Model Context Protocol · Claude Code, Cursor, VS Code, and more

Give your AI agent an automation engine.

Connect Claude Code, Cursor, VS Code, or any MCP client to Kovca. Your agent builds, tests, and runs real workflows, limited by the access of the key you give it, and every change shows up in the Studio.

Start freeRead the MCP docs
Connect

One command, one API key

Kovca is a remote MCP server over Streamable HTTP. Create an API key with the access you want the agent to have, and add the server to your client.

Terminal
claude mcp add --transport http kovca https://kovca.io/api/v1/mcp \
  --header "Authorization: Bearer kvc_…"
Access levels

The key decides what the agent can do

Tools above the key's level answer INSUFFICIENT_ACCESS, so you can let an agent build and test freely while publishing stays with a person.

Level 1
Run
Run what's published
list_workflowsget_workflowrun_workflowget_runlist_runslist_waitswf_… workflow tools
Level 2 · adds
Author
Build and test drafts
list_nodesget_node_speclist_connectorscreate_workflowedit_workflowset_triggervalidate_workflowtest_workflow
Level 3 · adds
Publish
Ship and operate
publish_workflowactivate_automationpause_automationset_workflow_enableddecide_wait

A selection of tools. Each level includes the ones before it. The MCP docs list every tool.

Built for agents

Powerful for the agent, safe for you

The MCP server calls the same functions as the Studio and the API. It's never a second, looser way to do things.

  • Every edit is visible

    Agents edit the same drafts as the Studio, through the same validated operations, so you can watch, undo, or take over at any point.

  • Credentials stay sealed

    Agents never see app tokens or secrets. Connecting an app returns a link for a person to approve on the Connections page.

  • Access you choose

    Every API key is Run, Author, or Publish. An agent that can build a workflow can't ship it unless you give it a Publish key.

  • Workflows become tools

    Expose a published workflow as its own wf_ tool, with its input schema and a description, so any agent can run it like a function.

A published workflow as an agent tool
> Triage this one: "App crashes on login since 2.3.0"

● kovca - wf_triage_issue (MCP)
  ⎿ { "category": "bug",
      "priority": "high",
      "linear_issue": "ENG-482" }

Not using an agent?

Build the same workflows on a canvas, or in your terminal with the kovca CLI.

The Studio The CLI