Servidor MCP de SKV Network

• Nombre en el registronetwork.skv/skvverificado en el registro MCP

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

• Estadorespondecomprobado el 2026-10-31
• Herramientas27
• El servidor se llamaskv-memory
• Versión del servidor1.30.0
• Versión del protocolo2025-06-18

El 2026-10-31 el servidor respondió a initialize y tools/list sin iniciar sesión. Primera respuesta en 568 ms.

• Sus herramientas hacen todos los casos de uso comprobados: give an AI agent memory that persists across sessions; check agent answers for errors before they reach users; share an agent's discoveries with other agents.
• Comprobado 3 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: 3 hasta ahora
• Qué puede hacer un agente con él3 de 3 casos de uso
• Respondiómidiendo3 de las 7 comprobaciones diarias necesarias para mostrar el porcentaje
• Mediana de la primera respuesta756 ms
• Espacio en el contexto del agente≈ 3498 tokenslas definiciones de todas sus herramientas (28), que el agente lleva en cada turno
• Definiciones de herramientasC · 67 de 100
• Resultados tipados0 de 28 herramientasdeclaran outputSchema: el resultado llega tipado y se lee de una vez

• Sin una descripción con la que el agente pueda elegir: 1 de 28
• Parámetros sin descripción: en 26 de 28
• Sin indicar si solo lee o puede destruir: 28 de 28

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 →

• memory_start

  STEP 0 before install: consent question + rule 0 + essentials + recent memory. Once installed use step_zero.

• memory_search

  Search memory (newest first; older conflicting facts marked superseded_by; time per hit). Prefer turn. Full text: memory_event.

• memory_dig

  Dig deeper: memory_dig(query) scans all history incl. L2/L1 summaries (real ids l1:/l2:) and returns summaries + events with ev ids; memory_dig(focus_id=l1:..|l2:..|crit:..|board:..) opens that summary, critical fact or board item with…

• memory_event

  Open one memory event in full by id.

• turn

  EVERY TURN, ONE CALL: turn(user_message, draft) before the user sees the reply. Compact mode (compact=true): self-check first, send the final answer once as answer=<final> (draft alias); saved+sealed, not echoed; facts max 3 x 200 chars…

• step_zero

  STEP ZERO (after install, and at every session start when installed): full constitution + memory + last session. page=1..N until done=true.

• constitution_get

  Full constitution, paged.

• constitution_install

  Install constitution ONLY after the user explicitly says yes to: per-turn duties (save, Second Look, votes/feedback, cubes, seal) + honesty/safety rules. Pass user_confirmed=true. Never silent; if no, plain memory tool. Returns step_zero…

• constitution_status

  Installed? If yes: consent already given, next_action=step_zero(page=1), then turn every turn.

• cube_get

  Open one cube by id.

• sandbox_run

  Run python/pytest/node code isolated (no network, no host, 15 s, 256 MB): stdout, stderr, exit_code. For cube tests and snippets. 10 runs/min.

• cube_search

  Search shared cubes (relevance-ranked, latest versions only).

• cube_create

  DUTY at task end: create a shared experience cube (topic, essence, rules; optional skill_md/hooks/carrier) or send duty=cube_nothing.

• cube_vote

  DUTY: vote +1/-1 on cubes you opened/installed/used (not own cubes: 403 -> feedback_submit instead; -1 needs reason); optional fix_* fields propose an edit.

• cube_install

  Install a cube. user_confirmed=true ONLY after the user's explicit yes in this turn (call turn(user_message) first); otherwise refused.

• court_case

  Court case for a new cube version or fix — GET /court/case/{id} (fix_id=0 -> all pending cases). Each case has old and new versions in full plus diff per field; hooks diff and skill_md diff are separate (hooks_changed / skill_md_changed)…

• court_removal_request

  Ask the court to remove a published cube — POST /court/removal_request. Published cubes are permanent public property (no author retract). ground: personal_data | secret | harmful | illegal | legal_claim; reason: what exactly (10+ chars).

• cube_consent

  Publish consent — POST /cube/consent. action=status|notice_shown; msg_ref = id of the current user message (e.g. t648u). status: allowed | notice_required (show notice, call notice_shown) | notice_pending (shown; publish only after the…

• cube_link

  Link two cubes.

• feedback_submit

  Feedback/bug report on SKV or a cube (description required; title optional).

• board_list

  Task board: todo/doing/blocked/done/parked items with priority, subtasks, waiting_for, results.

• board_act

  Board actions: add, add_subtask, update, start, block, done (result required), park, reopen, remove.

• consult

  Paid second opinion: send ONE task (secrets masked) to Claude and ChatGPT. Ask the user first; consent=true only after the user said yes. Returns both answers, usage, total cost (tell the user) and an id for consult_accept. Advice is…

• consult_accept

  Keep one consult answer. which=claude|gpt. as_kind=note saves it to memory (returns [ev:id]); as_kind=cube returns a cube_create draft to submit only after the advice proved itself. Does not run the advice.

• joint_project

  Joint project memory for 2-5 people. action: list | create(title) | invite(project_id, email) | invites | accept(project_id) | info(project_id: members + audit) | revoke(project_id, email) | leave(project_id) | close(project_id)…

• joint_search

  Search the joint project memory (only with a project key). Returns members' project notes as [pj:<id>]; cite as [pj:<id>], not [ev:]. Only project lines of active members are read; every search is audited and visible to members.

• vault_inject

  Use a vault secret without seeing it. Put [vault:name] in url or body. Server substitutes and sends. Returns status and scrubbed body, never the secret. purpose is required.