English Français العربية

Process Street

Official registry AI and agents

Connect AI agents to Process Street workflows, tasks, runs, data sets, and operational records.

Source code Website Documentation

What can you do with Process Street?

  • Find and work with workflows, workflow runs, tasks, users, and data sets
  • Create and manage workflow runs and assigned tasks
  • Produce reports and summaries from Process Street data
  • Analyze operational records available to the connected user

Install

Add this to your client's MCP configuration (Claude Desktop: claude_desktop_config.json; Cursor: .cursor/mcp.json; VS Code and others use the same "mcpServers" shape).

Remote (streamable-http)
Claude Code 
claude mcp add --transport http process-street 'https://mcp.process.st/'
JSON configuration (Claude Desktop, Cursor, VS Code) 
{
    "mcpServers": {
        "process-street": {
            "type": "http",
            "url": "https://mcp.process.st/"
        }
    }
}

Documentation

From the project's README on GitHub, refreshed weekly. Links open on GitHub.

Contents
  1. Process Street MCP Server
  2. Connect
  3. Capabilities and access
  4. Registry metadata
  5. Resources
  6. Repository scope

Process Street MCP Server

Process Street's hosted Model Context Protocol server connects compatible AI clients to Process Street workflows, workflow runs, tasks, users, data sets, and operational records.

This repository contains the public discovery metadata for the hosted server. It does not contain the server implementation.

Connect

Use this remote server URL in an MCP client:

https://mcp.process.st/

The server uses Streamable HTTP. Compatible clients can use the interactive authorization flow. Process Street API keys can also be supplied as bearer tokens where the client supports custom authentication.

See the Process Street MCP Server guide for setup instructions for supported clients.

Capabilities and access

The server exposes Process Street operations as MCP tools. Depending on the connected user's permissions, these tools can help an AI client:

  • Find and work with workflows, workflow runs, tasks, users, and data sets
  • Create and manage workflow runs and assigned tasks
  • Produce reports and summaries from Process Street data
  • Analyze operational records available to the connected user

Access remains subject to the user's Process Street permissions. Organizations that require SAML SSO are not currently supported by the documented MCP connection flow.

Registry metadata

server.json is published in the Official MCP Registry as io.github.process-street/process-street-mcp version 1.0.0.

Published Registry versions are immutable. Any metadata correction must use a new unique version.

Resources

Repository scope

Issues and pull requests in this repository should concern public discovery metadata or its documentation. Product support and security matters should use the official resources above.

Frequently asked questions

What is Process Street?

Connect AI agents to Process Street workflows, tasks, runs, data sets, and operational records.

How do I install Process Street?

It runs as a remote server. In Claude Code: claude mcp add --transport http process-street 'https://mcp.process.st/'. For other clients, paste the JSON configuration from this page into their MCP settings.

Does Process Street need an API key?

Its registry entry lists no required key or secret. Some features may still need an account with the service it connects to.

Is Process Street open source?

Its code is public on GitHub, but the repository does not declare a standard license.

Who maintains Process Street?

It is published by process-street. AI.tn lists it but does not maintain or endorse it.

From the official MCP Registry. Listing is not an endorsement: review a server's code and permissions before giving it access to your data.