Which integrations are available for this server?

Provides capabilities to ingest event data via MQTT and forward data streams to MQTT brokers for real-time messaging and IoT integration.

How do I use Conduit MCP?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Conduit MCP Show me the schema for the 'user-activity' stream" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

Conduit MCP

by useconduit

Overview Schema Source Related Servers Discussions Admin

JavaScript

Remote

@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_..."
      }
    }
  }
}

Related MCP server: Open Enterprise AI MCP Server

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

Available Tools

15 tools

conduit_add_forwardC

Add a forwarding destination to a stream. Supports HTTP webhooks, MQTT brokers, and WebSocket endpoints. Events are forwarded in real-time.

Inputs: stream (required), dest_type, url, broker, +7 more.

conduit_analyze_schemaB

Analyze a JSON payload and get the optimal ClickHouse schema with compression codecs

Inputs: payload (required).

conduit_backfillA

Replay historical events from a stream to one or more forwarding destinations. Runs as a background job with progress tracking.

Inputs: stream (required), from (required), to (required), destination_ids.

conduit_backfill_statusB

Check the status of a backfill job — progress, events processed, errors.

Inputs: stream (required), job_id.

conduit_create_streamA

Create a new data stream. Just send a name — schema is auto-detected from the first event.

Inputs: name (required), description.

conduit_create_transformB

Create a new transform for a stream. The code should be a JS function body that receives an event object and returns the transformed event. Available helpers: pick, omit, get, set, flatten, rename, mapValues, mapKeys.

Inputs: stream (required), name (required), code (required).

conduit_feedbackB

Submit feedback to the Conduit team — bugs, feature requests, improvements, or praise

Inputs: category (required), message (required), context.

conduit_get_schemaB

Get the current schema (columns, types, codecs) for a stream

Inputs: stream (required).

conduit_ingestB

Send one or more events (JSON objects) to a stream. Schema is auto-detected and evolves.

Inputs: stream (required), events (required).

conduit_list_eventsB

Query events from a stream with optional pagination and time range filters

Inputs: stream (required), limit, offset, from, +1 more.

conduit_list_streamsB

List all data streams in your Conduit account

Inputs: no named parameters.

conduit_list_transformsB

List all transforms configured for a stream. Transforms are JS functions applied to events before forwarding to destinations.

Inputs: stream (required).

conduit_preview_transformA

Preview a transform by running it against a sample payload without persisting. Returns the transformed output and execution time.

Inputs: stream (required), code (required), payload (required).

conduit_stream_statsB

Get ingestion statistics for a stream (event count, rate, schema version)

Inputs: stream (required).

conduit_time_rangeA

Get the time range and total event count for a stream. Useful before starting a backfill.

Inputs: stream (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

Deploy Server

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.7/5.0

Scored 2026-04-17 19:36 across 15 tools

Disambiguation5/5

Each tool has a clearly distinct purpose with no overlap: adding destinations, analyzing schemas, backfilling data, creating streams/transforms, submitting feedback, getting schemas, ingesting events, listing events/streams/transforms, previewing transforms, getting stats, and checking time ranges. The descriptions reinforce unique functions, making misselection unlikely.

Naming Consistency5/5

All tools follow a consistent 'conduit_verb_noun' pattern (e.g., conduit_add_forward, conduit_analyze_schema), with verbs like add, analyze, backfill, create, get, list, preview, and stream. This uniformity enhances predictability and readability across the toolset.

Tool Count5/5

With 15 tools, the set is well-scoped for a data streaming and processing server, covering core operations like ingestion, transformation, forwarding, querying, and management. Each tool serves a specific role without redundancy, fitting the domain's complexity appropriately.

Completeness5/5

The toolset provides complete coverage for data streaming workflows: creating and managing streams (create, list, stats), ingesting and querying events (ingest, list_events), transforming data (create_transform, list_transforms, preview_transform), forwarding (add_forward, backfill), and schema handling (analyze_schema, get_schema). No obvious gaps exist, supporting end-to-end agent operations.

Maintenance

ActivityInactive

ResponsivenessNo recent community issues

Resources

Related MCP Connectors

Composio
io.github.ComposioHQ
Connect AI agents to 1000+ apps with managed authentication and tool-calling.
Agent Orchestration App Automation
21
https://connect.composio.dev/mcp
Build to Launch MCP
io.github.jenny-ouyang
Connect your AI agent to 300+ methods and 100+ live tools
Developer Tools App Automation
1
https://mcp.buildtolaunch.ai
Connext MCP
com.rti
Integrate Connext AI into agentic workflows, enabling Connext product-aware assistance.
Agent Orchestration AI & Machine Learning Autonomous Agents
2
https://chatbot.rti.com/mcp
Airbyte
io.github.airbytehq
Build and manage data pipelines, add custom connectors, and chat with your data.
Data Platforms RAG Systems
1342
https://mcp.airbyte.com/mcp

Related MCP Servers

Keboola MCP Server
Data Platforms Databases
fastmcp-me
A
license
Not graded
quality
D
maintenance
Connects AI agents and MCP clients to Keboola, enabling storage queries, SQL transformations, job triggers, and more through natural language.
Updated 10 months ago (2026-01-19 23:25 UTC)
MIT
Open Enterprise AI MCP Serverofficial
Databases File Systems Data Platforms
enthrium
F
license
Not graded
quality
B
maintenance
Connects AI coding assistants like Claude Code, Cursor, and Windsurf to enterprise data sources (databases, files, APIs, etc.) via a single binary, with 45+ connector categories and built-in memory tools.
Updated 2 months ago (2026-09-09 02:06 UTC)
1
-
Production Monitoring MCP
Observability Monitoring Developer Tools
kowshik3383
A
license
A
quality
B
maintenance
Connects AI agents to live observability stacks including Sentry, GitHub, Vercel, Better Stack, and Cloudflare, enabling end-to-end incident investigation, deployment correlation, root cause analysis, and regression triage.
Updated 2 months ago (2026-09-13 05:56 UTC)
14
MIT
OutcomeCI MCP Serverofficial
App Automation Autonomous Agents
outcomeci
A
license
Not graded
quality
C
maintenance
Enables AI assistants to create, validate, and manage agent-powered workflows across team tools, with tools for inspecting schemas, configuring triggers, and reviewing runs and logs. It provides authorized remote access through OAuth without local installation or shared API keys.
Updated a month ago (2026-10-05 17:18 UTC)
1
MIT

@useconduit/mcp

Quick Start

Claude Code / Claude Desktop

Cursor

Windsurf

Environment Variables

Tools

Resources

API Documentation

What is Conduit?

How agents use Conduit

License

Available Tools

Tool Schema Changelog

TDQS

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

Keboola MCP Server

Open Enterprise AI MCP Serverofficial

Production Monitoring MCP

OutcomeCI MCP Serverofficial