Serveur MCP

zero-core-verify

io.github.meltingpixelsai/zero-core-verify
Données et analytique Public et accessible MCP 2025-11-25

Ce que fait ce MCP

Verifies service outcomes after transactions and records pass/fail results, quality metrics, and LLM-based assessments.

get_service_quality
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.
Schéma d’entrée
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['service_id'], 'properties': {'service_id': {'type': 'string', 'description': "Service identifier to query (e.g. 'harvey-tools/scrape_url')"}}, 'additionalProperties': False}
health
Check Harvey Verify server status, uptime, and payment network configuration.
Schéma d’entrée
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}, 'additionalProperties': False}
list_tools
List all available Harvey Verify tools with pricing and input requirements. Use this for discovery.
Schéma d’entrée
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}, 'additionalProperties': False}
report_outcome
Record a simple pass/fail outcome report for a service call. No LLM analysis - just logs the result to the quality database. Cheaper alternative to verify_outcome when you only need to record success/failure.
Schéma d’entrée
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['service_id', 'was_successful'], 'properties': {'notes': {'type': 'string', 'description': 'Optional notes about the outcome'}, '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'}}, 'additionalProperties': False}
verify_outcome
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.
Schéma d’entrée
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['request_description', 'response_data'], 'properties': {'service_id': {'type': 'string', 'description': "Service identifier for quality tracking (e.g. 'harvey-tools/scrape_url')"}, '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')"}, 'request_description': {'type': 'string', 'description': 'What was requested from the service'}}, 'additionalProperties': False}
Ajouté
report_outcome
17 September 2026 12:45
Ajouté
get_service_quality
17 September 2026 12:45
Ajouté
verify_outcome
17 September 2026 12:45
Ajouté
health
17 September 2026 12:45
Ajouté
list_tools
17 September 2026 12:45