Rework

A Model Context Protocol (MCP) server for integrating Rework platform with AI applications. This server allows AI agents to interact with Rework projects, tasks, workflows, and jobs through a standardized protocol.

🚀Status Update:v1.1.3 now available with complete project management and workflow support.
- Get your Rework credentials:

- API key from Rework platform settings
- Workspace information from your Rework account

Add this entry to your client's MCP settings JSON file:

{ "mcpServers": { "Rework": { "command": "npx", "args": [ "-y", "rework-mcp-server" ], "env": { "REWORK_PROJECT_ACCESS_TOKEN": "", "REWORK_PROJECT_PASSWORD": "", "REWORK_WORKFLOW_ACCESS_TOKEN": "", "REWORK_WORKFLOW_PASSWORD": "", "REWORK_ACCOUNT_ACCESS_TOKEN": "", "REWORK_ACCOUNT_PASSWORD": "" } } } }

Alternatively, you can run the server directly using Node:

node index.js --env REWORK_PROJECT_ACCESS_TOKEN=your-project-access-token --env REWORK_PROJECT_PASSWORD=your-project-password --env REWORK_WORKFLOW_ACCESS_TOKEN=your-workflow-access-token --env REWORK_WORKFLOW_PASSWORD=your-workflow-password --env REWORK_ACCOUNT_ACCESS_TOKEN=your-account-access-token --env REWORK_ACCOUNT_PASSWORD=your-account-password

You can use theDISABLED_TOOLSenvironment variable to disable specific tools. Provide a comma-separated list of tool names to disable (e.g.,create_task,get_tasks).

Disable tools you don't need if you are experiencing issues with the number of tools or any context limitations.

The server can be run in SSE (Server-Sent Events) mode by setting the following environment variables:

{ "mcpServers": { "Rework": { "command": "node", "args": [ "index.js" ], "env": { "REWORK_PROJECT_ACCESS_TOKEN": "your-project-access-token", "REWORK_PROJECT_PASSWORD": "your-project-password", "REWORK_WORKFLOW_ACCESS_TOKEN": "your-workflow-access-token", "REWORK_WORKFLOW_PASSWORD": "your-workflow-password", "REWORK_ACCOUNT_ACCESS_TOKEN": "your-account-access-token", "REWORK_ACCOUNT_PASSWORD": "your-account-password", "ENABLE_SSE": "true", "PORT": "8000" // Optional, defaults to 3000 } } } }

node index.js --env REWORK_PROJECT_ACCESS_TOKEN=your-project-access-token --env REWORK_PROJECT_PASSWORD=your-project-password --env REWORK_WORKFLOW_ACCESS_TOKEN=your-workflow-access-token --env REWORK_WORKFLOW_PASSWORD=your-workflow-password --env REWORK_ACCOUNT_ACCESS_TOKEN=your-account-access-token --env REWORK_ACCOUNT_PASSWORD=your-account-password --env ENABLE_SSE=true --env PORT=8000

version: '3.8' services: rework-mcp-server: build: context: . dockerfile: Dockerfile ports: - '3000:8000' environment: - REWORK_PROJECT_ACCESS_TOKEN=${REWORK_PROJECT_ACCESS_TOKEN} - REWORK_PROJECT_PASSWORD=${REWORK_PROJECT_PASSWORD} - REWORK_WORKFLOW_ACCESS_TOKEN=${REWORK_WORKFLOW_ACCESS_TOKEN} - REWORK_WORKFLOW_PASSWORD=${REWORK_WORKFLOW_PASSWORD} - REWORK_ACCOUNT_ACCESS_TOKEN=${REWORK_ACCOUNT_ACCESS_TOKEN} - REWORK_ACCOUNT_PASSWORD=${REWORK_ACCOUNT_PASSWORD} - ENABLE_SSE=true - LOG_LEVEL=info volumes: - ./src:/app/src restart: unless-stopped healthcheck: test: ["CMD", "curl", "-f", "http://localhost:8000/health"] interval: 30s timeout: 10s retries: 3 start_period: 5s

See the project documentation for optional parameters and advanced usage.

When creating tasks or jobs, you can assign users using theuser_idparameter. Additionally, you need to specify thecreator_usernameto indicate who created the task or job:

{ "name": "🚀 New Feature Implementation", "board_id": "board_123", "content": "Implement the new feature described in the spec", "creator_username": "jane.doe", "user_id": "user_456" }

The user management tools help you find users by name or email and get their IDs for task assignment.

The Rework MCP server provides clear error messages for:

- Missing required parameters
- Invalid IDs or references
- Resources not found
- Authentication failures
- Permission issues
- API errors
- Rate limiting

TheLOG_LEVELenvironment variable can be specified to control the verbosity of server logs. Valid values aretrace,debug,info,warn, anderror(default). This can also be specified on the command line as:--env LOG_LEVEL=info.

Both task and job creation support custom fields through thecustom_fieldsparameter, which accepts an array of objects withidandvalueproperties:

{ "custom_fields": [ { "id": "custom_field_123", "value": "High Priority" }, { "id": "custom_field_456", "value": true } ] }

Contributions are welcome! Please feel free to submit a Pull Request.

This project is licensed under the MIT License - see theLICENSEfile for details.

Perform queries and entity operations in your Fibery workspace.