capability_benchmark — PHION Agent Trust Infrastructure MCP Tool
capability_benchmark
(capability benchmark) is one of 124 tools on the
PHION Agent Trust Infrastructure
MCP server. Connect the server and your client discovers it on the handshake.
by client
How to call capability_benchmark from your client
- Claude Code PHION Agent Trust Infrastructure capability_benchmark run in your project directory
- Claude Desktop PHION Agent Trust Infrastructure capability_benchmark ~/Library/Application Support/Claude/claude_desktop_config.json
- Cursor PHION Agent Trust Infrastructure capability_benchmark ~/.cursor/mcp.json
- VS Code PHION Agent Trust Infrastructure capability_benchmark .vscode/mcp.json
- Zed PHION Agent Trust Infrastructure capability_benchmark ~/.config/zed/settings.json
- Windsurf PHION Agent Trust Infrastructure capability_benchmark ~/.codeium/windsurf/mcp_config.json
- Cline PHION Agent Trust Infrastructure capability_benchmark ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
- Gemini CLI PHION Agent Trust Infrastructure capability_benchmark ~/.gemini/settings.json
- Grok PHION Agent Trust Infrastructure capability_benchmark .mcp.json (in your project root)
- ChatGPT PHION Agent Trust Infrastructure capability_benchmark Settings → Connectors → Advanced → Developer mode
- Claude.ai PHION Agent Trust Infrastructure capability_benchmark Settings → Connectors → Add custom connector
- LangChain PHION Agent Trust Infrastructure capability_benchmark pip install langchain-mcp-adapters
Fastest route
claude mcp add --transport http evidence-engine https://phion.systems/mcpOther tools on this server
- phion_execute
- index_feed
- preflight
- try_service
- schema_normalize_free
- payment_diagnose
- verify
- attest
- payment_preflight
- fetch_evidence
- mandate_reserve
- inspect_agent
- journey_verify
- transaction_assurance
- transaction_recovery
- schema_normalize
- agent_reputation_evidence
- counterparty_risk_preflight
- tool_output_firewall
- delegation_scope_guard
- memory_write_guard
- mcp_manifest_firewall
- tool_call_policy_guard
- data_egress_preflight
- agent_budget_guard
- idempotency_replay_guard
- human_approval_policy
- secret_redaction_preflight
- oauth_token_audience_guard
- redirect_callback_validator
- tool_capability_drift_monitor
- mcp_server_identity_evidence
- agent_task_handoff_receipt
- context_provenance_labeler
- signed_result_comparator
- service_sla_attestation
- payment_route_selector
- x402_quote_comparator
- payment_receipt_reconciler
- duplicate_charge_detector
- subscription_spend_guard
- webhook_verifier
- delivery_evidence
- inter_agent_policy_evaluator
- concurrency_guard
- resource_cycle_guard
- abandoned_tool_detector
- manifest_version_diff
- dependency_provenance_assessment
- conflict_resolution
- data_freshness_certificate
- domain_ownership_evidence
- purpose_bound_consent
- retention_deletion_receipt
- interrupted_task_recovery
- portable_observability_audit
- rwa_asset_due_diligence
- rwa_compliance
- rwa_nav_reserve
- rwa_transaction_assurance
- rwa_corporate_actions
- rwa_sanctions_screening_evidence
- verified_web_extract
- entity_enrichment_evidence
- social_source_evidence
- market_data_snapshot
- onchain_evidence
- verified_news_monitor
- multi_source_fact_bundle
- document_to_verified_json
- source_backed_search
- live_data_freshness
- person_enrichment_evidence
- company_enrichment_evidence
- contact_enrichment_evidence
- mcp_2026_compatibility_gateway
- durable_agent_task
- task_checkpoint_evidence
- task_cancel_assurance
- agent_approval_relay
- capability_negotiation_preflight
- mcp_catalog_cache_guard
- oauth_issuer_binding_evidence
- mcp_a2a_task_bridge
- quote_freshness_guard
- delegated_credential_guard
- agent_session_continuity
- task_lease_guard
- tool_result_schema_validator
- agent_memory_provenance
- payment_delivery_atomicity
- service_failover_selector
- agent_rate_limit_negotiator
- execution_cost_estimator
- cross_agent_receipt_bundle
- capability_verification
- sybil_reputation_guard
- agent_behavior_fingerprint
- trust_anomaly_detector
- economic_loop_detector
- provider_quality_predictor
- transaction_risk_score
- payment_optimizer
- x402_v2_router
- erc8004_identity_evidence
- erc8004_reputation_intelligence
- delegated_spend_policy
- ap2_mandate_bridge
- a2a_transaction_bridge
- mcp_transaction_gateway
- proof_of_service
- automated_dispute_bundle
- transaction_recovery_v2
- reputation_update_receipt
- agent_economic_graph
- market_demand_predictor
- service_gap_detector
- price_discovery_engine
- sla_risk_predictor
- dynamic_service_pricing
- autonomous_procurement
- multi_agent_escrow
- cross_protocol_receipt
This list was read from the server itself, by connecting to it and calling tools/list on 24 September 2026. It is what
the server actually exposes, not what its listing claims.
Mutating and Read-only are read off each tool's name, not its schema — a hint, not a guarantee. The registry stores tool names only; connect the server for its live schemas.