MCP

Orvanta supports the Model Context Protocol (MCP), an open standard enabling seamless interaction between LLMs and tools like Orvanta.

With MCP, you can connect favorite LLMs (Claude, Cursor, or any MCP-compatible client) to Orvanta, allowing you to trigger scripts and flows from client chat.

MCP provides access to Orvanta’s API endpoints for basic operations on:

Jobs — Monitor and manage job executions, track progress, retrieve logs, and view results
Resources — Create, read, update, and delete resources for third-party system connections
Variables — Manage workspace variables and secrets for secure credential storage
Schedules — Control scheduled executions with CRON-like automation
Workers — Monitor worker status, configuration, worker groups, and resource allocation

Connect with Claude

From the Claude Connectors Directory

Go to the Connectors Directory and search for Orvanta
Click Connect and log in to your Orvanta account
Select your workspace and choose which tools to expose
Start using scripts and flows directly from Claude

As a custom integration

Go to Claude > Settings > Integrations
Click “Add an integration”
Name it “Orvanta” and set the URL to: https://app.orvanta.cloud/api/mcp/gateway

For self-hosted instances, replace with your own instance base URL (e.g., https://orvanta.example.com/api/mcp/gateway).

When redirected to Orvanta, select your workspace and configure scope
Click Approve to complete connection

How to use

Connect with OAuth

The simplest way to connect is via OAuth. Add this URL to your MCP client:

<base_url>/api/mcp/gateway

For Orvanta Cloud: https://app.orvanta.cloud/api/mcp/gateway

This gateway URL works without knowing your workspace ID upfront. During OAuth flow, you’ll select your workspace and configure which tools to expose.

If you know your workspace ID, use the workspace-specific URL:

<base_url>/api/mcp/w/<your-workspace-id>/mcp

Example: https://app.orvanta.cloud/api/mcp/w/my-workspace/mcp

Both approaches automatically handle authentication via OAuth.

Generate your MCP token and URL

Navigate to account settings in Orvanta
Create a new token under the Tokens section
Select Generate MCP URL

Your MCP URL will look like:

<base_url>/api/mcp/w/<your-workspace-id>/mcp?token=<your-token>

Example: https://app.orvanta.cloud/api/mcp/w/my-workspace/mcp?token=abc123

Connect your LLM to Orvanta

The Orvanta MCP server uses HTTP streamable as the transport layer.

For Cursor:

Go to Cursor > Settings > MCP Tools
Click “Add a Custom MCP server”
Add this configuration in the json file:

{
  "mcpServers": {
    "orvanta-mcp": {
      "url": "<base_url>/api/mcp/w/<your-workspace-id>/mcp?token=<your-token>"
    }
  }
}

For Claude:

Go to Claude > Settings > Integrations
Click “Add an integration”
Choose a name (e.g., “Orvanta”)
Add your MCP URL in the “URL” field

For Claude Code:

claude mcp add --transport http orvanta <orvanta_url_with_token>

Replace with your actual MCP URL.

Example: triggering a script from Claude

If you’ve created a script called send_welcome_email, in Claude you could type:

“Send an email to user@example.com with subject ‘Welcome’ and body ‘Welcome to our service!’ with Orvanta”

Claude will:

Find the send_welcome_email script in your workspace
Ask for required inputs if needed
Run the script and show results in chat

Example: running a flow and checking its status

Trigger multi-step flows and monitor them:

“Run the ‘daily_data_sync’ flow with parameter region set to ‘us-east-1’”

Then follow up:

“What’s the status of the job that just ran?”

Claude uses the Jobs endpoint tool to look up recent execution, returning status, duration, and result.

Example: managing resources through chat

“List all my PostgreSQL resources in Orvanta”

“Create a new Slack resource called ‘alerts-channel’ with webhook URL https://hooks.slack.com/services/T00/B00/xxx”

Claude uses the Resources endpoint tools to list, create, or update resources in your workspace.

Available MCP tools

In addition to workspace scripts and flows (exposed as individual tools), the Orvanta MCP server provides built-in API endpoint tools.

When configuring MCP scope, you can select multiple folders to restrict which scripts and flows are exposed, letting you expose only relevant tools without granting full workspace access.

Scripts & flows

Tool	Description
`listScripts`	List all scripts in the workspace
`createScript`	Create a new script
`getScriptByPath`	Get a script by its path
`deleteScriptByHash`	Delete a script by hash (admin only)
`deleteScriptByPath`	Delete a script at a given path (admin only)
`runScriptByPath`	Run a script by path
`runScriptPreviewAndWaitResult`	Run a script preview and wait for result
`listFlows`	List all flows
`getFlowByPath`	Get a flow by its path
`createFlow`	Create a new flow
`updateFlow`	Update an existing flow
`deleteFlowByPath`	Delete a flow by path
`runFlowByPath`	Run a flow by path

Resources & variables

Tool	Description
`listResource`	List all resources
`getResource`	Get a resource
`createResource`	Create a new resource
`updateResource`	Update an existing resource
`deleteResource`	Delete a resource
`listResourceType`	List available resource types
`listVariable`	List all variables
`getVariable`	Get a variable
`createVariable`	Create a new variable
`updateVariable`	Update an existing variable
`deleteVariable`	Delete a variable

Jobs & schedules

Tool	Description
`getJob`	Get details of a specific job by ID
`getJobLogs`	Get logs for a specific job by ID
`listJobs`	List all completed jobs
`listQueue`	List all queued jobs
`listSchedules`	List all schedules
`getSchedule`	Get a schedule
`createSchedule`	Create a new schedule
`updateSchedule`	Update an existing schedule
`deleteSchedule`	Delete a schedule

Apps & workers

Tool	Description
`createApp`	Create a new app
`updateApp`	Update an existing app
`listWorkers`	List workers and their status

Other

Tool	Description
`queryDocumentation`	Query the Orvanta AI documentation assistant (EE only)

Troubleshooting

Not seeing any scripts/flows?
- Ensure your LLM tool is connected to the correct MCP URL
- If you chose “favorites only” when creating your MCP URL, make sure the script or flow is in your favorites
My LLM does not find the correct script/flow to run
- Ensure the script or flow is deployed and visible in your workspace
- Choose good titles and descriptions to help the LLM find the correct script/flow
Client has issues connecting to the MCP server
- Make sure your MCP client is configured to use HTTP streamable as the transport protocol
- Verify that your MCP URL is correct and the token is valid