Merron
Inspect selected project excerpts and screen user-confirmed facts for bounded EU AI Act readiness.
我該用這個嗎
品質與安全性
根據工具定義與協定合規性的自動化分析。
上下文成本
這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高，可用於其他工作的注意力就越少。
安裝
一鍵安裝
將以下內容加入你的 `claude_desktop_config.json` 檔案：
{
"mcpServers": {
"ai-act-check": {
"url": "https://merron.app/mcp"
}
}
}遠端端點
https://merron.app/mcpstreamable-http它能做什麼
工具清單
工具（4）
🟢merron_scan_project(sharingConfirmed, files)
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.
輸入結構描述
{
"type": "object",
"properties": {
"sharingConfirmed": {
"type": "boolean",
"const": true,
"description": "True only after the user agrees to send these selected excerpts to Merron."
},
"files": {
"type": "array",
"items": {
"type": "object",
"properties": {
"path": {
"type": "string",
"minLength": 1,
"maxLength": 240
},
"startLine": {
"type": "integer",
"minimum": 1,
"maximum": 1000000,
"default": 1
},
"text": {
"type": "string",
"minLength": 1,
"maxLength": 8000
}
},
"required": [
"path",
"text"
],
"additionalProperties": false
},
"minItems": 1,
"maxItems": 12
}
},
"required": [
"sharingConfirmed",
"files"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢merron_get_questions(facts)
Get relevant business questions and explanations for a selected AI system. Pass only known user answers; omit unknown values or use null. Does not classify or assume unanswered questions mean No. No sign-in or private workspace access.
輸入結構描述
{
"type": "object",
"properties": {
"facts": {
"type": "object",
"additionalProperties": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "string",
"enum": [
"provider",
"deployer",
"both"
]
},
{
"type": "null"
}
]
},
"default": {}
}
},
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢merron_screen_ai_act(factsConfirmedByUser, facts)
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.
輸入結構描述
{
"type": "object",
"properties": {
"factsConfirmedByUser": {
"type": "boolean",
"const": true,
"description": "True only after the user confirms the supplied answers describe the actual system."
},
"facts": {
"type": "object",
"additionalProperties": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "string",
"enum": [
"provider",
"deployer",
"both"
]
},
{
"type": "null"
}
]
}
}
},
"required": [
"factsConfirmedByUser",
"facts"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟡merron_prepare_workspace(userAgreed, system)
Save this AI system to Merron so the user can build an evidence pack from it: the name, a description, the answers the user confirmed and the file/line findings from merron_scan_project. Returns a private single-use link, valid 7 days; the user signs in, the system opens prefilled and Merron guides them through connecting the code, confirming the answers and creating the pack. Ask the user first and tell them what will be saved. Never include code excerpts, secrets or personal data; findings carry only paths, line numbers and codes. Give the user the link exactly as returned.
輸入結構描述
{
"type": "object",
"properties": {
"userAgreed": {
"type": "boolean",
"const": true,
"description": "True only after the user agrees to save these details to Merron."
},
"system": {
"type": "object",
"properties": {
"company": {
"type": "string",
"minLength": 1,
"maxLength": 200
},
"productName": {
"type": "string",
"minLength": 1,
"maxLength": 200
},
"description": {
"type": "string",
"minLength": 20,
"maxLength": 4000
},
"facts": {
"type": "object",
"additionalProperties": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "string",
"enum": [
"provider",
"deployer",
"both"
]
},
{
"type": "null"
}
]
},
"default": {}
},
"findings": {
"type": "array",
"items": {
"type": "object",
"properties": {
"code": {
"type": "string",
"minLength": 1,
"maxLength": 60
},
"path": {
"type": "string",
"minLength": 1,
"maxLength": 240
},
"line": {
"type": "integer",
"minimum": 1,
"maximum": 1000000
},
"interpretation": {
"type": "string",
"maxLength": 300
}
},
"required": [
"code",
"path",
"line"
],
"additionalProperties": false
},
"maxItems": 60,
"default": []
}
},
"required": [
"company",
"productName",
"description"
],
"additionalProperties": false
}
},
"required": [
"userAgreed",
"system"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}社群
證據