MCP 服务器

Merron

app.merron/ai-act-check
法律与合规 公开且可连接 MCP 2025-11-25

此 MCP 可以做什么

Screens confirmed facts and selected project excerpts against bounded EU AI Act rules, returning conditional results and official references.

merron_get_questions
Get AI Act screening questions
Get relevant business questions and explanations for a selected AI system. Pass only known user answers; omit unknown values or use null. Does not classify or assume unanswered questions mean No. No sign-in or private workspace access.
只读 幂等
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {'facts': {'type': 'object', 'default': {}, 'additionalProperties': {'anyOf': [{'type': 'boolean'}, {'enum': ['provider', 'deployer', 'both'], 'type': 'string'}, {'type': 'null'}]}}}, 'additionalProperties': False}
merron_prepare_workspace
Prepare the system in a private Merron workspace
Save this AI system to Merron so the user can build an evidence pack from it: the name, a description, the answers the user confirmed and the file/line findings from merron_scan_project. Returns a private single-use link, valid 7 days; the user signs in, the system opens prefilled and Merron guides them through connecting the code, confirming the answers and creating the pack. Ask the user first and tell them what will be saved. Never include code excerpts, secrets or personal data; findings carry only paths, line numbers and codes. Give the user the link exactly as returned.
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['userAgreed', 'system'], 'properties': {'system': {'type': 'object', 'required': ['company', 'productName', 'description'], 'properties': {'facts': {'type': 'object', 'default': {}, 'additionalProperties': {'anyOf': [{'type': 'boolean'}, {'enum': ['provider', 'deployer', 'both'], 'type': 'string'}, {'type': 'null'}]}}, 'company': {'type': 'string', 'maxLength': 200, 'minLength': 1}, 'findings': {'type': 'array', 'items': {'type': 'object', 'required': ['code', 'path', 'line'], 'properties': {'code': {'type': 'string', 'maxLength': 60, 'minLength': 1}, 'line': {'type': 'integer', 'maximum': 1000000, 'minimum': 1}, 'path': {'type': 'string', 'maxLength': 240, 'minLength': 1}, 'interpretation': {'type': 'string', 'maxLength': 300}}, 'additionalProperties': False}, 'default': [], 'maxItems': 60}, 'description': {'type': 'string', 'maxLength': 4000, 'minLength': 20}, 'productName': {'type': 'string', 'maxLength': 200, 'minLength': 1}}, 'additionalProperties': False}, 'userAgreed': {'type': 'boolean', 'const': True, 'description': 'True only after the user agrees to save these details to Merron.'}}, 'additionalProperties': False}
merron_scan_project
Inspect selected project excerpts
Find possible AI integrations, model calls, disclosure wording and sensitive-use wording in user-selected project excerpts. Returns file/line references and follow-up questions, not a legal classification. First explain that the excerpts will be sent to Merron and obtain the user's agreement. Never send secrets, personal customer records, whole repositories or files the user has not authorised. Does not fetch URLs, execute code, persist inputs or access private cases.
只读 幂等
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['sharingConfirmed', 'files'], 'properties': {'files': {'type': 'array', 'items': {'type': 'object', 'required': ['path', 'text'], 'properties': {'path': {'type': 'string', 'maxLength': 240, 'minLength': 1}, 'text': {'type': 'string', 'maxLength': 8000, 'minLength': 1}, 'startLine': {'type': 'integer', 'default': 1, 'maximum': 1000000, 'minimum': 1}}, 'additionalProperties': False}, 'maxItems': 12, 'minItems': 1}, 'sharingConfirmed': {'type': 'boolean', 'const': True, 'description': 'True only after the user agrees to send these selected excerpts to Merron.'}}, 'additionalProperties': False}
merron_screen_ai_act
Screen confirmed facts for the EU AI Act
Run Merron's versioned, bounded AI Act rules on facts the user has explicitly confirmed. Returns a conditional screening result, unresolved routes, missing questions and official references. Never infer confirmation or legal compliance from source code or absence of signals. Unknown answers remain unknown. This computation does not check documents, use an AI model, save a report, access accounts or certify compliance.
只读 幂等
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['factsConfirmedByUser', 'facts'], 'properties': {'facts': {'type': 'object', 'additionalProperties': {'anyOf': [{'type': 'boolean'}, {'enum': ['provider', 'deployer', 'both'], 'type': 'string'}, {'type': 'null'}]}}, 'factsConfirmedByUser': {'type': 'boolean', 'const': True, 'description': 'True only after the user confirms the supplied answers describe the actual system.'}}, 'additionalProperties': False}
已添加
merron_prepare_workspace
2026年9月29日 03:00
已更改
merron_screen_ai_act
2026年9月19日 02:49
已更改
merron_get_questions
2026年9月19日 02:49
已添加
merron_screen_ai_act
2026年9月17日 07:57
已添加
merron_get_questions
2026年9月17日 07:57
已添加
merron_scan_project
2026年9月17日 07:57