SKV Network MCP server

• Registry namenetwork.skv/skvverified in the MCP registry

The registry name sits under skv.network. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

• Stateanswerschecked 2026-10-31
• Tools27
• Server calls itselfskv-memory
• Server version1.30.0
• Protocol version2025-06-18

On 2026-10-31 the server answered initialize and tools/list without a sign-in. First answer in 568 ms.

• Its tools do every use case we checked: 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.
• Checked on 3 of the 7 days it takes to judge reliability.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

• INITE MCP scoreafter a weeka score needs 7 daily checks: 3 so far
• What an agent can do with it3 of 3 use cases
• Answeredmeasuring3 of the 7 daily checks it takes to print a share
• Median first answer756 ms
• Space in an agent's context≈ 3,498 tokensthe definitions of all its tools (28), which an agent carries on every turn
• Tool definitionsC · 67 of 100
• Typed results0 of 28 toolsdeclared outputSchema: results come typed, read once

• No description an agent can choose by: 1 of 28
• Parameters without a description: in 26 of 28
• Not saying whether it only reads or can destroy: 28 of 28

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

• 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.