zero-core-verify
Post-tx outcome verification via LLM-as-judge. Zero Core Verify.
Should I use this
Quality & Safety
Based on automated analysis of tool definitions and protocol compliance.
Context Cost
This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.
Install
One-Click Install
Add this to your `claude_desktop_config.json` file:
{
"mcpServers": {
"zero-core-verify": {
"command": "npx",
"args": [
"@meltingpixels/zero-core-verify"
]
}
}
}Runnable packages
1.0.0streamable-httpRemote endpoints
https://verify.rugslayer.com/mcpstreamable-httpWhat it can do
Tool inventory
Tools (5)
🟢list_tools
List all available Harvey Verify tools with pricing and input requirements. Use this for discovery.
Input Schema
{
"type": "object",
"properties": {},
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢health
Check Harvey Verify server status, uptime, and payment network configuration.
Input Schema
{
"type": "object",
"properties": {},
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟡verify_outcome(request_description, response_data, expected_schema, sla_requirements, service_id, ...)
Post-transaction verification. Code checks what it can: the response against expected_schema (a JSON Schema or a list of required field names), and a measured response time against a stated limit. A response that fails code's checks fails without the AI judge; otherwise the judge scores accuracy and completeness as advice. Without a schema or a time limit only the judge decides, and decided_by says so. Returns a verdict (pass, fail or inconclusive), decided_by, scores, format compliance, SLA result, issues, and what code checked.
Input Schema
{
"type": "object",
"properties": {
"request_description": {
"type": "string",
"maxLength": 8000,
"description": "What was requested from the service"
},
"response_data": {
"type": "string",
"maxLength": 100000,
"description": "The actual response/output received from the service"
},
"expected_schema": {
"type": "string",
"maxLength": 20000,
"description": "A JSON Schema, or two or more required top-level field names (letters, digits, _ and -) separated by commas, e.g. 'name, price, url'. Anything else is passed to the AI judge only."
},
"sla_requirements": {
"type": "string",
"maxLength": 2000,
"description": "SLA wording for the AI judge (e.g. 'must include all fields'). For a time limit code can check, use the two fields below."
},
"service_id": {
"type": "string",
"maxLength": 200,
"description": "Service identifier for quality tracking (e.g. 'harvey-tools/scrape_url')"
},
"observed_response_time_ms": {
"type": "integer",
"minimum": 0,
"maximum": 3600000,
"description": "The response time you measured, in milliseconds"
},
"sla_max_response_time_ms": {
"type": "integer",
"minimum": 0,
"maximum": 3600000,
"description": "The response time limit, in milliseconds"
}
},
"required": [
"request_description",
"response_data"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢get_service_quality(service_id)
Get aggregated quality scores for a service based on past verifications and reports, counting each paying wallet once (its latest). Returns the pass rate (overall, and over the rows where code checked the format or a measured time), average completeness and accuracy over the scored rows with their count, the count of inconclusive rows, format and SLA compliance rates, and a trend by pass rate. The scores are self-reported by paying wallets and not attested: nothing proves a reporter used the service.
Input Schema
{
"type": "object",
"properties": {
"service_id": {
"type": "string",
"maxLength": 200,
"description": "Service identifier to query (e.g. 'harvey-tools/scrape_url')"
}
},
"required": [
"service_id"
],
"additionalProperties": false,
"$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.
Input Schema
{
"type": "object",
"properties": {
"service_id": {
"type": "string",
"maxLength": 200,
"description": "Service identifier (e.g. 'harvey-tools/scrape_url')"
},
"was_successful": {
"type": "boolean",
"description": "Whether the service call succeeded"
},
"response_time_ms": {
"type": "integer",
"minimum": 0,
"maximum": 3600000,
"description": "Response time in milliseconds"
},
"notes": {
"type": "string",
"maxLength": 2000,
"description": "Optional notes about the outcome"
}
},
"required": [
"service_id",
"was_successful"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}Community
Evidence