F
licenseNot graded
qualityD
maintenanceEnables interaction with OpenHEXA platform through Claude Desktop, allowing users to query workspaces, list datasets, search pipelines, and view pipeline runs using natural language.
1
-
Hevo MCP Server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Hevo MCP Server list all my pipelines"
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.
Hevo MCP Server
An MCP (Model Context Protocol) server that exposes Hevo Data's pipeline API as tools for Claude Code and other MCP clients.
What it does
Manage Hevo Data pipelines directly from Claude Code:
list_pipelines— list all pipelines in your Hevo accountget_pipeline— get details of a specific pipelinecreate_pipeline— create a new pipelineenable_pipeline— enable a pipelinedisable_pipeline— disable a pipeline (optionally cancel active jobs)resync_pipeline— trigger a resync (optionally drop and reload)update_pipeline_config— update a pipeline's configurationupdate_source_config— update a pipeline's source configuration
Related MCP server: Pipedrive MCP
Status
enable_pipeline, disable_pipeline, and resync_pipeline are verified against Hevo's live API docs. update_pipeline_config and update_source_config have not yet been verified against live docs and may need adjustment. Test carefully before relying on these two in production.
Setup
1. Get your Hevo API credentials
You'll need an API key and secret from your Hevo account, plus your region (us, eu, in, or asia).
2. Install and build
git clone https://github.com/felixjoy89hevo/hevo-mcp.git
cd hevo-mcp
npm install
npm run build3. Register with Claude Code
claude mcp add hevo --scope user -- node /absolute/path/to/hevo-mcp/dist/index.jsThen set your credentials as environment variables in Claude Code's MCP config (see .env.example for the required variables):
HEVO_API_KEYHEVO_API_SECRETHEVO_REGION
4. Restart Claude Code
After any config or code change, restart your Claude Code session fully. Reconnecting isn't enough.
Requirements
Node.js >= 18
API Reference
Built against Hevo's live API docs.
License
MIT
Available Tools
8 toolscreate_pipelineA
Create a new Hevo pipeline. The shape of source and destination depends on their type (e.g. MYSQL, POSTGRES, S3, BIGQUERY, SNOWFLAKE). See https://edge-api-docs.hevodata.com/reference/post_api-v1-pipelines for full schemas.
Inputs: name (required), source (required), destination (required), run_now, +1 more.
disable_pipelineC
Disable (pause) a running pipeline.
Inputs: pipeline_id (required).
enable_pipelineA
Enable (resume) a paused pipeline.
Inputs: pipeline_id (required).
get_pipelineA
Get full configuration and status of a single pipeline.
Inputs: pipeline_id (required).
list_pipelinesA
List all data pipelines in the Hevo account (id, name, source/destination type, status).
Inputs: no named parameters.
resync_pipelineA
Resync a pipeline by restarting its historical load. If drop_and_load=true, destination tables are dropped and recreated (destructive). If false (default), tables are kept and only differences are updated.
Inputs: pipeline_id (required), drop_and_load.
update_pipeline_configA
Modify pipeline-level config (name, schedule, query mode, auto-mapping). Send only fields to change.
Inputs: pipeline_id (required), name, extra, schedule, +2 more.
update_source_configA
Modify the SOURCE configuration of an existing pipeline (host, port, database, credentials, etc.).
Inputs: config (required), pipeline_id (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
A3.7/5.0
Scored across 8 tools
Disambiguation5/5
Each tool targets a distinct action and object (list, get, create, enable, disable, resync, update pipeline config, update source config). The two update tools are clearly separated by scope (pipeline-level vs source-level) with descriptions that prevent confusion.
Naming Consistency5/5
All tool names follow a consistent verb_noun pattern in snake_case: list_pipelines, get_pipeline, create_pipeline, enable_pipeline, disable_pipeline, resync_pipeline, update_pipeline_config, update_source_config. The naming style and verb choice are uniform.
Tool Count5/5
With 8 tools, the server covers the essential pipeline management operations without bloat. Each tool serves a distinct, necessary purpose for managing Hevo pipelines.
Completeness4/5
The surface covers list, get, create, enable/disable, resync, and update operations, which are core to pipeline management. The only notable gap is the absence of a delete_pipeline tool, which is a minor lifecycle gap that agents can work around by disabling pipelines.
Maintenance
ActivityInactive
ResponsivenessNo recent community issues
Related MCP Connectors
Build and manage data pipelines, add custom connectors, and chat with your data.
Manage Jitsu data pipelines: destinations, streams, connections, functions, live events.
List reverse-ETL sources, destinations, models, syncs and runs; trigger syncs into SaaS tools.
Inspect RudderStack workspaces, pipelines, and schemas, and manage transformations and audiences.
Related MCP Servers
- AlicenseBqualityFmaintenanceEnables natural language interaction with Pipedrive CRM via Claude Code, allowing users to manage deals, contacts, activities, and more through conversational commands.2611 npmMIT
- AlicenseAqualityDmaintenanceEnables Claude Code to manage Hetzner Cloud servers, including creating, deleting, powering on/off, and rebooting servers, as well as managing SSH keys and listing resources.1431 npm1MIT
- AlicenseNot gradedqualityDmaintenanceEnables Claude to manage GoHighLevel CRM contacts, pipelines, and workflows through natural language commands.115 npmMIT