Security Recipes

Measured conclusion: Deep-tested. L2 outcome: tools_ok.

Read-only CVE intelligence, remediation playbooks, and agent setup guides. Not a scanner.

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "Security Recipes": {
      "url": "https://security-recipes.ai/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (75)

• recipes_server_info

  Return MCP server metadata and source-index configuration.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recipes_mcp_upstream_servers

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

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recipes_mcp_servers_list

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

  Parameters:

  • limit — integer
  • query
  • availability

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recipes_mcp_server_get

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

  Parameters:

  • server_id (required) — string

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recipes_mcp_upstream_tools

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

  Parameters:

  • server_id (required) — string

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recipes_mcp_upstream_call

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

  Parameters:

  • server_id (required) — string
  • tool_name (required) — string
  • arguments

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recipes_mcp_upstream_context

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

  Parameters:

  • query (required) — string
  • max_chars — integer
  • server_ids

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recipes_refresh

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

  Parameters:

  • force — boolean

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recipes_search

  Full-text search over security-recipes documents.

  Parameters:

  • query (required) — string
  • tags
  • agent
  • limit
  • facets
  • section
  • min_quality

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recipes_list

  List recipes with optional metadata filtering.

  Parameters:

  • tags
  • agent
  • limit
  • facets
  • section
  • severity
  • min_quality

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recipes_get

  Get a full recipe record by slug or path.

  Parameters:

  • slug_or_path (required) — string

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recipes_playbooks_list

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

  Parameters:

  • limit — integer
  • query
  • category

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recipes_playbook_get

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

  Parameters:

  • playbook_id (required) — string

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recipes_playbook_plan

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

  Parameters:

  • playbook_id (required) — string
  • finding

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recipes_cve_catalog_info

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

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recipes_cve_search

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

  Parameters:

  • query (required) — string
  • limit — integer
  • kev_only — boolean
  • severity
  • published_year

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recipes_cve_get

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

  Parameters:

  • cve (required) — string

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recipes_quality_report

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

  Parameters:

  • tier
  • facet
  • limit

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recipes_workflow_control_plane

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

  Parameters:

  • workflow_id

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recipes_mcp_gateway_policy

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

  Parameters:

  • workflow_id

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recipes_agentic_assurance_pack

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

  Parameters:

  • control_id
  • workflow_id

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recipes_agent_identity_ledger

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

  Parameters:

  • agent_class
  • identity_id
  • workflow_id

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recipes_agentic_entitlement_review_pack

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

  Parameters:

  • namespace
  • risk_tier
  • access_mode
  • identity_id
  • workflow_id
  • entitlement_id

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recipes_agentic_approval_receipt_pack

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

  Parameters:

  • decision
  • risk_tier
  • workflow_id
  • action_class
  • approval_profile_id

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recipes_mcp_connector_trust_pack

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

  Parameters:

  • namespace
  • workflow_id
  • connector_id

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recipes_mcp_connector_intake_pack

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

  Parameters:

  • decision
  • namespace
  • candidate_id

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recipes_mcp_stdio_launch_boundary_pack

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

  Parameters:

  • decision
  • launch_id
  • profile_id

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recipes_mcp_authorization_conformance_pack

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

  Parameters:

  • decision
  • namespace
  • workflow_id
  • connector_id

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recipes_mcp_elicitation_boundary_pack

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

  Parameters:

  • mode
  • decision
  • risk_tier
  • profile_id
  • workflow_id

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recipes_mcp_tool_risk_contract

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

  Parameters:

  • decision
  • namespace
  • risk_tier
  • workflow_id
  • connector_id

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recipes_mcp_tool_surface_drift_pack

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

  Parameters:

  • decision
  • namespace
  • tool_name
  • surface_id
  • source_kind

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recipes_agentic_red_team_drill_pack

  Return adversarial drills for agentic remediation workflows and MCP controls.

  Parameters:

  • scenario_id
  • workflow_id
  • attack_family

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recipes_agentic_red_team_replay_harness

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

  Parameters:

  • severity
  • replay_id
  • scenario_id
  • workflow_id
  • attack_family

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recipes_agentic_readiness_scorecard

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

  Parameters:

  • decision
  • workflow_id
  • minimum_score

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recipes_agent_capability_risk_register

  Return capability-based residual risk scores for agentic workflows.

  Parameters:

  • decision
  • risk_tier
  • workflow_id
  • minimum_residual_score

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recipes_agent_memory_boundary_pack

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

  Parameters:

  • decision
  • persistent
  • workflow_id
  • memory_class_id

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recipes_agent_skill_supply_chain_pack

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

  Parameters:

  • decision
  • platform
  • skill_id
  • risk_tier
  • minimum_score

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recipes_agent_handoff_boundary_pack

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

  Parameters:

  • decision
  • protocol
  • profile_id
  • workflow_id

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recipes_a2a_agent_card_trust_profile

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

  Parameters:

  • decision
  • risk_tier
  • profile_id

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recipes_agentic_system_bom

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

  Parameters:

  • namespace
  • agent_class
  • workflow_id
  • component_type

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recipes_agentic_run_receipt_pack

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

  Parameters:

  • receipt_id
  • workflow_id
  • minimum_score

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recipes_secure_context_trust_pack

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

  Parameters:

  • decision
  • source_id
  • trust_tier
  • workflow_id

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recipes_secure_context_attestation_pack

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

  Parameters:

  • status
  • source_id
  • artifact_id
  • workflow_id
  • subject_type

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recipes_secure_context_lineage_ledger

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

  Parameters:

  • decision
  • stage_id
  • source_id
  • reuse_class
  • workflow_id

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recipes_secure_context_eval_pack

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

  Parameters:

  • decision
  • scenario_id
  • workflow_id
  • minimum_score
  • scenario_type

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recipes_context_poisoning_guard_pack

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

  Parameters:

  • limit
  • rule_id
  • decision
  • severity
  • source_id
  • actionable_only — boolean

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recipes_context_egress_boundary_pack

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

  Parameters:

  • source_id
  • data_class
  • workflow_id
  • destination_class

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recipes_agentic_threat_radar

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

  Parameters:

  • horizon
  • priority
  • signal_id
  • capability_id
  • minimum_score

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recipes_agentic_standards_crosswalk

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

  Parameters:

  • status
  • source_id
  • control_id
  • standard_id
  • capability_id

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recipes_agentic_source_freshness_watch

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

  Parameters:

  • decision
  • source_id
  • freshness_class
  • publisher_family
  • watched_source_id
  • source_class_family
  • primary_watchlist_id

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recipes_mcp_risk_coverage_pack

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

  Parameters:

  • status
  • risk_id
  • risk_tier
  • source_id
  • standard_id
  • capability_id

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recipes_agentic_protocol_conformance_pack

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

  Parameters:

  • check_id
  • decision
  • source_id
  • protocol_id

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recipes_agentic_control_plane_blueprint

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

  Parameters:

  • status
  • layer_id
  • question_id

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recipes_agentic_exposure_graph

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

  Parameters:

  • node_id
  • path_id
  • decision
  • namespace
  • identity_id
  • workflow_id
  • minimum_score
  • path_class_id

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recipes_agentic_posture_snapshot

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

  Parameters:

  • finding_id
  • workflow_id
  • minimum_score
  • risk_factor_id
  • posture_decision

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recipes_agentic_aivss_risk_scoring_pack

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

  Parameters:

  • owner
  • severity
  • scenario_id
  • minimum_score
  • runtime_default_decision

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recipes_agentic_app_intake_pack

  Return generated agentic app launch-review profiles and decisions.

  Parameters:

  • app_id
  • decision
  • risk_tier
  • buyer_stage
  • minimum_score

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recipes_model_provider_routing_pack

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

  Parameters:

  • decision
  • model_id
  • route_id
  • risk_tier
  • provider_id
  • workflow_id

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recipes_agentic_catastrophic_risk_annex

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

  Parameters:

  • status
  • control_id
  • scenario_id
  • buyer_view_id
  • impact_domain

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recipes_critical_infrastructure_secure_context_pack

  Return the generated critical-infrastructure secure-context profile.

  Parameters:

  • decision
  • sector_id
  • control_id
  • buyer_view_id
  • readiness_status

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recipes_agentic_incident_response_pack

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

  Parameters:

  • decision
  • severity
  • workflow_id
  • incident_class_id

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recipes_agentic_action_runtime_pack

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

  Parameters:

  • decision
  • risk_tier
  • workflow_id
  • action_class_id

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recipes_agent_trust_fabric_pack

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

  Parameters:

  • status
  • trust_tier
  • workflow_id
  • dimension_id

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recipes_browser_agent_boundary_pack

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

  Parameters:

  • decision
  • risk_tier
  • task_profile_id
  • workspace_class_id

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recipes_agentic_measurement_probe_pack

  Return measurement probes for agentic workflow traceability and readiness.

  Parameters:

  • status
  • class_id
  • decision
  • probe_id
  • workflow_id
  • minimum_score

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recipes_agentic_telemetry_contract

  Return the OpenTelemetry-aligned agentic telemetry and redaction contract.

  Parameters:

  • check_id
  • decision
  • workflow_id
  • signal_class_id
  • required_attribute

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recipes_agentic_soc_detection_pack

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

  Parameters:

  • rule_id
  • decision
  • severity
  • event_class
  • workflow_id

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recipes_enterprise_trust_center_export

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

  Parameters:

  • status
  • pack_id
  • category
  • section_id
  • question_id

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recipes_secure_context_value_model

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

  Parameters:

  • status
  • wedge_id
  • driver_id
  • segment_id
  • question_id
  • scenario_id

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recipes_design_partner_pilot_pack

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

  Parameters:

  • status
  • risk_id
  • phase_id
  • wedge_id
  • metric_id
  • segment_id
  • question_id

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recipes_secure_context_buyer_diligence_brief

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

  Parameters:

  • bet_id
  • status
  • buyer_id
  • source_id
  • question_id
  • objection_id

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recipes_secure_context_customer_proof_pack

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

  Parameters:

  • status
  • gate_id
  • risk_id
  • claim_id
  • event_id
  • metric_id

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recipes_secure_context_evidence_contract

  Return the secure context evidence API and release contract.

  Parameters:

  • status
  • channel_id
  • artifact_id
  • endpoint_id
  • object_type_id

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recipes_hosted_mcp_readiness_pack

  Return the hosted MCP readiness plan for enterprise product rollout.

  Parameters:

  • status
  • gate_id
  • risk_id
  • stage_id
  • control_id
  • buyer_evidence_id

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• recipes_match_finding

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

  Parameters:

  • cve
  • limit — integer
  • facets
  • package
  • rule_id
  • keywords
  • ecosystem
  • min_quality

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

Publisher website Repository

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.