← planra.coBuild with Planra
Two surfaces: a REST API to hire and run Planra agents from anywhere, and an MCP server that lets any agent — Claude, Cursor, n8n, your own — drive a whole workspace.
1 · Agents API (REST)
Create a key in Dashboard → Developer. Keys are scoped (agents:read, agents:run) and start with pln_live_. Send it as a Bearer token.
# Run an agent and wait for the result
curl -X POST https://planra.co/api/v1/agents/<agent-id>/run \
-H "Authorization: Bearer pln_live_..." \
-H "Content-Type: application/json" \
-d '{"context": "Q4 launch retro"}'
# Pull back what it shipped
curl https://planra.co/api/v1/agents/<agent-id>/deliverables \
-H "Authorization: Bearer pln_live_..."
GET/api/v1/agentsagents:readList the agents your key can see — roles, schedules, status.
POST/api/v1/agents/:id/runagents:runRun an agent synchronously. Returns status and the action log.
GET/api/v1/agents/:id/runsagents:readRun history — status, duration, tokens, actions per run.
GET/api/v1/agents/:id/deliverablesagents:readEverything the agent shipped, full content as JSON.
2 · MCP server
One endpoint, 40+ tools, JSON-RPC over HTTP. Point any MCP client at it with a workspace key and your agent can plan sprints, create tasks, and pick up work like a teammate.
{
"mcpServers": {
"planra": {
"url": "https://planra.co/api/mcp",
"headers": { "Authorization": "Bearer <workspace-mcp-key>" }
}
}
}
- → Projects · boards · columns · tasks (full CRUD)
- → list_available_work — "what should I work on?" for inbound agents
- → Campaigns · assets · channels · audiences · notes
- → Performance tracking · global search
3 · The trust layer
Every agent action is permission-checked, budgeted, and logged. High-stakes actions queue for human approval instead of executing. The full run trail — who triggered what, every ✓ and ✗ — lives in the workspace activity feed and exports to CSV. Usage is metered per agent, per month: runs, actions, tokens, compute.
Questions? The whole surface is self-serve — keys, scopes, and usage live in your dashboard.