Conduit MCP
Connects AI agents to Conduit data streams for ingesting events, querying data, and managing schemas. It enables seamless integration between services and agents with real-time forwarding and automated schema detection.
README
@useconduit/mcp
MCP server for Conduit — connect any AI agent to your data streams.
📖 API Docs · 🌐 Website · 📦 npm · 💻 GitHub
Quick Start
Get an API key from platform.usecondu.it/tokens, then add to your AI editor config:
Claude Code / Claude Desktop
Add to ~/.claude/settings.json:
{
"mcpServers": {
"conduit": {
"command": "npx",
"args": ["-y", "@useconduit/mcp"],
"env": {
"CONDUIT_API_KEY": "conduit_sk_..."
}
}
}
}
Cursor
Add to .cursor/mcp.json in your project:
{
"mcpServers": {
"conduit": {
"command": "npx",
"args": ["-y", "@useconduit/mcp"],
"env": {
"CONDUIT_API_KEY": "conduit_sk_..."
}
}
}
}
Windsurf
Add to ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"conduit": {
"command": "npx",
"args": ["-y", "@useconduit/mcp"],
"env": {
"CONDUIT_API_KEY": "conduit_sk_..."
}
}
}
}
Environment Variables
| Variable | Required | Default | Description |
|---|---|---|---|
CONDUIT_API_KEY |
✅ | — | Your Conduit API key |
CONDUIT_API_URL |
— | https://api.usecondu.it |
Custom API endpoint |
Tools
| Tool | Description |
|---|---|
conduit_list_streams |
List all data streams |
conduit_get_schema |
Get schema for a stream (columns, types, codecs) |
conduit_create_stream |
Create a new stream |
conduit_ingest |
Send events to a stream |
conduit_list_events |
Query events with pagination & time range filters |
conduit_add_forward |
Add a forwarding destination (HTTP, MQTT, or WebSocket) with auth options |
conduit_stream_stats |
Get ingestion statistics (event count, rate, latency) |
conduit_analyze_schema |
Analyze a JSON payload for optimal schema |
conduit_feedback |
Submit feedback to the Conduit team |
conduit_backfill |
Replay historical events to forwarding destinations |
conduit_backfill_status |
Check backfill job progress or list all jobs |
conduit_time_range |
Get earliest/latest event timestamps for a stream |
Resources
| URI | Description |
|---|---|
conduit://streams |
All streams |
conduit://streams/{name} |
Stream details + schema |
conduit://stats |
Platform-wide statistics |
API Documentation
Full interactive API docs are available at api.usecondu.it/docs (powered by Scalar).
Key endpoints:
| Method | Endpoint | Description |
|---|---|---|
POST |
/v1/{tenant}/{stream} |
Ingest events (any protocol: HTTP, WebSocket, MQTT) |
GET |
/api/v1/streams |
List streams |
GET |
/api/v1/streams/{name} |
Stream details + schema |
GET |
/api/v1/streams/{name}/events?from=&to=&limit= |
Query events with time range |
GET |
/api/v1/streams/{name}/stats |
Ingestion statistics |
GET |
/api/v1/streams/{name}/schema-history |
Schema evolution history |
POST |
/api/v1/streams/{name}/forwards |
Add forwarding destination |
POST |
/api/v1/streams/{name}/backfill |
Start backfill job |
GET |
/api/v1/streams/{name}/backfill |
List backfill jobs |
GET |
/api/v1/streams/{name}/time-range |
Event time range |
POST |
/api/v1/tokens |
Create API token |
GET |
/api/v1/account |
Account info + usage |
Machine-readable API specs:
- OpenAPI 3.1: api.usecondu.it/openapi.json
- LLM-friendly: api.usecondu.it/llms.txt
- LLM full spec: api.usecondu.it/llms-full.txt
What is Conduit?
Conduit is the lightweight data layer between your services. Send any JSON — schemas aren't defined, they emerge. And they evolve as your sources do.
- One endpoint, any protocol — HTTP, WebSocket, MQTT/S on the same path
- AI-powered schema detection — zero configuration, runs locally (your data never leaves)
- Real-time forwarding — HTTP webhooks, MQTT brokers, WebSocket endpoints with full auth options
- Backfill — replay historical events to new destinations
- Built for agents — MCP-native from day one, feedback loop included
- European infrastructure 🇪🇺 — all data hosted and processed in the EU, GDPR-compliant by design
How agents use Conduit
Agent: "I see live sensor data flowing in. I'll pipe it to our datawarehouse and add hot storage."
▸ conduit_list_events(stream: "sensors", limit: 1000)
↳ 1,000 events · 18.4 MB raw → 1.1 MB stored (94% compressed)
▸ conduit_add_forward(stream: "sensors", type: "http", url: "https://dwh.acme.io/ingest")
↳ Destination added · forwarding to datawarehouse
▸ conduit_add_forward(stream: "sensors", type: "mqtt", broker: "mqtt://redis.acme.io", topic: "hot/sensors")
↳ Destination added · 2 destinations active
▸ conduit_backfill(stream: "sensors", from: "2026-02-24", to: "2026-03-02")
↳ Backfilling 89,929 events from last 7 days
Learn more at usecondu.it
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。