Using Process Street’s MCP Server

Process Street offers a Model Context Protocol (MCP) server, accessible via app integration, which allows AI assistants and other applications to access your workflows, workflow runs, tasks, users, and data sets from outside the Process Street platform.

This server provides a way to interact with your Process Street organization through various AI platforms and tools that support MCP.

With this server, Process Street customers can:

1. Access Process Street data from compatible AI applications
2. Create and manage workflows runs & assign tasks
3. Generate reports and summaries based on Process Street data
4. Analyze Process Street data and get AI-powered suggestions

Example requests users could make from outside Process Street using the MCP:

1. “Create a new run of the Quarterly Access Review workflow and assign it to the compliance manager [[email protected]], if it’s not already been assigned to someone”
2. “Find the most recent Client Onboarding workflow runs and show me where there are bottlenecks from incomplete tasks”
3. “Search Data Set records for active vendors and, if they haven’t been reviewed in the past 6 months, mark them as Review”

The MCP server supports most Process Street API endpoints as tools.

The MCP server uses your Process Street login credentials to access it. If you have SAML SSO enabled in your organization, MCP server is NOT supported for you at the moment.

Admins, Builders and Users can use the MCP server and can only interact with resources they have permissions to.

Requirements

A compatible MCP client, including:

• Claude (claude.ai)
• ChatGPT (available on Pro, Team, Business, Enterprise, and Edu plans)
• Microsoft Copilot Studio
• Or any other application that has implemented an MCP client

How to set up the MCP

Claude

• Log in to Process Street (If you are part of more than one organization, be sure to switch to the one you’d like to connect the MCP with)
• Log in to Claude
• Click the + button in your chat
• Select Connectors, then select Manage connectors
• Select Browse Connectors, then type Process Street into the search box
• Click the + button to sign in with your Process Street credentials
• Authorize the app and open Claude to finish

ChatGPT

Note: MCP support in ChatGPT requires a Pro, Team, Business, Enterprise, or Edu plan.

1. Log in to Process Street (if you are part of more than one organization, be sure to switch to the one you’d like to connect the MCP with)
2. Log in to ChatGPT
3. Go to Settings → Connectors
4. Select Add Connector and enter the Process Street MCP server URL
5. Complete authentication with your Process Street credentials
6. Once connected, Process Street tools are available in your ChatGPT conversations

Tip: ChatGPT asks you to confirm before executing any actions that modify data in Process Street (such as creating runs or updating tasks). Read-only actions like viewing workflows or pulling reports run without a confirmation prompt.

Microsoft Copilot Studio

• Log in to Process Street (If you are part of more than one organization, be sure to switch to the one you’d like to connect the MCP with)
• Log in to Copilot Studio
• Create an Agent
• Add a tool, select Model Context Protocol and search for Process Street MCP Server
• Create a new connection
• Complete authentication
• Publish your Agent
• Connect the channels you’d like to connect the MCP with

Other clients

Process Street’s MCP server works with any application that supports the Model Context Protocol. For clients we don’t offer a one-click connector for, add it as a remote MCP server and authenticate with a bearer token, using a Process Street API key as the token.

You’ll need two things:

• The MCP server URL: https://mcp.process.st/
• A Process Street API key. Admins can generate one from the integrations page in the organization manager. See Process Street API for details, and Restricted API keys if you want to limit what the key can do.

Then add an Authorization: Bearer YOUR_API_KEY header to your client’s MCP configuration. Two common examples follow. Treat your API key like a password.

VS Code

Add the server to .vscode/mcp.json in your workspace, or open your user configuration with the MCP: Open User Configuration command. Using an input keeps the key out of the file: VS Code prompts for it once and stores it securely.

{
  "servers": {
    "process-street": {
      "type": "http",
      "url": "https://mcp.process.st/",
      "headers": {
        "Authorization": "Bearer ${input:ps-api-key}"
      }
    }
  },
  "inputs": [
    {
      "id": "ps-api-key",
      "type": "promptString",
      "description": "Process Street API key",
      "password": true
    }
  ]
}

Cursor

Add the server to ~/.cursor/mcp.json (available in every project) or .cursor/mcp.json (for a single project), then replace YOUR_API_KEY with your Process Street API key.

{
  "mcpServers": {
    "process-street": {
      "url": "https://mcp.process.st/",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}

The same pattern, a remote MCP server with an Authorization: Bearer header, works for any other MCP client that supports remote servers.

If you’re using an MCP client that we don’t already support and need a hand, reach out to our support team.

• Learn the 5 stages of process building in our Getting started guide
• Watch helpful videos and webinars on our YouTube channel
• Learn about Process AI
• Collect info with Forms
• Organize data with Data Sets
• Document information and policies with Pages
• Get inspired by our Blog