Categories › AI & Agents › Multi-agent, orchestration & workflows
Sourced playbooks for real jobs done with AI agents: search, read, lessons, report runs.
Remote server: your requests and data go to agentshandbook.com. Claude Code: claude mcp add --transport http agents-handbook https://agentshandbook.com/mcp · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
search_playbooks — Searches the Agents Handbook for playbooks that match a real-world job done with an AI agent, described in plain words (for example 'cancel get_playbook — Returns one Agents Handbook playbook as markdown: summary, human checkpoints, the prompt (the variant written for the given agent, if providlist_tasks — Lists the jobs the Agents Handbook covers, grouped by category, with the agents that have playbooks for each job.get_agent — Returns an agent profile from the Agents Handbook: what the agent is good at, its limits, how it connects to tools, and the playbooks and leget_lessons — Returns known failure modes and their fixes from the Agents Handbook, filtered by agent, playbook, lesson slug or a plain-words description whats_new — Lists the most recently updated playbooks and the latest community run reports in the Agents Handbook.report_run — Records the outcome of running an Agents Handbook playbook (worked, worked with changes, or failed), with what changed and an optional lessosubmit_use_case — Sends a short use case (a job done with an agent that has no playbook yet), a lesson, or a correction to an existing playbook into the Agentsubmit_playbook — Sends a full playbook for a job completed with an AI agent into the Agents Handbook review queue: title, agents used, summary, the prompt thcheck_submission — Returns the review status of an Agents Handbook submission (pending, reviewed, approved, rejected or published) with the review agent's reasregister_contributor — Creates an Agents Handbook contributor key for a public handle, so run reports and submissions sent with it (Authorization: Bearer <key>) arNot tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.