ContextStream MCP Server

ContextStream MCP Server

Provides AI assistants with persistent memory and code intelligence across all tools and conversations. Features semantic search, knowledge graphs, decision tracking, and impact analysis with 60+ tools for universal context preservation.

Category
访问服务器

README

ContextStream MCP Server

npm version GitHub

🧠 Your AI's Permanent Brain — Across Every Tool, Every Conversation

Tired of re-explaining your codebase to AI every single time?

ContextStream gives your AI persistent memory that follows you everywhere. Decisions remembered. Context preserved. No more repeating yourself.

Website: contextstream.io | Docs: contextstream.io/docs/mcp


✨ Why ContextStream?

The Problem

  • Close a chat with Cursor → Open a new one → AI forgot everything
  • Switch from Claude to Windsurf → Start explaining from scratch
  • New team member joins → Days of onboarding conversations
  • "Why did we build it this way?" → No one remembers

The Solution

ContextStream is a universal memory layer for AI coding tools. It works with Cursor, Claude Code, Windsurf, VS Code, and any MCP-compatible client.

You: "Initialize session and remember we use PostgreSQL with TypeScript strict mode"
...later, in a NEW conversation...
You: "What are my preferences for this project?"
AI: "You prefer TypeScript with strict mode, and you're using PostgreSQL."

It remembers. Across sessions. Across tools. Forever.


🚀 2-Minute Setup

1. Get your API key (30 seconds)

Sign up at contextstream.io → Settings → API Keys → Create one.

2. Add to your MCP config (60 seconds)

Cursor / Claude Code / Windsurf / VS Code:

{
  "mcpServers": {
    "contextstream": {
      "command": "npx",
      "args": ["-y", "@contextstream/mcp-server"],
      "env": {
        "CONTEXTSTREAM_API_URL": "https://api.contextstream.io",
        "CONTEXTSTREAM_API_KEY": "your_api_key"
      }
    }
  }
}

Codex CLI: Add to ~/.codex/config.toml:

[mcpServers.contextstream]
command = "npx"
args = ["-y", "@contextstream/mcp-server"]

[mcpServers.contextstream.env]
CONTEXTSTREAM_API_URL = "https://api.contextstream.io"
CONTEXTSTREAM_API_KEY = "your_api_key"

3. Try it out (30 seconds)

Start a chat and say:

"Initialize session and remember that I prefer TypeScript with strict mode"

Then start a brand new conversation and ask:

"What are my preferences?"

It remembers.


🔥 Beyond Memory — That's Just the Beginning

ContextStream isn't just memory storage. It understands your code.

Impact Analysis

"What breaks if I change the UserService class?"

See all dependencies and side effects before refactoring.

Decision History

"Why did we choose PostgreSQL over MongoDB?"

Recall past decisions with full context and reasoning.

Semantic Code Search

"Find where we handle rate limiting"

Search by meaning, not just keywords. Find code by intent.

Knowledge Graph

"Show dependencies for the auth module"

Visualize connections between code, decisions, and docs.


📊 60+ MCP Tools at Your Fingertips

🔍 Code Search & Context

Tool Description
search_semantic Find code by meaning, not just keywords
search_hybrid Combines semantic + keyword for best results
search_pattern Regex-based code search
ai_context Automatically gather relevant code, docs, and memory

🧠 Memory & Knowledge

Tool Description
session_remember Quick natural language memory ("Remember I prefer TypeScript")
session_recall Quick recall ("What were the auth decisions?")
memory_create_event Store decisions, insights, and context
memory_search Find relevant past context
memory_decisions Get decision summaries

📊 Code Intelligence

Tool Description
graph_dependencies Understand what depends on what
graph_call_path Trace execution flows
graph_impact Understand change impact
graph_circular_dependencies Find problematic cycles
graph_unused_code Identify dead code

🤖 AI Integration

Tool Description
ai_context Build LLM-ready context from your codebase
ai_enhanced_context Deep analysis with memory integration
ai_plan AI-powered development planning
ai_tasks Break down work into actionable tasks

🚀 Session Management

Tool Description
session_init Initialize conversation with auto-context
context_smart Get relevant context for any message
session_capture Store context to memory
session_compress Compress chat history to memory

See all 60+ tools →


✨ Auto-Context (v0.3.0+)

Context loads automatically on the first tool call. No manual setup required.

═══════════════════════════════════════════
🧠 AUTO-CONTEXT LOADED (ContextStream)
═══════════════════════════════════════════
📁 Workspace: my-project
📂 Project: backend-api

📋 Recent Decisions:
   • Use PostgreSQL for persistence
   • JWT for authentication

🧠 Recent Context:
   • [decision] API design patterns
   • [preference] TypeScript strict mode
═══════════════════════════════════════════

Works with all MCP clients — no client-side changes required.


🛡️ Privacy & Security

  • Encrypted at rest — All data encrypted with AES-256
  • No training on your data — We never use your code to train AI
  • You control access — Workspace permissions & API keys
  • Self-host option — Enterprise can self-host for full control

🏆 Why Not Built-in Memory?

Built-in memory ContextStream
✗ Vendor lock-in — switch tools, lose everything Universal — Cursor, Claude, Windsurf, any MCP tool
✗ Expires or resets over time Persistent forever — never lose context (paid plans)
✗ No semantic search Semantic search — find anything across all history
✗ Personal only — teammates start from zero Team memory — shared context, instant onboarding
✗ No API access 60+ MCP tools — full API and automation
✗ Memory isolated from code Knowledge graph — decisions linked to code
✗ Clunky to use Natural language — "remember X", "what did we decide about Y?"

📖 Full Tool Reference

<details> <summary><strong>Authentication</strong></summary>

Tool Description
auth_me Get current user profile

</details>

<details> <summary><strong>Workspaces</strong></summary>

Tool Description
workspaces_list List accessible workspaces
workspaces_get Get workspace details
workspaces_create Create a new workspace
workspaces_overview Get workspace summary
workspaces_analytics Get usage analytics
workspaces_content List workspace content

</details>

<details> <summary><strong>Projects</strong></summary>

Tool Description
projects_list List projects (by workspace)
projects_get Get project details
projects_create Create a new project
projects_overview Get project summary
projects_statistics Get code statistics
projects_files List indexed files
projects_index Trigger re-indexing
projects_index_status Check indexing status

</details>

<details> <summary><strong>Search</strong></summary>

Tool Description
search_semantic Semantic vector search
search_hybrid Combined semantic + keyword
search_keyword Traditional keyword search
search_pattern Regex pattern search
search_suggestions Get search suggestions

</details>

<details> <summary><strong>Memory</strong></summary>

Tool Description
memory_create_event Store a memory event
memory_get_event Retrieve an event
memory_update_event Update an event
memory_delete_event Remove an event
memory_list_events List events in workspace
memory_bulk_ingest Bulk import events
memory_distill_event Extract key insights
memory_create_node Create knowledge node
memory_get_node Get knowledge node
memory_update_node Update knowledge node
memory_delete_node Remove knowledge node
memory_supersede_node Replace with new version
memory_list_nodes List knowledge nodes
memory_search Search memory
memory_decisions Get decision summaries
memory_timeline Get chronological timeline
memory_summary Get condensed summary

</details>

<details> <summary><strong>Graph Analysis</strong></summary>

Tool Description
graph_related Find related knowledge nodes
graph_path Find path between nodes
graph_decisions Decision history in graph
graph_dependencies Query code dependencies
graph_call_path Trace call paths
graph_impact Analyze change impact
graph_circular_dependencies Find circular deps
graph_unused_code Find dead code
graph_contradictions Find conflicting info

</details>

<details> <summary><strong>AI</strong></summary>

Tool Description
ai_context Build LLM context
ai_enhanced_context Deep context with memory
ai_embeddings Generate embeddings
ai_plan Generate dev plan
ai_tasks Generate tasks

</details>

<details> <summary><strong>Session & Auto-Context</strong></summary>

Tool Description
session_init Initialize conversation
session_get_user_context Get user preferences
session_capture Store context to memory
session_smart_search Search with context enrichment
session_remember Quick natural language memory
session_recall Quick natural language recall
context_smart Get relevant context for message
session_compress Compress chat history to memory
session_summary Get compact workspace summary
session_delta Get changes since timestamp

</details>


🔌 Pre-built Prompts

Prompt Description
explore-codebase Get a codebase overview
capture-decision Document an ADR
review-context Build code review context
investigate-bug Debug investigation helper
explore-knowledge Navigate knowledge graph
onboard-to-project Generate onboarding guide
analyze-refactoring Find refactoring opportunities
build-context Build comprehensive LLM context

⚙️ Environment Variables

Variable Required Description
CONTEXTSTREAM_API_URL Yes API base URL (https://api.contextstream.io)
CONTEXTSTREAM_API_KEY Yes Your API key from contextstream.io

🔗 Links


🤝 Contributing

We welcome contributions! Here's how you can help:

  1. Report bugs — Open an issue at GitHub Issues
  2. Request features — Share your ideas in the issues
  3. Submit PRs — Fork the repo and submit pull requests

Development

# Clone the repo
git clone https://github.com/contextstream/mcp-server.git
cd mcp-server

# Install dependencies
npm install

# Run in development mode
npm run dev

# Build for production
npm run build

# Type check
npm run typecheck

📄 License

MIT

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选