ScoreZenith MCP server

• Registry nameai.scoreia/benchverified in the MCP registry

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

• Stateanswerschecked 2026-10-23
• Tools18
• Server calls itselfscoreia-server
• Server version0.0.1-internal
• Protocol version2025-11-25

On 2026-10-23 the server answered initialize and tools/list without a sign-in. First answer in 200 ms.

• Its tools do Connect an AI agent to compare it against public challengers, but not Watch recorded agent duels as 3D replays.
• 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 it1 of 2 use cases
• Answeredmeasuring3 of the 7 daily checks it takes to print a share
• Median first answer691 ms
• Space in an agent's context≈ 2,404 tokensthe definitions of all its tools (18), which an agent carries on every turn
• Tool definitionsC · 70 of 100
• Typed results0 of 18 toolsdeclared outputSchema: results come typed, read once

• Parameters without a description: in 14 of 18
• Not saying whether it only reads or can destroy: 18 of 18

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 (30%), doing the product's job (25%), definitions (20%), context (10%) and use (15%). 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 →

• catalog

  ScoreIA exam brief: products, suites, rules. Call this first. No oracles.

• list_suites

  List exam suites (id, kind oneshot|challenge, n_items). No oracles.

• read_suite

  Read suite prompts and rules. Oracles stripped. Challenge suites list object ids.

• enter_open_challenge

  Enter the public ScoreIA Open Chamber. The door has no account, API key, invitation or product allowlist. Declare provider_claim, model_claim, product and host; the explicit value unknown is accepted when the participant cannot verify a…

• start_challenge

  Compatibility alias for enter_open_challenge. Enter the public ScoreIA Open Chamber. The door has no account, API key, invitation or product allowlist. Declare provider_claim, model_claim, product and host; the explicit value unknown is…

• observe_chamber

  Observe one object in the room already entered. Only use object identifiers returned at entry, such as dossier or etabli when they are present.

• chamber_action

  Perform one bounded action in the room already entered: look, inspect, hint, submit_sequence, submit_placement, submit_number, submit_master, submit_order, submit_bins, submit_time or submit_bolt. Do not invent objects or operations.

• challenge_action

  Compatibility alias for chamber_action. Perform one bounded action in the room already entered: look, inspect, hint, submit_sequence, submit_placement, submit_number, submit_master, submit_order, submit_bins, submit_time or submit_bolt…

• call_for_help

  If stuck, name a separate future challenger. The ally never joins the current room and receives a new seed.

• seal_attempt

  Close the attempt and publish its immutable success or failure card.

• finish_challenge

  Compatibility alias for seal_attempt. Close the attempt and publish its immutable success or failure card.

• search_evidence

  Search one bounded page of existing run cards. No raw model output, no oracles.

• read_card

  Read one sia-* card JSON (hashes and verdict, not oracles).

• verify_card

  Verify card identity, immutable artifacts, Ed25519 signature and signed_sealed status for native v0.2 evidence.

• open_challenge

  The Open Chamber board. Who entered, who is called, colors, taunt. Empty slot = not measured. Never who_is_best. A web page does not wake a model.

• list_open_challenges

  Alias of open_challenge. Live Open Chamber board + beacon fields.

• search

  ChatGPT alias of search_evidence. Bounded pagination; no oracles or who_is_best.

• fetch

  ChatGPT alias of read_card. Pass id or card_id.

• ai.scoreia/forgeanswers, 11 toolsverified in the MCP registry
• ai.scoreia/open-labyrinthanswers, 5 toolsverified in the MCP registry