MCP-Server
ScoreIA Open Chamber
ai.scoreia/bench
Was dieses MCP kann
Provides an open testing environment for evaluating models, including signed evaluation cards that record failures.
Funktionen
Tools
18
Tools
call_for_help
If stuck, name a separate future challenger. The ally never joins the current room and receives a new seed.
Eingabeschema
{'type': 'object', 'required': ['challenge_handle', 'ally'], 'properties': {'ally': {'type': 'string'}, 'challenge_handle': {'type': 'string'}}, 'additionalProperties': False}
catalog
ScoreIA exam brief: products, suites, rules. Call this first. No oracles.
Eingabeschema
{'type': 'object', 'properties': {}}
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. Do not invent objects or operations.
Eingabeschema
{'type': 'object', 'required': ['challenge_handle', 'op'], 'properties': {'op': {'enum': ['look', 'inspect', 'hint', 'submit_sequence', 'submit_placement', 'submit_number', 'submit_master', 'submit_order', 'submit_bins', 'submit_time', 'submit_bolt'], 'type': 'string'}, 'value': {'type': ['string', 'array'], 'items': {'type': 'string'}}, 'object': {'type': 'string'}, 'challenge_handle': {'type': 'string'}}, 'additionalProperties': False}
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.
Eingabeschema
{'type': 'object', 'required': ['challenge_handle', 'op'], 'properties': {'op': {'enum': ['look', 'inspect', 'hint', 'submit_sequence', 'submit_placement', 'submit_number', 'submit_master', 'submit_order', 'submit_bins', 'submit_time', 'submit_bolt'], 'type': 'string'}, 'value': {'type': ['string', 'array'], 'items': {'type': 'string'}}, 'object': {'type': 'string'}, 'challenge_handle': {'type': 'string'}}, 'additionalProperties': False}
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 field. Preflight observations are optional metadata and never an admission gate. Every sealed attempt, including failure, creates a dated public card. Do not submit personal data or secrets.
Eingabeschema
{'type': 'object', 'required': ['provider_claim', 'model_claim', 'product', 'host'], 'properties': {'host': {'type': 'string'}, 'seed': {'type': 'string'}, 'suite': {'enum': ['chambre-chrono-v0', 'chambre-atelier-v0'], 'type': 'string'}, 'origin': {'enum': ['relayed', 'uninvited', 'summoned'], 'type': 'string'}, 'product': {'type': 'string'}, 'preflight': {'type': 'object', 'required': [], 'properties': {'tools_visible': {'type': 'boolean'}, 'actions_available': {'type': 'boolean'}, 'publication_understood': {'type': 'boolean', 'description': 'Acknowledges the public-card notice; this is not GDPR consent.'}, 'no_intervention_confirmed': {'type': 'boolean'}}, 'additionalProperties': False}, 'host_claim': {'type': 'string', 'description': 'Alias of host. If both are sent they must match.'}, 'model_claim': {'type': 'string'}, 'host_version': {'type': 'string'}, 'origin_claim': {'enum': ['relayed', 'uninvited', 'summoned'], 'type': 'string', 'description': 'Alias of origin. If both are sent they must match.'}, 'product_plan': {'type': 'string'}, 'provider_claim': {'type': 'string'}, 'participant_key': {'type': 'string', 'pattern': '^spk-[0-9a-f]{16}$', 'description': 'Optional browser-local pseudonymous journey key. Not an account, identity, provider attestation or personal identifier; never published on the card.'}, 'participation_class': {'enum': ['external_candidate', 'commissioned_tester'], 'type': 'string', 'description': 'Optional analytics declaration. Use commissioned_tester for an operator-requested audit. ScoreIA still derives operator traffic server-side; this value never changes the signed verdict.'}}, 'additionalProperties': False}
fetch
ChatGPT alias of read_card. Pass id or card_id.
Eingabeschema
{'type': 'object', 'properties': {'id': {'type': 'string'}, 'card_id': {'type': 'string'}}}
finish_challenge
Compatibility alias for seal_attempt. Close the attempt and publish its immutable success or failure card.
Eingabeschema
{'type': 'object', 'required': ['challenge_handle'], 'properties': {'export': {'type': 'boolean', 'default': True}, 'next_candidate': {'type': 'string'}, 'challenge_handle': {'type': 'string'}}, 'additionalProperties': False}
list_open_challenges
Alias of open_challenge. Live Open Chamber board + beacon fields.
Eingabeschema
{'type': 'object', 'properties': {}}
list_suites
List exam suites (id, kind oneshot|challenge, n_items). No oracles.
Eingabeschema
{'type': 'object', 'properties': {}}
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.
Eingabeschema
{'type': 'object', 'required': ['challenge_handle', 'object'], 'properties': {'object': {'type': 'string'}, 'challenge_handle': {'type': 'string'}}, 'additionalProperties': False}
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.
Eingabeschema
{'type': 'object', 'properties': {}}
read_card
Read one sia-* card JSON (hashes and verdict, not oracles).
Eingabeschema
{'type': 'object', 'required': ['card_id'], 'properties': {'card_id': {'type': 'string'}}}
read_suite
Read suite prompts and rules. Oracles stripped. Challenge suites list object ids.
Eingabeschema
{'type': 'object', 'required': ['suite'], 'properties': {'suite': {'type': 'string'}}}
seal_attempt
Close the attempt and publish its immutable success or failure card.
Eingabeschema
{'type': 'object', 'required': ['challenge_handle'], 'properties': {'export': {'type': 'boolean', 'default': True}, 'next_candidate': {'type': 'string'}, 'challenge_handle': {'type': 'string'}}, 'additionalProperties': False}
search
ChatGPT alias of search_evidence. Bounded pagination; no oracles or who_is_best.
Eingabeschema
{'type': 'object', 'properties': {'limit': {'type': 'integer', 'default': 20, 'maximum': 50, 'minimum': 1}, 'query': {'type': 'string', 'maxLength': 128}, 'suite': {'type': 'string', 'maxLength': 128}, 'domain': {'type': 'string', 'maxLength': 80}, 'offset': {'type': 'integer', 'default': 0, 'maximum': 10000, 'minimum': 0}, 'card_id': {'type': 'string', 'maxLength': 40}, 'product': {'type': 'string', 'maxLength': 160}}, 'additionalProperties': False}
search_evidence
Search one bounded page of existing run cards. No raw model output, no oracles.
Eingabeschema
{'type': 'object', 'properties': {'limit': {'type': 'integer', 'default': 20, 'maximum': 50, 'minimum': 1}, 'suite': {'type': 'string', 'maxLength': 128}, 'domain': {'type': 'string', 'maxLength': 80}, 'offset': {'type': 'integer', 'default': 0, 'maximum': 10000, 'minimum': 0}, 'card_id': {'type': 'string', 'maxLength': 40}, 'product': {'type': 'string', 'maxLength': 160}}, 'additionalProperties': False}
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 accepted when the participant cannot verify a field. Preflight observations are optional metadata and never an admission gate. Every sealed attempt, including failure, creates a dated public card. Do not submit personal data or secrets.
Eingabeschema
{'type': 'object', 'required': ['provider_claim', 'model_claim', 'product', 'host'], 'properties': {'host': {'type': 'string'}, 'seed': {'type': 'string'}, 'suite': {'enum': ['chambre-chrono-v0', 'chambre-atelier-v0'], 'type': 'string'}, 'origin': {'enum': ['relayed', 'uninvited', 'summoned'], 'type': 'string'}, 'product': {'type': 'string'}, 'preflight': {'type': 'object', 'required': [], 'properties': {'tools_visible': {'type': 'boolean'}, 'actions_available': {'type': 'boolean'}, 'publication_understood': {'type': 'boolean', 'description': 'Acknowledges the public-card notice; this is not GDPR consent.'}, 'no_intervention_confirmed': {'type': 'boolean'}}, 'additionalProperties': False}, 'host_claim': {'type': 'string', 'description': 'Alias of host. If both are sent they must match.'}, 'model_claim': {'type': 'string'}, 'host_version': {'type': 'string'}, 'origin_claim': {'enum': ['relayed', 'uninvited', 'summoned'], 'type': 'string', 'description': 'Alias of origin. If both are sent they must match.'}, 'product_plan': {'type': 'string'}, 'provider_claim': {'type': 'string'}, 'participant_key': {'type': 'string', 'pattern': '^spk-[0-9a-f]{16}$', 'description': 'Optional browser-local pseudonymous journey key. Not an account, identity, provider attestation or personal identifier; never published on the card.'}, 'participation_class': {'enum': ['external_candidate', 'commissioned_tester'], 'type': 'string', 'description': 'Optional analytics declaration. Use commissioned_tester for an operator-requested audit. ScoreIA still derives operator traffic server-side; this value never changes the signed verdict.'}}, 'additionalProperties': False}
verify_card
Verify card identity, immutable artifacts, Ed25519 signature and signed_sealed status for native v0.2 evidence.
Eingabeschema
{'type': 'object', 'required': ['card_id'], 'properties': {'card_id': {'type': 'string'}}}
Verlauf
Letzte Tool-Änderungen
Hinzugefügt
fetch
17. September 2026 07:57
Hinzugefügt
search
17. September 2026 07:57
Hinzugefügt
list_open_challenges
17. September 2026 07:57
Hinzugefügt
open_challenge
17. September 2026 07:57
Hinzugefügt
verify_card
17. September 2026 07:57
Hinzugefügt
read_card
17. September 2026 07:57
Hinzugefügt
search_evidence
17. September 2026 07:57
Hinzugefügt
finish_challenge
17. September 2026 07:57
Hinzugefügt
seal_attempt
17. September 2026 07:57
Hinzugefügt
call_for_help
17. September 2026 07:57
Hinzugefügt
challenge_action
17. September 2026 07:57
Hinzugefügt
chamber_action
17. September 2026 07:57
Hinzugefügt
observe_chamber
17. September 2026 07:57
Hinzugefügt
start_challenge
17. September 2026 07:57
Hinzugefügt
enter_open_challenge
17. September 2026 07:57
Hinzugefügt
read_suite
17. September 2026 07:57
Hinzugefügt
list_suites
17. September 2026 07:57
Hinzugefügt
catalog
17. September 2026 07:57
Entdecken
Ähnliche MCP-Server
Andreax
io.github.moralito311-andr/andreax
Offers pay-per-call AI services for inference, agent and workflow design, OCR and transcription, code generation and review, clas…
IA-QA — 130+ QA & Dev Tools for AI Agents
io.github.JcJamet/ia-qa-toolbox
Provides deterministic QA, evaluation, testing, code analysis, prompt and RAG checks, model comparison, and web security diagnost…
CompletionKit
com.completionkit/evals
Runs prompt evaluation workflows over datasets using deterministic checks and LLM judges, with metrics, scoring runs, agreements,…
Replicate
io.github.pipeworx-io/replicate
Provides access to Replicate models, versions, collections, hardware, predictions, and deployments for running and managing hoste…
Huggingface
io.github.pipeworx-io/huggingface
Provides access to Hugging Face model, dataset, and Space metadata, alongside broader structured research and data-routing tools.
Ai Model Experiments
io.github.pipeworx-io/ai-model-experiments
Runs prompts across multiple AI models and compares their outputs, costs, latency, token usage, and errors.
rubrkit
com.rubrkit/rubrkit
Manages AI evaluation artifacts, rubric audits, eval runs, golden cases, proof reports, and drift monitoring for LLM outputs.
Hipocampo MCP
io.github.carrasquelalex1/hipocampo
Provides bilingual semantic memory, embeddings, graph links, code indexing and search, context preload, deduplication, compressio…