zero-core-verify
Post-tx outcome verification via LLM-as-judge. Zero Core Verify.
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": {
"zero-core-verify": {
"command": "npx",
"args": [
"@meltingpixels/zero-core-verify"
]
}
}
}可執行的套件
1.0.0streamable-http遠端端點
https://verify.rugslayer.com/mcpstreamable-http它能做什麼
工具清單
工具（5）
🟢list_tools
List all available Harvey Verify tools with pricing and input requirements. Use this for discovery.
輸入結構描述
{
"type": "object",
"properties": {},
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢health
Check Harvey Verify server status, uptime, and payment network configuration.
輸入結構描述
{
"type": "object",
"properties": {},
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟡verify_outcome(request_description, response_data, expected_schema, sla_requirements, service_id)
Post-transaction verification using LLM-as-judge. Checks if a service delivered what was promised. Returns completeness score, accuracy score, format compliance, SLA adherence, issues list, and overall pass/fail.
輸入結構描述
{
"type": "object",
"properties": {
"request_description": {
"type": "string",
"description": "What was requested from the service"
},
"response_data": {
"type": "string",
"description": "The actual response/output received from the service"
},
"expected_schema": {
"type": "string",
"description": "Expected output format or JSON schema"
},
"sla_requirements": {
"type": "string",
"description": "SLA requirements to check against (e.g. 'response under 5s, must include all fields')"
},
"service_id": {
"type": "string",
"description": "Service identifier for quality tracking (e.g. 'harvey-tools/scrape_url')"
}
},
"required": [
"request_description",
"response_data"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢get_service_quality(service_id)
Get aggregated quality scores for a service based on all past verifications. Returns average completeness, accuracy, pass rate, format compliance rate, SLA compliance rate, and quality trend.
輸入結構描述
{
"type": "object",
"properties": {
"service_id": {
"type": "string",
"description": "Service identifier to query (e.g. 'harvey-tools/scrape_url')"
}
},
"required": [
"service_id"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}⚪report_outcome(service_id, was_successful, response_time_ms, notes)
Record a simple pass/fail outcome report for a service call. No LLM analysis - just logs the result to the quality database. Cheaper alternative to verify_outcome when you only need to record success/failure.
輸入結構描述
{
"type": "object",
"properties": {
"service_id": {
"type": "string",
"description": "Service identifier (e.g. 'harvey-tools/scrape_url')"
},
"was_successful": {
"type": "boolean",
"description": "Whether the service call succeeded"
},
"response_time_ms": {
"type": "number",
"description": "Response time in milliseconds"
},
"notes": {
"type": "string",
"description": "Optional notes about the outcome"
}
},
"required": [
"service_id",
"was_successful"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}社群
證據