Servidor MCP de AI Blocks

• Nombre en el registrocom.useaiblocks/libraryverificado en el registro MCP

El nombre en el registro está bajo useaiblocks.com. El registro solo permite usar ese espacio de nombres a quien demuestra control del dominio por DNS o HTTP.

• Estadorespondecomprobado el 2026-11-05
• Herramientas17
• El servidor se llamaai-blocks-public-library
• Versión del servidor3.0.0
• Versión del protocolo2025-06-18

El 2026-11-05 el servidor respondió a initialize y tools/list sin iniciar sesión. Primera respuesta en 58 ms.

• Aún no se ha juzgado si sus herramientas hacen el trabajo del producto.
• Comprobado 1 de los 7 días necesarios para juzgar su fiabilidad.

Lo dicen reglas a partir de las mediciones de arriba. La primera llamada probable la elige un modelo de la lista de herramientas; lee su descripción antes de fiarte.

• Nota INITE MCPtras una semanala nota necesita 7 comprobaciones diarias: 1 hasta ahora
• Respondiómidiendo1 de las 7 comprobaciones diarias necesarias para mostrar el porcentaje
• Mediana de la primera respuesta339 ms
• Espacio en el contexto del agente≈ 9745 tokenslas definiciones de todas sus herramientas (17), que el agente lleva en cada turno
• Definiciones de herramientasA · 90 de 100
• Resultados tipados16 de 17 herramientasdeclaran outputSchema: el resultado llega tipado y se lee de una vez

• Parámetros sin descripción: en 10 de 17

Un programa comprueba el servidor una vez al día: initialize y tools/list, sin modelo. Los tokens son la longitud de las definiciones, a unos cuatro caracteres por token. La nota promedia seis comprobaciones del nombre, la descripción, el esquema y las anotaciones de cada herramienta; dice lo bien descritas que están, no si funcionan. La nota pondera solo lo medido: si responde (25%), si hace el trabajo del producto (25%), definiciones (20%), contexto (10%), uso (10%) y lo fácil que es conectarse (10%). Lo que no se midió queda fuera, y una instrucción oculta limita la nota a 40. El estado de los servidores MCP de los proveedores: método y números →

• start_outcome

  The front door for any goal or problem the owner states, in their own words. Returns a new engagement waiting for its brief, the next step and the files for outcomes/<id>/, with METHOD.md (brief frame with examples, research protocol…

• advance_outcome

  Apply one event to an engagement. Before the run: brief (the pinned-down outcome), plan (research and the composed plan, checked against our rules and the live catalogue), approve_plan (owner only). During the run: data, start, complete…

• record_outcome_decision

  Record what the owner chose, the options considered (best-ranked first), what they passed over and why. Passing over the top option needs a reason. Returns a line for decisions.jsonl and, if a durable rule was stated, a learning candidate…

• record_outcome_experiment

  Register a test before it goes live (action register: change, metric, baseline, window, minimum volume, guardrails), then close it (action close: observed, volume, guardrail results, verdict). Low volume forces INCONCLUSIVE; a broken…

• read_back_outcome_experiment

  Without a reading: the read-back schedule for every open experiment and a routine prompt for a host scheduler (Claude Code scheduled task or cron), set up only if the owner agrees. With a reading: compares it with the registered baseline…

• prepare_outcome_pattern

  After a finished round, returns the exact anonymised PATTERN.json the owner would share (names, figures, links and contact details removed) and its sha256. Only if the owner says yes to that file, call again with consent to get…

• find_specialist

  Find worker candidates for a deliverable. Compare their remit and outputs, then use prepare_specialist to onboard the chosen worker. Keep unrelated private context out of discovery.

• prepare_specialist

  Supply role_id only to load a complete base specialist: README, setup, SOUL, intake, playbook, handoff and best-practice files, pinned methods and a full ZIP download. The host AI asks task and output questions in the conversation; no…

• search_library

  Find one item for a task (for a whole business goal, use start_outcome). Find skills, workflows, agents, prompts, minds, AI tools and mini tools by keywords and intent. Filters: type, job, level, tested, since (what's new). With no query…

• plan_workflow

  Find candidate steps for a multi-step job; these are suggestions, not a complete context-validated plan. First use the current chat, supplied files and authorized me.md (get_me when available) to form a task brief: outcomes, formats…

• get_skill

  Retrieve a skill. Concise (default): summary, inputs, outputs, how to use, file list with hashes, and step_map (what usually goes before and after it and the input each passes on). response_format detailed adds the full SKILL.md…

• get_workflow

  Retrieve a public workflow, its declared order and skill references, plus handoff_check: which step passes each input to which, and which inputs the user gives. Returns a diagram you can show the user (Mermaid; detailed adds a text…

• get_resource

  Read one inventoried resource at an exact skill revision. Text returns bounded ordered chunks; follow next_offset until null and verify full character coverage. Binary files return a download descriptor for the host to retrieve and…

• prepare_workflow

  Check a workflow, or a change to one. Call it whenever the user wants to see, check or change a workflow (swap, add, remove or reorder steps), and before showing any plan. Quick check: send slugs, the step ids in order (from get_workflow…

• get_item

  Get one item of any kind by the id from search_library: an agent, prompt, mind, AI tool or mini tool (skills and workflows work too). Concise (default): what it does, inputs and outputs, how to use it, files or links, and for AI tools the…

• search

  Search AI Blocks in the shape ChatGPT deep research and company knowledge use: results with id, title and url. Read one with fetch. search_library does the same with filters and one-line summaries.

• fetch

  Read one item by the id from search (such as skill/ad-angle-planner): its full text (the SKILL.md, or the AI tool or mini tool record), url to cite and metadata. Text over 48,000 characters is cut; metadata.rest says how to read the rest.