Zero Core Verify

meltingpixelsai/harvey-verify

This is post-transaction verification infrastructure for autonomous agents on RelayZero's network. It uses LLM-as-judge evaluation to confirm whether a paid service call actually delivered what it promised. The server exposes verification tools through streamable HTTP at verify.rugslayer.com/mcp, letting agents programmatically validate outcomes from x402 micropayment transactions. You'd reach for this when building agents that need to audit service quality before releasing escrowed USDC or deciding whether to rehire a seller agent. Think of it as the reputation feedback loop for the agent economy: agents call external services through RelayZero's rails, then use this to log whether the work was actually good enough to justify payment and future trust.

tools: 5
transport: HTTP
last updated: Apr 30, 2026

View on GitHub

Install

From registry metadata

$ npx add-mcp https://verify.rugslayer.com/mcp --name zero-core-verify

Run in your terminal. add-mcp asks which agents to add it to (Claude Code, Codex, Cursor and more). Add -g to install it for every project.

Review the command, arguments and environment values before installing. MCP servers run with your local permissions.

Other ways

Claude Code

$ claude mcp add --transport http zero-core-verify https://verify.rugslayer.com/mcp

Run in your terminal. Add --scope user to make it available in every project.

Tools

Verified live · 5 tools

Verified live against the running server on Nov 6, 2026.

list_toolsList all available Harvey Verify tools with pricing and input requirements. Use this for discovery.

List all available Harvey Verify tools with pricing and input requirements. Use this for discovery.

No parameters. Call it with no arguments.

healthCheck Harvey Verify server status, uptime, and payment network configuration.

Check Harvey Verify server status, uptime, and payment network configuration.

No parameters. Call it with no arguments.

verify_outcomePost-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 ju...7 params

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 ju...

Parameters* required

expected_schemastring

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.

observed_response_time_msinteger

The response time you measured, in milliseconds

request_description*string

What was requested from the service

response_data*string

The actual response/output received from the service

service_idstring

Service identifier for quality tracking (e.g. 'harvey-tools/scrape_url')

sla_max_response_time_msinteger

The response time limit, in milliseconds

sla_requirementsstring

SLA wording for the AI judge (e.g. 'must include all fields'). For a time limit code can check, use the two fields below.

get_service_qualityGet 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 s...1 params

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 s...

Parameters* required

service_id*string

Service identifier to query (e.g. 'harvey-tools/scrape_url')

report_outcomeRecord 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.4 params

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.

Parameters* required

notesstring

Optional notes about the outcome

response_time_msinteger

Response time in milliseconds

service_id*string

Service identifier (e.g. 'harvey-tools/scrape_url')

was_successful*boolean

Whether the service call succeeded