MCP Server

Connect AI agents to clienwork via Model Context Protocol.

What is MCP?

Model Context Protocol (MCP) allows AI assistants to interact with external tools. clienwork provides an MCP server for AI-powered workflows.

Capabilities

AI agents can:

• List and search requests
• Get request/issue details
• Update status
• Query project data
• Create comments

Setup

Claude Desktop

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "clienwork": {
      "command": "npx",
      "args": ["-y", "@anthropic-ai/mcp-server-clienwork"],
      "env": {
        "CLIENWORK_API_KEY": "your-api-key"
      }
    }
  }
}

API Key

Generate in Settings → API → MCP:

1. Click Generate MCP Key
2. Copy the key
3. Store securely

Available Tools

| Tool | Description | |------|-------------| | list_requests | Query requests with filters | | get_request | Get request details | | update_request_status | Change request status | | list_issues | Query issues | | get_issue | Get issue details | | update_issue_status | Change issue status |

Example Queries

Ask your AI assistant:

• "Show me all open requests for Acme project"
• "What's the status of REQ-45?"
• "Mark REQ-45 as completed"
• "List high priority issues"

Security

• API key scoped to workspace
• Audit log of all actions
• Read-only mode available
• Revoke anytime