Working Machines MCP Server
RemoteAbout Working Machines MCP Server
Working Machines provides a hosted MCP server and Cursor plugin that connects agents to apps and structured actions. It is for Cursor users who need remote integrations with scoped permissions and auditable execution records.
Key features
- 01Connect to 1,400+ apps
- 02Discover actions by intent
- 03Use provider-scoped permissions
- 04Enforce execution approval policies
- 05Review auditable action records
Use cases
- 01Find an action across connected apps
- 02Limit an agent to permitted account operations
- 03Require approval before an action runs
- 04Audit changes made by agent actions
MCP support
Provides a hosted remote MCP server at https://app.workingmachines.dev/mcp. It exposes app discovery, connection and action-search tools, guides, and secure action execution to clients such as Cursor.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://app.workingmachines.dev/mcpclaude mcp add --transport http klei30-working-machines https://app.workingmachines.dev/mcp{"mcpServers":{"klei30-working-machines":{"type":"http","url":"https://app.workingmachines.dev/mcp"}}}Open in Cursor{"servers":{"klei30-working-machines":{"type":"http","url":"https://app.workingmachines.dev/mcp"}}}Open in VS Code{"mcpServers":{"klei30-working-machines":{"type":"http","url":"https://app.workingmachines.dev/mcp"}}}{"mcpServers":{"klei30-working-machines":{"serverUrl":"https://app.workingmachines.dev/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
https://app.workingmachines.dev/mcpAuth requiredTools
Details
From the project READMEWorking Machines MCP Server for Cursor
Official Cursor plugin repository for Working Machines.
Connect Cursor to 1,400+ apps and 15,000+ machine-ready tools remotely through one secure, hosted Model Context Protocol (MCP) server.
Remote Access to 1,400+ Apps & 15,000+ Tools
Working Machines provides the application layer for AI agents. Through a single remote MCP connection (https://app.workingmachines.dev/mcp), your agent gets instant access to 1,400+ integrations and 15,000+ structured actions across:
- Team Collaboration: Slack, Gmail, Google Workspace, Microsoft Teams, Notion
- Development & Cloud: GitHub, GitLab, Sentry, Jira, AWS, Vercel, Datadog
- Projects & Productivity: Linear, Asana, Trello, ClickUp, Monday.com
- Commerce & CRM: Salesforce, HubSpot, Stripe, Shopify, Zendesk
- Data & Analytics: Snowflake, BigQuery, PostgreSQL, Airtable, Pinecone
Safety & Security Architecture
Working Machines is engineered from the ground up for safe, enterprise-grade AI execution:
🛡️ 1. Your Credentials Are Not Context
- Zero Local Secret Storage: API keys, OAuth tokens, and secret credentials stay behind the Working Machines execution boundary.
- Context Protection: Credentials never enter your Cursor chat context, prompt buffers, or local workspace files.
🔒 2. Scoped Capabilities & Policy Enforcement
- Intent-Based Access: Agents discover only the minimal actions required for the task at hand rather than loading full provider schemas.
- Provider-Native Scopes: Connect accounts once with provider-bound permissions (e.g. create issues only).
- Execution Policies: Allow, reject, or require approval for actions before any call leaves the execution boundary.
📋 3. Verifiable & Auditable Run History
- Structured Proof: Every action execution produces a structured, redacted, and auditable record.
- Execution Visibility: Tracks who acted, which connection was used, what changed, timing, and policy decisions for complete transparency.
Repository Structure
This repository follows the official Cursor plugin marketplace format:
working-machines/
├── .cursor-plugin/
│ └── marketplace.json
├── plugins/
│ └── working-machines/
│ ├── .cursor-plugin/
│ │ └── plugin.json
│ ├── assets/
│ │ └── logo.png
│ ├── skills/
│ │ └── working-machines/
│ │ └── SKILL.md
│ ├── mcp.json
│ └── README.md
├── scripts/
│ └── validate-template.mjs
├── README.md
├── CHANGELOG.md
├── LICENSE
├── NOTICE
└── .gitignore
Agent Workflow
Cursor agents follow the Working Machines discovery and execution sequence:
list_apps
↓
list_connections
↓
search_actions
↓
get_action_guide
↓
execute_action
↓
verify result
list_apps: Discover available applications and tool integrations.list_connections: Verify active account authorizations and permissions.search_actions: Find machine actions by intent.get_action_guide: Retrieve validated schemas and input parameters.execute_action: Execute the action securely behind the boundary.- Verify Result: Audit the structured execution response.
Validation
Verify repository manifest and component compliance:
node scripts/validate-template.mjs
Documentation & Links
- Website: https://www.workingmachines.dev
- Cursor Integration Guide: https://www.workingmachines.dev/agents/cursor
- Documentation: https://www.workingmachines.dev/docs
- App Dashboard: https://app.workingmachines.dev
License & Notice
- Open-source plugin wrapper licensed under the MIT License.
- See the NOTICE file regarding proprietary hosted infrastructure details.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.