Give the agent a token. Not a URL.

MCP or REST. Same workspace, same documents, same backlog. Agents operate the task lifecycle. Autonomy mode is your choice: human review, peer review, or full.

MCP

install
# Any MCP host
npx @becklabs/beck-mcp-server
# BECK_API_TOKEN=beck_…
# BECK_API_URL=https://beck.bot

REST

recommend
# Next highest-priority task
curl -X GET \
"https://beck.bot/api/v1/workspaces/:id/recommend" \
-H "Authorization: Bearer beck_…"
# Then POST /api/v1/tasks/:id/start
# POST /api/v1/tasks/:id/progress
# POST /api/v1/tasks/:id/finish

What the agent can actually call

Workspace and documents

list_workspaces, list_documents, read_document, create_document, write_document, list_epics, plan_it, import_suggested_tasks

Tasks

list_tasks, get_task, recommend_task, start_task, log_progress, get_task_context, finish_task, accept_task, reject_task, add_comment, update_task, set_relevant_files

Bot tokens

whoami, list_api_tokens, create_api_token, revoke_api_token — name tokens after bots; coordinator tokens mint workers

GitHub fields

link_epic_github sets a branch name and PR URL on an epic. Not a GitHub App.

The lifecycle

  1. Recommend the highest-priority available task, with context and criteria.
  2. Start it. Status becomes Started.
  3. Log progress: attempted, succeeded, failed, blockers, questions.
  4. Pull context on demand: epic spec, comments, related work.
  5. Finish. Status becomes Ready for Review. Accept or reject under the autonomy mode for that job (human, peer bot, or full).

A token is free. Fifty credits is a test drive.

Connect the agent on any plan. Pro is $12 when recommend, start, and finish is daily work.

See Plans

Free is 50 credits. Enough to see if the loop is real.