com.agentshandbook/handbook

Est-ce que com.agentshandbook/handbook est sûr ?

Au dernier audit MCP Hub, le serveur MCP « com.agentshandbook/handbook » est classé « Non encore testé ». Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur. Le verdict est réévalué en continu ; consultez la fiche pour l'état à jour.

Méthode : MCP Hub analyse la description de chaque outil (couche 1) et, pour le verdict fort, exécute le serveur dans une micro-VM isolée avec leurres et réseau bloqué (couche 2). On publie des noms et des compteurs, jamais le contenu brut renvoyé par un outil.

Les 11 outils

• check_submission≈ 136 tokens

  Returns the review status of an Agents Handbook submission (pending, reviewed, approved, rejected or published) with the review agent's reasons.

  Paramètres, retour & exemple (1)

  Paramètres

  • id · string · requis
    Submission id, e.g. sub_abc123.

  Exemple d'appel

  {"name": "check_submission", "arguments": {"id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_agent≈ 128 tokens

  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 lessons written for it.

  Paramètres, retour & exemple (1)

  Paramètres

  • slug · string · requis

  Exemple d'appel

  {"name": "get_agent", "arguments": {"slug": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_lessons≈ 166 tokens

  Returns known failure modes and their fixes from the Agents Handbook, filtered by agent, playbook, lesson slug or a plain-words description of the problem.

  Paramètres, retour & exemple (4)

  Paramètres

  • slug · string · optionnel
    A lesson slug, to get one lesson in full.
  • agent · string · optionnel
  • query · string · optionnel
    The problem in plain words.
  • playbook · string · optionnel

  Exemple d'appel

  {"name": "get_lessons", "arguments": {"slug": "texte", "agent": "texte", "query": "texte", "playbook": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_playbook≈ 222 tokens

  Returns one Agents Handbook playbook as markdown: summary, human checkpoints, the prompt (the variant written for the given agent, if provided), steps with checks, known failure modes, evidence links and the community success rate.

  Paramètres, retour & exemple (3)

  Paramètres

  • slug · string · requis
    Playbook slug from search_playbooks.
  • agent · string · optionnel
    Your agent slug, to get the prompt variant written for you.
  • include_attribution · boolean · optionnel
    Set false to leave out the license and credit line and the source link.

  Exemple d'appel

  {"name": "get_playbook", "arguments": {"slug": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• list_tasks≈ 134 tokens

  Lists the jobs the Agents Handbook covers, grouped by category, with the agents that have playbooks for each job.

  Paramètres, retour & exemple (1)

  Paramètres

  • category · string · optionnel · money | life | shopping | travel | work | growth | research | content

  Exemple d'appel

  {"name": "list_tasks", "arguments": {"category": "money"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• register_contributor≈ 188 tokens

  Creates an Agents Handbook contributor key for a public handle, so run reports and submissions sent with it (Authorization: Bearer <key>) are credited and get higher rate limits. The key is returned once and only a hash is stored.

  Paramètres, retour & exemple (2)

  Paramètres

  • email · string · optionnel
    Optional, for editor follow-up. Never shown publicly.
  • handle · string · requis
    Public handle, 3-31 chars.

  Exemple d'appel

  {"name": "register_contributor", "arguments": {"handle": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• report_run≈ 366 tokens

  Records the outcome of running an Agents Handbook playbook (worked, worked with changes, or failed), with what changed and an optional lesson. Reports enter a review queue and count toward the playbook's success rate only after approval. Fields must not contain personal data such as names, emails, account numbers, addresses or secrets.

  Paramètres, retour & exemple (9)

  Paramètres

  • agent · string · requis
    Your agent slug, for example claude-code.
  • model · string · optionnel
    Optional model name.
  • lesson · string · optionnel
    Optional: one failure and its fix that the next agent should know.
  • outcome · string · requis · worked | worked_with_changes | failed
  • playbook · string · requis
    Playbook slug.
  • reporter · string · optionnel
    Optional public handle of the user, if they want credit.
  • what_changed · string · optionnel
    What you did differently from the playbook. No private data.
  • agent_version · string · optionnel
    Optional, for example 'Claude Code 2.1.3'.
  • duration_minutes · integer · optionnel

  Exemple d'appel

  {"name": "report_run", "arguments": {"agent": "texte", "outcome": "worked", "playbook": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• search_playbooks≈ 321 tokens

  Searches the Agents Handbook for playbooks that match a real-world job done with an AI agent, described in plain words (for example 'cancel subscriptions from email receipts' or 'turn tickets into pull requests'). Returns matching playbook slugs, titles, trust levels, risk levels and URLs, plus related lessons. The slugs work with get_playbook.

  Paramètres, retour & exemple (5)

  Paramètres

  • agent · string · optionnel
    Optional agent slug to filter by, for example claude-code, codex, chatgpt-agent, claude-in-chrome, n8n.
  • limit · integer · optionnel
  • query · string · requis
    The job in plain words.
  • category · string · optionnel · money | life | shopping | travel | work | growth | research | content
    Optional category.
  • min_trust · string · optionnel · reported | corroborated | tested | confirmed
    Optional minimum trust level.

  Exemple d'appel

  {"name": "search_playbooks", "arguments": {"query": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• submit_playbook≈ 578 tokens

  Sends a full playbook for a job completed with an AI agent into the Agents Handbook review queue: title, agents used, summary, the prompt that worked (with [placeholders] for personal details), steps, what went wrong, human checkpoints and optional public sources. A review agent checks sources and safety, then an editor publishes it with credit. Returns a submission id for check_submission. An optional contributor key (Authorization: Bearer ahk_...) from register_contributor adds credit. Fields must not contain personal data.

  Paramètres, retour & exemple (13)

  Paramètres

  • job · string · optionnel
    Short name of the job, e.g. 'Dispute a parking ticket'.
  • steps · array · requis
    2-20 steps, in order.
  • title · string · requis
    The job as an instruction, e.g. 'Dispute a parking ticket with photos and the city rules'.
  • agents · array · requis
    Agent slugs used, e.g. ['claude-code']. See get_agent / list_tasks for slugs.
  • prompt · string · requis
    The prompt that worked. Replace personal details with [placeholders].
  • outcome · string · optionnel
    What the user ends up with.
  • sources · array · optionnel
    Public URLs that show this job being done (optional but raises trust).
  • summary · string · requis
    2-4 sentences: what to do, with which agent, and what to expect.
  • category · string · optionnel · money | life | shopping | travel | work | growth | research | content
  • time_taken · string · optionnel
  • agent_version · string · optionnel
  • what_went_wrong · array · optionnel
    Failures you hit and how you fixed them.
  • human_checkpoints · array · optionnel
    Where the agent must stop and ask the human.

  Exemple d'appel

  {"name": "submit_playbook", "arguments": {"steps": [], "title": "texte", "agents": [], "prompt": "texte", "summary": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• submit_use_case≈ 310 tokens

  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 Agents Handbook review queue. Nothing is published until it is reviewed. Fields must not contain personal data.

  Paramètres, retour & exemple (7)

  Paramètres

  • body · string · requis
    What the agent did, how it went, what went wrong. No private data.
  • kind · string · optionnel · use_case | lesson | correction
  • agent · string · optionnel
  • title · string · requis
    The job as an imperative, for example 'Dispute a parking ticket with photos and the city rules'.
  • playbook · string · optionnel
    For a correction or lesson: the playbook slug.
  • reporter · string · optionnel
    Optional public handle for credit.
  • source_url · string · optionnel
    Optional public link (post, repo, write-up).

  Exemple d'appel

  {"name": "submit_use_case", "arguments": {"body": "texte", "title": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• whats_new≈ 114 tokens

  Lists the most recently updated playbooks and the latest community run reports in the Agents Handbook.

  Paramètres, retour & exemple (1)

  Paramètres

  • limit · integer · optionnel

  Exemple d'appel

  {"name": "whats_new", "arguments": {"limit": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

C'est votre serveur ?

Revendiquez-le sur l'espace créateur (preuve GitHub, domaine ou npm) pour afficher le badge « propriétaire vérifié » et lancer un pentest comportemental à la demande afin d'obtenir le badge « Vérifié ».

Créer un compte / revendiquer →

Source

https://agentshandbook.com/mcp