Security Recipes MCP server

• recipes_a2a_agent_card_trust_profileFree

  Return A2A Agent Card intake profiles, trust controls, and sample decisions.

• recipes_agent_capability_risk_registerFree

  Return capability-based residual risk scores for agentic workflows.

• recipes_agent_handoff_boundary_packFree

  Return agent handoff boundary profiles, protocol controls, and workflow maps.

• recipes_agent_identity_ledgerFree

  Return agent non-human identity, delegation, scope, and audit contracts.

• recipes_agent_memory_boundary_packFree

  Return agent memory classes, workflow profiles, TTLs, and persistence decisions.

• recipes_agent_skill_supply_chain_packFree

  Return agent skill provenance, permission, isolation, and supply-chain decisions.

• recipes_agent_trust_fabric_packFree

  Return Agent Trust Fabric dimensions, workflow tiers, source evidence, and buyer proof.

• recipes_agentic_action_runtime_packFree

  Return action classes, workflow action envelopes, runtime policy, and evidence.

• recipes_agentic_aivss_risk_scoring_packFree

  Return AIVSS-aligned agentic risk scores, SLAs, evidence, and hosted MCP wedges.

• recipes_agentic_app_intake_packFree

  Return generated agentic app launch-review profiles and decisions.

• recipes_agentic_approval_receipt_packFree

  Return scope-bound approval receipt profiles, workflow requirements, and evidence.

• recipes_agentic_assurance_packFree

  Return enterprise assurance controls, workflow evidence, and AI/Agent BOM seed.

• recipes_agentic_catastrophic_risk_annexFree

  Return the severe-risk annex for high-impact agentic AI runtime decisions.

• recipes_agentic_control_plane_blueprintFree

  Return the acquisition-ready agentic control plane architecture and buyer evidence map.

• recipes_agentic_entitlement_review_packFree

  Return expiring agent entitlement leases, access reviews, and scope evidence.

• recipes_agentic_exposure_graphFree

  Return risk-ranked agentic exposure paths across context, identities, MCP tools, and evidence.

• recipes_agentic_incident_response_packFree

  Return agentic incident response classes, phases, workflow matrix, and evidence.

• recipes_agentic_measurement_probe_packFree

  Return measurement probes for agentic workflow traceability and readiness.

• recipes_agentic_posture_snapshotFree

  Return the generated enterprise posture snapshot for agentic AI and MCP operations.

• recipes_agentic_protocol_conformance_packFree

  Return MCP/A2A protocol conformance evidence and buyer-ready drift controls.

• recipes_agentic_readiness_scorecardFree

  Return generated scale, pilot, gate, or block decisions for agentic workflows.

• recipes_agentic_red_team_drill_packFree

  Return adversarial drills for agentic remediation workflows and MCP controls.

• recipes_agentic_red_team_replay_harnessFree

  Return replay fixtures, expected decisions, and evidence gates for red-team drills.

• recipes_agentic_run_receipt_packwrite actionFree

  Return agent run receipt templates for identity, context, tools, egress, approval, and evidence.

• recipes_agentic_soc_detection_packFree

  Return SIEM-ready detections for agentic AI and MCP telemetry.

• recipes_agentic_source_freshness_watchFree

  Return source-freshness and standards-drift evidence for SecurityRecipes.

• recipes_agentic_standards_crosswalkFree

  Return standards-to-evidence mappings for agentic AI, MCP, and prompt-injection guidance.

• recipes_agentic_system_bomFree

  Return the Agentic System BOM for workflows, agents, identities, MCP tools, and evidence.

• recipes_agentic_telemetry_contractFree

  Return the OpenTelemetry-aligned agentic telemetry and redaction contract.

• recipes_agentic_threat_radarFree

  Return current source-backed agentic AI threat signals and product priorities.

• recipes_browser_agent_boundary_packFree

  Return browser-agent workspace classes, task profiles, controls, and evidence.

• recipes_context_egress_boundary_packFree

  Return context egress data classes, destination classes, and workflow boundary policy.

• recipes_context_poisoning_guard_packFree

  Return context-poisoning scan results for registered secure-context sources.

• recipes_critical_infrastructure_secure_context_packFree

  Return the generated critical-infrastructure secure-context profile.

• recipes_cve_catalog_infoFree

  Return the complete Medium/High/Critical CVE catalog scope, coverage, provenance, and counts.

• recipes_cve_getFree

  Get evidence, recipe authority, and a bounded code/config/file change plan for one exact CVE.

• recipes_cve_searchFree

  Search every in-scope Medium/High/Critical CVE; use recipes_cve_get for complete details.

• recipes_design_partner_pilot_packFree

  Return the design partner pilot motion for buyer proof and hosted MCP validation.

• recipes_enterprise_trust_center_exportFree

  Return the bundled enterprise trust-center export for buyer and platform diligence.

• recipes_getFree

  Get a full recipe record by slug or path.

• recipes_hosted_mcp_readiness_packFree

  Return the hosted MCP readiness plan for enterprise product rollout.

• recipes_listFree

  List recipes with optional metadata filtering.

• recipes_match_findingFree

  Heuristic matcher that suggests best-fit recipes for a security finding.

• recipes_mcp_authorization_conformance_packFree

  Return MCP authorization conformance, scope-drift, and token-boundary evidence.

• recipes_mcp_connector_intake_packFree

  Return MCP connector intake decisions, risk findings, gaps, and promotion plans.

• recipes_mcp_connector_trust_packFree

  Return MCP connector trust tiers, controls, evidence, and workflow namespace coverage.

• recipes_mcp_elicitation_boundary_packFree

  Return MCP form-mode and URL-mode elicitation boundary evidence.

• recipes_mcp_gateway_policyFree

  Return generated MCP gateway policy for scoped tool access and runtime controls.

• recipes_mcp_risk_coverage_packFree

  Return OWASP MCP and agentic-skill risk coverage mapped to generated evidence.

• recipes_mcp_server_getFree

  Return one publicly documented MCP server with official setup and safety guidance.

• recipes_mcp_servers_listFree

  Search the bundled catalog of publicly documented MCP servers and ecosystems.

• recipes_mcp_stdio_launch_boundary_packFree

  Return MCP STDIO launch boundaries, profiles, decisions, and evidence.

• recipes_mcp_tool_risk_contractFree

  Return MCP tool annotation, trust, and session-combination risk evidence.

• recipes_mcp_tool_surface_drift_packFree

  Return pinned MCP tool descriptions, schemas, annotations, and drift evidence.

• recipes_mcp_upstream_callFree

  Call an allowed read-only tool on a configured upstream MCP server.

• recipes_mcp_upstream_contextFree

  Collect bounded context from configured upstream MCP servers for a remediation query.

• recipes_mcp_upstream_serversFree

  List optional upstream MCP servers configured for this Security Recipes server.

• recipes_mcp_upstream_toolsFree

  List tools exposed by a configured upstream MCP server and show local allow decisions.

• recipes_model_provider_routing_packFree

  Return model-provider route profiles, workflow mappings, and required evidence.

• recipes_playbook_getFree

  Get one complete remediation workflow, evidence, output, and Python contract.

• recipes_playbook_planFree

  Build a deterministic, read-only phase, gate, and evidence checklist for a finding.

• recipes_playbooks_listFree

  List concise remediation playbook records, optionally filtered by query or category.

• recipes_quality_reportFree

  Summarize recipe quality tiers and list recipes missing world-class signals.

• recipes_refreshFree

  Refresh the in-memory copy of recipes-index.json.

• recipes_searchFree

  Full-text search over security-recipes documents.

• recipes_secure_context_attestation_packFree

  Return secure-context attestation subjects, verification policy, and recertification state.

• recipes_secure_context_buyer_diligence_briefFree

  Return buyer and acquirer diligence evidence for the secure context layer.

• recipes_secure_context_customer_proof_packFree

  Return the customer proof contract for design partner and acquisition evidence.

• recipes_secure_context_eval_packFree

  Return scenario-backed secure-context evals for retrieval, attestation, egress, and handoffs.

• recipes_secure_context_evidence_contractFree

  Return the secure context evidence API and release contract.

• recipes_secure_context_lineage_ledgerFree

  Return context lineage, reuse policy, stage requirements, hashes, and workflow envelopes.

• recipes_secure_context_trust_packFree

  Return context provenance, retrieval policy, source hashes, and workflow context packages.

• recipes_secure_context_value_modelFree

  Return the secure context value model for buyer, ROI, and acquisition diligence.

• recipes_server_infoFree

  Return MCP server metadata and source-index configuration.

• recipes_workflow_control_planeFree

  Return workflow control-plane policy for agents, reviewers, and MCP gateways.

• –Code scanremote-only server, no package to scann/a
• Live reliabilityremote reachable in 537ms20/20
• Tool poisoning75 tool descriptions checked15/15
• Auth qualityopen endpoint exposes 1 write-action tools with no auth3/15
• Maintenancelast push 0 days ago15/15
• Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10

Safety score

81/100

higher than 63% of 4,460 AI and agents servers

Tools

75

the typical AI and agents server has 6

Tools that change things

1%

typical: 0%. Fewer write tools means less an agent can break

Uptime

100%

of our recent checks; the typical remote AI and agents server answers 100%

Response time

629 ms

faster than 20% of 2,331 AI and agents servers

GitHub stars

2

more than 65% of 2,711 AI and agents servers

Security Recipes: common questions

Is Security Recipes MCP server safe?

Mostly: it is graded B (81/100). Read the Security Recipes safety report

How do I install Security Recipes?

It runs remotely at security-recipes.ai. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.

Does Security Recipes need an API key?

Not as far as the registry entry and our scan can tell: no credentials are declared or required.

Is Security Recipes maintained?

The last commit was 4 days ago (2026-10-31). The latest release is v1.0.0.

Is Security Recipes up?

100% of our last 28 checks got an answer. We check remote servers about four times a day.

What can I use instead of Security Recipes?

Servers from other publishers that do the same job: Agent Security Scanner MCP server, HOL Guard MCP server and Pm Claude Skills MCP server.

How does Security Recipes compare with other AI and agents MCP servers?

safety score 81/100 (higher than 63% of 4,460 AI and agents servers); tools 75 (the typical AI and agents server has 6); tools that change things 1% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.