{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_qb5q7pks76bu","handle":"agent-trust-firewall","url":"https://wellknown.network/agents/agent-trust-firewall","links":{"self":"https://wellknown.network/agents/agent-trust-firewall/record.json","html":"https://wellknown.network/agents/agent-trust-firewall","markdown":"https://wellknown.network/agents/agent-trust-firewall/record.md","api":"https://wellknown.network/api/v1/agents/agent-trust-firewall","status":"https://wellknown.network/api/v1/agents/agent-trust-firewall/status","claim":"https://wellknown.network/agents/agent-trust-firewall/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/agent-trust-firewall/claim.json","badge":"https://wellknown.network/agents/agent-trust-firewall/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/agent-trust-firewall/history","tools":"https://wellknown.network/api/v1/agents/agent-trust-firewall/tools"},"ard":{"identifier":"urn:air:agent-trust-firewall.andrea-vignoni.workers.dev:server:agent-trust-firewall","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"Agent Trust Firewall","summary":"Free pre-action policy checks and data cleaning for autonomous AI agents.","description":"Free pre-action policy checks and data cleaning for autonomous AI agents.","publisher":{"name":"Benji18sport","url":null},"homepage":null,"repository":"https://github.com/Benji18sport/agent-commerce-os","version":"1.5.0","license":null,"protocols":["mcp"],"tags":[],"pricing":null,"endpoints":[{"url":"https://agent-trust-firewall.andrea-vignoni.workers.dev/mcp","type":"mcp_streamable_http","auth":null,"probeable":true}],"skills":null,"tools":null,"extra":{"updatedAt":"2026-10-30T18:58:59.764342Z","publishedAt":"2026-10-30T18:58:59.764342Z","registryName":"io.github.Benji18sport/agent-trust-firewall"},"attribution":{"kind":"mcp_registry","name":"mcp_registry","repoUrl":"mcp_registry","summary":"mcp_registry","version":"mcp_registry","description":"mcp_registry","publisherName":"mcp_registry"}},"derived":{"capabilities":[{"slug":"commerce.ecommerce","name":"E-commerce Operations","confidence":0.54,"provenance":"derived"},{"slug":"commerce.payments","name":"Payments","confidence":0.51,"provenance":"derived"}],"categories":["commerce"],"language":"en"},"observed":{"status":"live","statusReason":"Responded 5h ago.","lastOkAt":"2026-11-04T00:29:41.937Z","lastProbedAt":"2026-11-04T00:29:41.937Z","statusComputedAt":"2026-11-04T00:34:15.983Z","reliability30d":{"probes":7,"successRate":1,"p50Ms":42,"basis":"service","measures":{"availability":"availability","latency":"response time","tools":"tool surface observed","summary":"Checks reached the service itself."},"checks":{"total":7,"ok":7,"authBoundaryOk":0,"serviceOk":7,"note":"Counted from the observation rows for the window, checks of the server only (HTTP, A2A card, MCP initialize). ok = authBoundaryOk + serviceOk. `probes` is the sum of daily rollups and includes registry checks, so it can differ from `total`."}},"latestObservations":[{"at":"2026-11-04T00:29:41.937Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":31,"error":null,"detail":{"tools":[{"name":"trust_check_action","description":"Evaluate a proposed action against evidence, source allowlists, data constraints and payment limits, returning ALLOW/BLOCK with reason codes. All enabled checks"},{"name":"trust_check_spend","description":"Compare a proposed spend with a remaining budget, transaction ceiling and merchant allowlist, returning ALLOW/BLOCK with reasons. Budget and ceiling are indepen"},{"name":"trust_validate_data","description":"Validate JSON field presence, exact types, primitive enums and inclusive numeric bounds, returning ALLOW/BLOCK, field reasons and checked_fields. Combine requir"},{"name":"trust_clean_data","description":"Audit and optionally clean up to 500 JSON rows, returning cleaned_rows, original zero-based issues and counts. Processing order is trim, primary-key deduplicati"},{"name":"trust_get_capabilities","description":"Discover the deployed version, request/row limits, tool names, legacy call aliases and check-clean-recheck workflow before integrating. Pass {}: this inventory "}],"toolCount":5,"toolsHash":"66340562c52542c4910ba2d70474bf07551e9f848832e251101ca75a4c2923b7","serverName":"agent-trust-firewall","capabilities":["tools"],"serverVersion":"1.8.1","protocolVersion":"2025-06-18"}},{"at":"2026-11-03T15:26:17.798Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":57,"error":null,"detail":{"tools":[{"name":"trust_check_action","description":"Evaluate a proposed action against evidence, source allowlists, data constraints and payment limits, returning ALLOW/BLOCK with reason codes. All enabled checks"},{"name":"trust_check_spend","description":"Compare a proposed spend with a remaining budget, transaction ceiling and merchant allowlist, returning ALLOW/BLOCK with reasons. Budget and ceiling are indepen"},{"name":"trust_validate_data","description":"Validate JSON field presence, exact types, primitive enums and inclusive numeric bounds, returning ALLOW/BLOCK, field reasons and checked_fields. Combine requir"},{"name":"trust_clean_data","description":"Audit and optionally clean up to 500 JSON rows, returning cleaned_rows, original zero-based issues and counts. Processing order is trim, primary-key deduplicati"},{"name":"trust_get_capabilities","description":"Discover the deployed version, request/row limits, tool names, legacy call aliases and check-clean-recheck workflow before integrating. Pass {}: this inventory "}],"toolCount":5,"toolsHash":"66340562c52542c4910ba2d70474bf07551e9f848832e251101ca75a4c2923b7","serverName":"agent-trust-firewall","capabilities":["tools"],"serverVersion":"1.8.1","protocolVersion":"2025-06-18"}},{"at":"2026-11-03T07:28:50.513Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":71,"error":null,"detail":{"tools":[{"name":"trust_check_action","description":"Evaluate a proposed action against evidence, source allowlists, data constraints and payment limits, returning ALLOW/BLOCK with reason codes. All enabled checks"},{"name":"trust_check_spend","description":"Compare a proposed spend with a remaining budget, transaction ceiling and merchant allowlist, returning ALLOW/BLOCK with reasons. Budget and ceiling are indepen"},{"name":"trust_validate_data","description":"Validate JSON field presence, exact types, primitive enums and inclusive numeric bounds, returning ALLOW/BLOCK, field reasons and checked_fields. Combine requir"},{"name":"trust_clean_data","description":"Audit and optionally clean up to 500 JSON rows, returning cleaned_rows, original zero-based issues and counts. Processing order is trim, primary-key deduplicati"},{"name":"trust_get_capabilities","description":"Discover the deployed version, request/row limits, tool names, legacy call aliases and check-clean-recheck workflow before integrating. Pass {}: this inventory "}],"toolCount":5,"toolsHash":"66340562c52542c4910ba2d70474bf07551e9f848832e251101ca75a4c2923b7","serverName":"agent-trust-firewall","capabilities":["tools"],"serverVersion":"1.8.1","protocolVersion":"2025-06-18"}},{"at":"2026-11-02T23:31:28.959Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":45,"error":null,"detail":{"tools":[{"name":"trust_check_action","description":"Evaluate a proposed action against evidence, source allowlists, data constraints and payment limits, returning ALLOW/BLOCK with reason codes. All enabled checks"},{"name":"trust_check_spend","description":"Compare a proposed spend with a remaining budget, transaction ceiling and merchant allowlist, returning ALLOW/BLOCK with reasons. Budget and ceiling are indepen"},{"name":"trust_validate_data","description":"Validate JSON field presence, exact types, primitive enums and inclusive numeric bounds, returning ALLOW/BLOCK, field reasons and checked_fields. Combine requir"},{"name":"trust_clean_data","description":"Audit and optionally clean up to 500 JSON rows, returning cleaned_rows, original zero-based issues and counts. Processing order is trim, primary-key deduplicati"},{"name":"trust_get_capabilities","description":"Discover the deployed version, request/row limits, tool names, legacy call aliases and check-clean-recheck workflow before integrating. Pass {}: this inventory "}],"toolCount":5,"toolsHash":"66340562c52542c4910ba2d70474bf07551e9f848832e251101ca75a4c2923b7","serverName":"agent-trust-firewall","capabilities":["tools"],"serverVersion":"1.8.1","protocolVersion":"2025-06-18"}},{"at":"2026-11-02T15:26:32.068Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":151,"error":null,"detail":{"tools":[{"name":"trust_check_action","description":"Evaluate a proposed action against evidence, source allowlists, data constraints and payment limits, returning ALLOW/BLOCK with reason codes. All enabled checks"},{"name":"trust_check_spend","description":"Compare a proposed spend with a remaining budget, transaction ceiling and merchant allowlist, returning ALLOW/BLOCK with reasons. Budget and ceiling are indepen"},{"name":"trust_validate_data","description":"Validate JSON field presence, exact types, primitive enums and inclusive numeric bounds, returning ALLOW/BLOCK, field reasons and checked_fields. Combine requir"},{"name":"trust_clean_data","description":"Audit and optionally clean up to 500 JSON rows, returning cleaned_rows, original zero-based issues and counts. Processing order is trim, primary-key deduplicati"},{"name":"trust_get_capabilities","description":"Discover the deployed version, request/row limits, tool names, legacy call aliases and check-clean-recheck workflow before integrating. Pass {}: this inventory "}],"toolCount":5,"toolsHash":"66340562c52542c4910ba2d70474bf07551e9f848832e251101ca75a4c2923b7","serverName":"agent-trust-firewall","capabilities":["tools"],"serverVersion":"1.8.1","protocolVersion":"2025-06-18"}},{"at":"2026-11-02T07:24:13.089Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":36,"error":null,"detail":{"tools":[{"name":"trust_check_action","description":"Evaluate a proposed action against evidence, source allowlists, data constraints and payment limits, returning ALLOW/BLOCK with reason codes. All enabled checks"},{"name":"trust_check_spend","description":"Compare a proposed spend with a remaining budget, transaction ceiling and merchant allowlist, returning ALLOW/BLOCK with reasons. Budget and ceiling are indepen"},{"name":"trust_validate_data","description":"Validate JSON field presence, exact types, primitive enums and inclusive numeric bounds, returning ALLOW/BLOCK, field reasons and checked_fields. Combine requir"},{"name":"trust_clean_data","description":"Audit and optionally clean up to 500 JSON rows, returning cleaned_rows, original zero-based issues and counts. Processing order is trim, primary-key deduplicati"},{"name":"trust_get_capabilities","description":"Discover the deployed version, request/row limits, tool names, legacy call aliases and check-clean-recheck workflow before integrating. Pass {}: this inventory "}],"toolCount":5,"toolsHash":"66340562c52542c4910ba2d70474bf07551e9f848832e251101ca75a4c2923b7","serverName":"agent-trust-firewall","capabilities":["tools"],"serverVersion":"1.8.1","protocolVersion":"2025-06-18"}},{"at":"2026-11-01T22:23:34.940Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":27,"error":null,"detail":{"tools":[{"name":"trust_check_action","description":"Evaluate a proposed action against evidence, source allowlists, data constraints and payment limits, returning ALLOW/BLOCK with reason codes. All enabled checks"},{"name":"trust_check_spend","description":"Compare a proposed spend with a remaining budget, transaction ceiling and merchant allowlist, returning ALLOW/BLOCK with reasons. Budget and ceiling are indepen"},{"name":"trust_validate_data","description":"Validate JSON field presence, exact types, primitive enums and inclusive numeric bounds, returning ALLOW/BLOCK, field reasons and checked_fields. Combine requir"},{"name":"trust_clean_data","description":"Audit and optionally clean up to 500 JSON rows, returning cleaned_rows, original zero-based issues and counts. Processing order is trim, primary-key deduplicati"},{"name":"trust_get_capabilities","description":"Discover the deployed version, request/row limits, tool names, legacy call aliases and check-clean-recheck workflow before integrating. Pass {}: this inventory "}],"toolCount":5,"toolsHash":"66340562c52542c4910ba2d70474bf07551e9f848832e251101ca75a4c2923b7","serverName":"agent-trust-firewall","capabilities":["tools"],"serverVersion":"1.8.1","protocolVersion":"2025-06-18"}}],"tools":[{"name":"trust_check_action","description":"Evaluate a proposed action against evidence, source allowlists, data constraints and payment limits, returning ALLOW/BLOCK with reason codes. All enabled checks"},{"name":"trust_check_spend","description":"Compare a proposed spend with a remaining budget, transaction ceiling and merchant allowlist, returning ALLOW/BLOCK with reasons. Budget and ceiling are indepen"},{"name":"trust_validate_data","description":"Validate JSON field presence, exact types, primitive enums and inclusive numeric bounds, returning ALLOW/BLOCK, field reasons and checked_fields. Combine requir"},{"name":"trust_clean_data","description":"Audit and optionally clean up to 500 JSON rows, returning cleaned_rows, original zero-based issues and counts. Processing order is trim, primary-key deduplicati"},{"name":"trust_get_capabilities","description":"Discover the deployed version, request/row limits, tool names, legacy call aliases and check-clean-recheck workflow before integrating. Pass {}: this inventory "}],"package":null,"toolSurface":{"id":"ts_cyyegyu8qs2h","endpointId":"ep_bbc926cebnkj","hash":"66340562c52542c4910ba2d70474bf07551e9f848832e251101ca75a4c2923b7","toolCount":5,"serverName":"agent-trust-firewall","serverVersion":"1.8.1","protocolVersion":"2025-06-18","firstSeenAt":"2026-11-01T22:23:34.948Z","lastSeenAt":"2026-11-04T00:29:41.944Z","observations":7,"toolNames":["trust_check_action","trust_check_spend","trust_validate_data","trust_clean_data","trust_get_capabilities"],"distinctSurfaces":1},"endpointFacts":[{"id":"ep_bbc926cebnkj","url":"https://agent-trust-firewall.andrea-vignoni.workers.dev/mcp","type":"mcp_streamable_http","factsCheckedAt":"2026-11-04T00:29:41.955Z","auth":{"observedAt":"2026-11-04T00:29:41.980Z","authRequired":false,"scheme":null,"resourceMetadata":null,"authorizationServer":null,"conformance":{"dpop":false,"rfc8414":false,"rfc9728":false,"pkceS256":false,"clientIdMetadataDocument":false,"dynamicClientRegistration":false}},"tls":{"observedAt":"2026-11-04T00:29:41.997Z","protocol":"TLSv1.3","chainValid":true,"chainError":null,"hostMatches":true,"subject":"andrea-vignoni.workers.dev","issuer":{"commonName":"WE1","organization":"Google Trust Services"},"validFrom":"2026-09-06T09:36:16.000Z","validTo":"2026-12-05T10:34:59.000Z","daysToExpiry":31,"sanCount":2,"fingerprint256":"4C:3B:51:1F:05:1B:9A:6B:A1:B9:A6:79:88:18:68:6E:51:D2:EB:25:11:D4:BE:C8:A1:06:5F:1C:61:3A:6A:17"}}]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"mcp_registry","key":"io.github.Benji18sport/agent-trust-firewall","url":"https://registry.modelcontextprotocol.io/v0/servers/io.github.Benji18sport%2Fagent-trust-firewall","firstSeenAt":"2026-11-01T20:20:32.724Z","fetchedAt":"2026-11-01T20:20:32.724Z","normalizedAt":"2026-11-01T20:20:32.724Z"}]},"firstSeenAt":"2026-11-01T20:20:32.724Z","updatedAt":"2026-11-04T00:37:09.235Z"}