LeashIndex Get the report

Index / payments

PHION Agent Trust Infrastructure

systems-phion-evidence-engine declares 135 capabilities across 135 tools, with 3 critical issues.

100/100 exposureHigh exposure

Manifest recorded 2026-10-21 from tools/list on https://phion.systems/mcp, published in the official MCP registry as systems.phion/evidence-engine 1.57.0. The date changes only when the manifest does. Not verified by a maintainer.

Issues

These describe what this server's manifest declares. A product can provide controls that MCP has no way to express — token revocation, an admin console, audit logs — and this page cannot see them. The absence of a declaration is not evidence that a control is absent.

critical · no-revocation · All 135 tools

135 of 135 tools declare no way for the customer to switch them off once granted. This applies to every tool because MCP has no field in which to declare a revocation mechanism; the product may provide one outside MCP that a manifest cannot show.

critical · irreversible-uncapped · 10 of 135 tools

10 tools are classified as irreversible and declare no limit.

critical · uncapped-spend · 8 of 135 tools

8 tools are classified as moving money and declare no dollar limit. A cap on the number of payments does not bound their amount.

high · no-expiry · All 135 tools

135 of 135 tools declare no expiry. This applies to every tool because MCP has no field in which to declare an expiry; the product may provide one outside MCP that a manifest cannot show.

high · no-audit-trail · All 135 tools

135 of 135 tools declare no record of their actions that the customer can read. This applies to every tool because MCP has no field in which to declare an audit requirement; the product may provide one outside MCP that a manifest cannot show.

high · uncapped-write · 37 of 135 tools

37 tools can modify data and declare no limit.

low · uncapped-read · 88 of 135 tools

88 tools can read data and declare no limit.

Declared capabilities

How each tool was read. declared means the server's own annotation said so — self-reported and unverified. inferred is from the tool's name. assumed means nothing indicated either way.

ToolRead asBasis
phion_discoverread declared
phion_search_servicesread declared
phion_get_serviceread declared
phion_preflightread declared
phion_resolveread declared
phion_executewrite assumed
index_feedread declared
preflightwrite assumed
try_serviceread inferred
schema_normalize_freewrite assumed
payment_diagnosepay inferred
payment_capability_preflightpay inferred
verifyread declared
attestwrite assumed
payment_preflightpay inferred
fetch_evidenceread declared
mandate_reservewrite assumed
inspect_agentread declared
journey_verifyread declared
transaction_assuranceread declared
transaction_recoveryread declared
schema_normalizeread declared
agent_reputation_evidencewrite assumed
counterparty_risk_preflightwrite assumed
tool_output_firewallwrite assumed
delegation_scope_guardwrite assumed
memory_write_guardwrite inferred
mcp_manifest_firewallwrite assumed
tool_call_policy_guardwrite assumed
data_egress_preflightwrite assumed
agent_budget_guardwrite assumed
idempotency_replay_guardread inferred
human_approval_policywrite assumed
secret_redaction_preflightread inferred
oauth_token_audience_guardread inferred
redirect_callback_validatorread inferred
tool_capability_drift_monitorread inferred
mcp_server_identity_evidencewrite assumed
agent_task_handoff_receiptwrite assumed
context_provenance_labelerwrite assumed
signed_result_comparatorread inferred
service_sla_attestationwrite assumed
payment_route_selectorpay inferred
x402_quote_comparatorread declared
payment_receipt_reconcilerpay inferred
duplicate_charge_detectorpay inferred
subscription_spend_guardread declared
webhook_verifierread declared
delivery_evidenceread declared
inter_agent_policy_evaluatorread declared
concurrency_guardread declared
resource_cycle_guardread declared
abandoned_tool_detectorread declared
manifest_version_diffwrite assumed
dependency_provenance_assessmentdelete inferred
conflict_resolutionwrite assumed
data_freshness_certificatewrite assumed
domain_ownership_evidencewrite assumed
purpose_bound_consentdelete inferred
retention_deletion_receiptwrite inferred
interrupted_task_recoverywrite assumed
portable_observability_auditread inferred
rwa_asset_due_diligenceread declared
rwa_complianceread declared
rwa_nav_reserveread inferred
rwa_transaction_assuranceread inferred
rwa_corporate_actionsread inferred
rwa_sanctions_screening_evidencewrite assumed
verified_web_extractwrite assumed
entity_enrichment_evidencewrite assumed
social_source_evidencewrite assumed
market_data_snapshotwrite assumed
onchain_evidencewrite assumed
verified_news_monitorread inferred
multi_source_fact_bundlewrite assumed
document_to_verified_jsonwrite assumed
source_backed_searchread inferred
live_data_freshnesswrite assumed
person_enrichment_evidencewrite assumed
company_enrichment_evidencewrite assumed
contact_enrichment_evidencewrite assumed
mcp_2026_compatibility_gatewayread declared
durable_agent_taskread declared
task_checkpoint_evidenceread declared
task_cancel_assuranceread declared
agent_approval_relayread declared
capability_negotiation_preflightread declared
mcp_catalog_cache_guardread declared
oauth_issuer_binding_evidenceread declared
mcp_a2a_task_bridgeread declared
quote_freshness_guardread declared
delegated_credential_guardread declared
agent_session_continuityread declared
task_lease_guardread declared
tool_result_schema_validatorread declared
agent_memory_provenanceread declared
payment_delivery_atomicitypay inferred
service_failover_selectorread declared
agent_rate_limit_negotiatorread declared
execution_cost_estimatorread declared
cross_agent_receipt_bundleread declared
capability_verificationread declared
capability_benchmarkread declared
sybil_reputation_guardread declared
agent_behavior_fingerprintread declared
trust_anomaly_detectorread declared
economic_loop_detectorread declared
provider_quality_predictorread declared
transaction_risk_scoreread declared
payment_optimizerpay inferred
x402_v2_routerread declared
erc8004_identity_evidenceread declared
erc8004_reputation_intelligenceread declared
delegated_spend_policyread declared
ap2_mandate_bridgeread declared
a2a_transaction_bridgeread declared
mcp_transaction_gatewayread declared
proof_of_serviceread declared
automated_dispute_bundleread declared
transaction_recovery_v2read declared
reputation_update_receiptread declared
agent_economic_graphread declared
market_demand_predictorread declared
service_gap_detectorread declared
price_discovery_engineread declared
sla_risk_predictorread declared
dynamic_service_pricingread declared
autonomous_procurementread declared
multi_agent_escrowread declared
cross_protocol_receiptread declared
phion_inferenceread declared
phion_searchread declared
phion_enrich_basicread declared
phion_enrichread declared
phion_intelligenceread declared

Record history

Earlier records for this server. A correction is added here, never written over the record it corrects.

RecordedExposureSource
2026-10-11100 tools/list on https://phion.systems/mcp, published in the official MCP registry as systems.phion/evidence-engine 1.57.0
Answering this question about your own agent? The self-serve stack report applies the same reading to your own stack or server and gives you a dated document you can hand to a customer's security review. It is generated in your browser, with nobody to wait for. Buying one does not change this page, its score or its place in the index — see Independence.
Maintain this server? If this page misreads your manifest, or your server has changed, submit its current tools/list response and it will be re-scored and dated. Corrections are published alongside the original, not in place of it.