catch 块5. 查找 API 端点:
{
"project_root_path": "C:/Users/username/projects/myproject",
"query": "API 端点 路由 HTTP 处理器"
}
返回:API 路由定义、HTTP 处理器、端点实现获得更好结果的技巧:
索引特性:
.gitignore 模式,与配置的排除模式结合使用搜索特性:
默认排除模式:
.venv, venv, .env, env, node_modules, .git, .svn, .hg, __pycache__,
.pytest_cache, .mypy_cache, .tox, .eggs, *.egg-info, dist, build,
.idea, .vscode, .DS_Store, *.pyc, *.pyo, *.pyd, .Python,
pip-log.txt, pip-delete-this-directory.txt, .coverage, htmlcov,
.gradle, target, bin, obj
模式支持通配符(*、?),并匹配目录/文件名或路径。注意: 如果项目根目录存在 .gitignore 文件,其模式将自动加载并与配置的排除模式结合使用。.gitignore 模式遵循 Git 的标准 wildmatch 语法。
高级特性
多编码文件支持
Acemcp 自动检测和处理不同字符编码的文件,适用于国际化项目:
Related MCP Servers
AI Research Assistant
hamid-vakilzadeh
AI Research Assistant provides comprehensive access to millions of academic papers through the Semantic Scholar and arXiv databases. This MCP server enables AI coding assistants to perform intelligent literature searches, citation network analysis, and paper content extraction without requiring an API key. Key features include: - Advanced paper search with multi-filter support by year ranges, citation thresholds, field of study, and publication type - Title matching with confidence scoring for finding specific papers - Batch operations supporting up to 500 papers per request - Citation analysis and network exploration for understanding research relationships - Full-text PDF extraction from arXiv and Wiley open-access content (Wiley TDM token required for institutional access) - Rate limits of 100 requests per 5 minutes with options to request higher limits through Semantic Scholar
Linkup
LinkupPlatform
Linkup is a real-time web search and content extraction service that enables AI assistants to search the web and retrieve information from trusted sources. It provides source-backed answers with citations, making it ideal for fact-checking, news gathering, and research tasks. Key features of Linkup: - Real-time web search using natural language queries to find current information, news, and data - Page fetching to extract and read content from any webpage URL - Search depth modes: Standard for direct-answer queries and Deep for complex research across multiple sources - Source-backed results with citations and context from relevant, trustworthy websites - JavaScript rendering support for accessing dynamic content on JavaScript-heavy pages
Math-MCP
EthanHenrickson
Math-MCP is a computation server that enables Large Language Models (LLMs) to perform accurate numerical calculations through the Model Context Protocol. It provides precise mathematical operations via a simple API to overcome LLM limitations in arithmetic and statistical reasoning. Key features of Math-MCP: - Basic arithmetic operations: addition, subtraction, multiplication, division, modulo, and bulk summation - Statistical analysis functions: mean, median, mode, minimum, and maximum calculations - Rounding utilities: floor, ceiling, and nearest integer rounding - Trigonometric functions: sine, cosine, tangent, and their inverses with degrees and radians conversion support