# Pneumatic — how to use (mcp.ai)

Connect your Pneumatic account and use 10 tools for project management straight from your AI agent. Connect with your own API key. Pneumatic is a workflow management platform for designing reusable processes, running workflows, coordinating tasks, and tracking operational performance.

## Option A — via MCP (recommended)
Remote MCP endpoint (HTTP, streamable): `https://api.mcp.ai/p_pneumatic?ms=1787295840000`
Add it as a custom/remote MCP connector in your client (Claude, Cursor, VS Code…), then authenticate when prompted. Once connected, ask the agent to use the server's tools (e.g. `pneumatic_get_task`).

## Option B — via direct REST API
Base URL: `https://api.mcp.ai/api/pneumatic`
Auth: `Authorization: Bearer sk_live_…` — create a workspace API key at https://mcp.ai/settings/api-keys
Discover endpoints: `GET https://api.mcp.ai/api/pneumatic/_endpoints`

### Endpoints
- `POST https://api.mcp.ai/api/pneumatic/get/task` — Get one task's instructions, output fields, performers, checklists, due date, and completion state.
  - body: { task_id: string }
- `POST https://api.mcp.ai/api/pneumatic/get/template` — Get a workflow template's tasks, kickoff fields, owners, and execution settings before running it.
  - body: { template_id: integer }
- `POST https://api.mcp.ai/api/pneumatic/get/workflow` — Get the current state, tasks, kickoff values, owners, and timing for one workflow run.
  - body: { workflow_id: integer }
- `POST https://api.mcp.ai/api/pneumatic/list/datasets` — List reusable Pneumatic datasets available for workflow and template field configuration.
  - body: { limit?: integer, offset?: integer }
- `POST https://api.mcp.ai/api/pneumatic/list/tasks` — Find tasks assigned to the connected user or team, including active or completed work.
  - body: { limit?: integer, offset?: integer, search?: string, assigned_to?: integer, template_id?: integer, is_completed?: boolean, template_task_api_name?: string }
- `POST https://api.mcp.ai/api/pneumatic/list/templates` — Find workflow templates the connected user can access, with filters for name, activity, and visibility.
  - body: { limit?: integer, offset?: integer, search?: string, is_active?: boolean, is_public?: boolean }
- `POST https://api.mcp.ai/api/pneumatic/list/workflows` — Find workflow runs by text, status, template, starter, current performer, or current task.
  - body: { limit?: integer, fields?: string, offset?: integer, search?: string, status?: string, is_external?: boolean, template_id?: string, workflow_starter?: string, current_performer?: string, template_task_api_name?: string, current_performer_group_ids?: string }
- `POST https://api.mcp.ai/api/pneumatic/run/template` — Start a workflow from an accessible template, optionally supplying a name, urgency, due date, and kickoff field values.
  - body: { name?: string, kickoff?: object, is_urgent?: boolean, template_id: integer, due_date_tsp?: string, ancestor_task_id?: integer }
- `POST https://api.mcp.ai/api/pneumatic/save/dataset` — Create a reusable dataset or update an existing dataset's name, description, or ordered items without exposing deletion.
  - body: { name?: string, items?: object[], dataset_id?: integer, description?: string }
- `POST https://api.mcp.ai/api/pneumatic/set/task/completion` — Complete an active task with output values or revert a completed task back to active work.
  - body: { output?: object, comment?: string, task_id: string, desired_state: string }

## Example prompts
- "What can I do in Pneumatic?"
- "Show me a summary of my Pneumatic account"

## More
- Page: https://mcp.ai/pneumatic
- Agent spec (llms.txt): https://mcp.ai/pneumatic/llms.txt
- Postman collection: https://mcp.ai/pneumatic/postman.json