context-bridge
Context Bridge is a lightweight MCP server that builds a persistent semantic knowledge graph of your codebase, enabling AI assistants to query complex codebases with sub-millisecond latency without re-reading files every session.
README
Context Bridge
Bridge the context gap between your codebase and AI coding tools.
Context Bridge is a lightweight MCP (Model Context Protocol) server that builds a persistent semantic knowledge graph of your codebase. It enables AI assistants to query complex codebases with sub-millisecond latency, eliminating the need to re-read files every session.
Why?
AI coding tools are powerful but suffer from a context gap:
- They re-read the same files in every session
- They lack deep understanding of your architecture
- They can't learn from your coding conventions
- 23 minutes of developer focus are lost per context switch
Context Bridge solves this by indexing your codebase into a local knowledge graph that persists across sessions.
Features
- Semantic Code Search — Query code with natural language
- Persistent Knowledge Graph — SQLite-based, survives restarts
- Sub-millisecond Queries — FTS5 + precomputed embeddings
- MCP Protocol — Works with Claude Code, Cursor, and any MCP client
- Auto-indexing — Watches files and updates the index automatically
- Zero Cloud — Everything runs locally
Quick Start
# Install globally
npm install -g context-bridge
# Initialize in your project
cd your-project
context-bridge init
# Start the MCP server
context-bridge serve
# Or use with Claude Code
claude mcp add context-bridge -- node context-bridge serve
Configuration
Create .context-bridge.json in your project root:
{
"include": ["src/**/*.{js,ts,jsx,tsx}", "lib/**/*.py"],
"exclude": ["node_modules/**", "dist/**", "*.test.js"],
"dbPath": ".context-bridge/db.sqlite",
"watch": true,
"maxFileSizeKB": 500
}
MCP Tools
| Tool | Description |
|---|---|
search_code |
Search code with natural language or regex |
get_symbol |
Get full context of a function/class/variable |
get_dependencies |
Show what a file depends on |
get_callers |
Find all callers of a function |
summarize_module |
Get a high-level summary of a module |
Architecture
┌─────────────────┐ ┌──────────────┐ ┌────────────────┐
│ Claude Code │────▶│ Context │────▶│ SQLite + FTS5 │
│ Cursor │ │ Bridge MCP │ │ Knowledge Graph│
│ Other MCP │◀────│ Server │◀────│ (persistent) │
│ Clients │ │ │ │ │
└─────────────────┘ └──────────────┘ └────────────────┘
│
▼
┌──────────────┐
│ File Watcher │
│ (auto-index) │
└──────────────┘
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。
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。
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。
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。
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。
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。
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。
mcp-server-qdrant
这个仓库展示了如何为向量搜索引擎 Qdrant 创建一个 MCP (Managed Control Plane) 服务器的示例。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。