AI agent
Agents CLI + ProjectMind
HTTP and client CLIs—no ProjectMind binary
Headless automation uses the same MCP URL. Prefer OAuth in interactive clients; use project API keys only where browser login is impossible.
Example chat
via ProjectMind MCP · Agents CLI
How to connect Agents CLI
- Claude Code: claude mcp add with HTTP transport to the ProjectMind URL and Authorization header.
- Codex / scripts: JSON-RPC POST to /api/mcp with Bearer API key.
- Claude Desktop: bridge with npx mcp-remote and --header Authorization when needed.
- Never commit API keys; rotate keys in Project Settings if leaked.
ProjectMind MCP server URL
https://projectm.dev/api/mcp
cURL tools/list (API key)
curl -X POST https://projectm.dev/api/mcp \ -H "Authorization: Bearer YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{"jsonrpc":"2.0","id":1,"method":"tools/list","params":{}}'
OAuth sign-in is recommended for chat clients. Project API keys (imk_…) work when the client cannot open a browser. Confirm before startEpicExecution, enqueueAgentJob, or deleteTask.
What you can do with Agents CLI
Claude Code
Interactive terminal sessions with OAuth or API keys.
curl / HTTP
tools/list and tools/call for debugging integrations.
mcp-remote
Stdio bridge for clients that cannot speak remote HTTP directly.
No imemory-cli
We do not ship a standalone npm binary—clients speak MCP directly.
Example prompts
- Document the difference between OAuth MCP and API key headers.
- List environment variables used by npm run setup:cursor.
Prefer read tools first (listTasks, getProjectContext, searchContext). Mutations should follow your confirmation—especially epic execution and agent job enqueue.
Frequently asked questions
- Is ProjectMind preinstalled in ChatGPT or Claude?
- No. Add ProjectMind as a custom MCP connector (or sign in with OAuth when the client supports remote MCP). Use your ProjectMind account and approve project access in the consent flow.
- Will the agent change my project without asking?
- Destructive or high-impact MCP writes—deleting tasks, starting epic execution, completing agent jobs—should run only after you confirm in chat or in the ProjectMind UI. Prefer read tools first (listTasks, getTaskContext, searchContext).
- Which authentication should I use?
- OAuth is best for interactive assistants. Project API keys (imk_…), global keys (imgk_…), and bucket keys (imbk_…) work in headers for headless clients. Never put keys in query strings.
- Can agents run epics and background jobs?
- Yes, when your role allows it. Tools such as confirmEpicPlan, startEpicExecution, and enqueueAgentJob enqueue work your team can monitor in ProjectMind. Pause or cancel from the app if something looks wrong.
- Is there a ProjectMind CLI npm package?
- No. Use MCP-compatible clients (Claude Code, Cursor, curl) or the mcp-remote bridge documented on /docs/mcp.