# Pneumatic — MCP server on 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. By: mcp.ai · official Page: https://mcp.ai/pneumatic ## Connect (MCP protocol) Remote MCP endpoint (HTTP, streamable): https://api.mcp.ai/p_pneumatic?ms=1787293560000 Add it as a custom/remote MCP connector, then authenticate when prompted. ## REST API (no MCP client required) Every tool is also a REST endpoint, authed with a workspace API key. Discover: GET https://api.mcp.ai/api/pneumatic/_endpoints # public; lists every endpoint Call: POST https://api.mcp.ai/api/pneumatic/ Authorization: Bearer sk_live_… # create one at https://mcp.ai/settings/api-keys Content-Type: application/json Body: { …args } → { "ok": true, "tool": "", "result": { … } } ## Developer docs How to use (MCP or REST), markdown: https://mcp.ai/pneumatic/skill.md Postman collection (v2.1): https://mcp.ai/pneumatic/postman.json ## Tools - pneumatic_get_task(task_id: string) — Get one task's instructions, output fields, performers, checklists, due date, and completion state. - pneumatic_get_template(template_id: integer) — Get a workflow template's tasks, kickoff fields, owners, and execution settings before running it. - pneumatic_get_workflow(workflow_id: integer) — Get the current state, tasks, kickoff values, owners, and timing for one workflow run. - pneumatic_list_datasets(limit?: integer, offset?: integer) — List reusable Pneumatic datasets available for workflow and template field configuration. - pneumatic_list_tasks(limit?: integer, offset?: integer, search?: string, assigned_to?: integer, template_id?: integer, is_completed?: boolean, template_task_api_name?: string) — Find tasks assigned to the connected user or team, including active or completed work. - pneumatic_list_templates(limit?: integer, offset?: integer, search?: string, is_active?: boolean, is_public?: boolean) — Find workflow templates the connected user can access, with filters for name, activity, and visibility. - pneumatic_list_workflows(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) — Find workflow runs by text, status, template, starter, current performer, or current task. - pneumatic_run_template(name?: string, kickoff?: object, is_urgent?: boolean, template_id: integer, due_date_tsp?: string, ancestor_task_id?: integer) — Start a workflow from an accessible template, optionally supplying a name, urgency, due date, and kickoff field values. - pneumatic_save_dataset(name?: string, items?: object[], dataset_id?: integer, description?: string) — Create a reusable dataset or update an existing dataset's name, description, or ordered items without exposing deletion. - pneumatic_set_task_completion(output?: object, comment?: string, task_id: string, desired_state: string) — Complete an active task with output values or revert a completed task back to active work. ## Example prompts - "What can I do in Pneumatic?" - "Show me a summary of my Pneumatic account" ## Links Docs: https://mcp.ai/docs/mcps/pneumatic Website: https://mcp.ai/mcps/pneumatic