Security Recipes
by stevologic · remote · no sign-in to list tools · v1.0.0 · published by GitHub user stevologic
Read-only CVE intelligence, remediation playbooks, and agent setup guides. Not a scanner.
Changes · 6
75 tools: 6 change things and 69 only read.
Scanned Oct 21, 2026
- Deletes or cancels0Claude Code: deny
- Can't be undone0Claude Code: ask
- Changes things6Claude Code: ask: see these tools
- Only reads69Claude Code: allow: see these tools
No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.
claude mcp add --transport http security-recipes https://security-recipes.ai/mcpTools
Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.
75 tools
Changes things 6Claude Code: ask
recipes_agentic_run_receipt_packReturn agent run receipt templates for identity, context, tools, egress, approval, and evidence.No findings
Why it is in this group
- The name "recipes_agentic_run_receipt_pack" says "run": a word for a change.
Description, as the server wrote it Return agent run receipt templates for identity, context, tools, egress, approval, and evidence.
recipes_match_findingHeuristic matcher that suggests best-fit recipes for a security finding.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Heuristic matcher that suggests best-fit recipes for a security finding.
recipes_mcp_upstream_callCall an allowed read-only tool on a configured upstream MCP server.No findings
Why it is in this group
- The name "recipes_mcp_upstream_call" says "call": a word for a change.
Description, as the server wrote it Call an allowed read-only tool on a configured upstream MCP server.
recipes_mcp_upstream_contextCollect bounded context from configured upstream MCP servers for a remediation query.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Collect bounded context from configured upstream MCP servers for a remediation query.
recipes_playbook_planBuild a deterministic, read-only phase, gate, and evidence checklist for a finding.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Build a deterministic, read-only phase, gate, and evidence checklist for a finding.
recipes_refreshRefresh the in-memory copy of recipes-index.json.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Refresh the in-memory copy of recipes-index.json.
Only reads 69Claude Code: allow
recipes_a2a_agent_card_trust_profileReturn A2A Agent Card intake profiles, trust controls, and sample decisions.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it Return A2A Agent Card intake profiles, trust controls, and sample decisions.
recipes_agent_capability_risk_registerReturn capability-based residual risk scores for agentic workflows.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it Return capability-based residual risk scores for agentic workflows.
recipes_agent_handoff_boundary_packReturn agent handoff boundary profiles, protocol controls, and workflow maps.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it Return agent handoff boundary profiles, protocol controls, and workflow maps.
recipes_agent_identity_ledgerReturn agent non-human identity, delegation, scope, and audit contracts.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it Return agent non-human identity, delegation, scope, and audit contracts.
recipes_agent_memory_boundary_packReturn agent memory classes, workflow profiles, TTLs, and persistence decisions.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it Return agent memory classes, workflow profiles, TTLs, and persistence decisions.
recipes_agent_skill_supply_chain_packReturn agent skill provenance, permission, isolation, and supply-chain decisions.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it Return agent skill provenance, permission, isolation, and supply-chain decisions.
recipes_agent_trust_fabric_packReturn Agent Trust Fabric dimensions, workflow tiers, source evidence, and buyer proof.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it Return Agent Trust Fabric dimensions, workflow tiers, source evidence, and buyer proof.
recipes_agentic_action_runtime_packReturn action classes, workflow action envelopes, runtime policy, and evidence.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it Return action classes, workflow action envelopes, runtime policy, and evidence.
recipes_agentic_aivss_risk_scoring_packReturn AIVSS-aligned agentic risk scores, SLAs, evidence, and hosted MCP wedges.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it Return AIVSS-aligned agentic risk scores, SLAs, evidence, and hosted MCP wedges.
recipes_agentic_app_intake_packReturn generated agentic app launch-review profiles and decisions.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it Return generated agentic app launch-review profiles and decisions.
recipes_agentic_approval_receipt_packReturn scope-bound approval receipt profiles, workflow requirements, and evidence.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it Return scope-bound approval receipt profiles, workflow requirements, and evidence.
recipes_agentic_assurance_packReturn enterprise assurance controls, workflow evidence, and AI/Agent BOM seed.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it Return enterprise assurance controls, workflow evidence, and AI/Agent BOM seed.
recipes_agentic_catastrophic_risk_annexReturn the severe-risk annex for high-impact agentic AI runtime decisions.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it Return the severe-risk annex for high-impact agentic AI runtime decisions.
recipes_agentic_control_plane_blueprintReturn the acquisition-ready agentic control plane architecture and buyer evidence map.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it Return the acquisition-ready agentic control plane architecture and buyer evidence map.
recipes_agentic_entitlement_review_packReturn expiring agent entitlement leases, access reviews, and scope evidence.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it Return expiring agent entitlement leases, access reviews, and scope evidence.
recipes_agentic_exposure_graphReturn risk-ranked agentic exposure paths across context, identities, MCP tools, and evidence.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it Return risk-ranked agentic exposure paths across context, identities, MCP tools, and evidence.
recipes_agentic_incident_response_packReturn agentic incident response classes, phases, workflow matrix, and evidence.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it Return agentic incident response classes, phases, workflow matrix, and evidence.
recipes_agentic_measurement_probe_packReturn measurement probes for agentic workflow traceability and readiness.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it Return measurement probes for agentic workflow traceability and readiness.
recipes_agentic_posture_snapshotReturn the generated enterprise posture snapshot for agentic AI and MCP operations.No findings
Why it is in this group
- The name "recipes_agentic_posture_snapshot" says "snapshot": a word for reading.
Description, as the server wrote it Return the generated enterprise posture snapshot for agentic AI and MCP operations.
recipes_agentic_protocol_conformance_packReturn MCP/A2A protocol conformance evidence and buyer-ready drift controls.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it Return MCP/A2A protocol conformance evidence and buyer-ready drift controls.
recipes_agentic_readiness_scorecardReturn generated scale, pilot, gate, or block decisions for agentic workflows.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it Return generated scale, pilot, gate, or block decisions for agentic workflows.
recipes_agentic_red_team_drill_packReturn adversarial drills for agentic remediation workflows and MCP controls.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it Return adversarial drills for agentic remediation workflows and MCP controls.
recipes_agentic_red_team_replay_harnessReturn replay fixtures, expected decisions, and evidence gates for red-team drills.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it Return replay fixtures, expected decisions, and evidence gates for red-team drills.
recipes_agentic_soc_detection_packReturn SIEM-ready detections for agentic AI and MCP telemetry.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it Return SIEM-ready detections for agentic AI and MCP telemetry.
recipes_agentic_source_freshness_watchReturn source-freshness and standards-drift evidence for SecurityRecipes.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it Return source-freshness and standards-drift evidence for SecurityRecipes.
recipes_agentic_standards_crosswalkReturn standards-to-evidence mappings for agentic AI, MCP, and prompt-injection guidance.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it Return standards-to-evidence mappings for agentic AI, MCP, and prompt-injection guidance.
recipes_agentic_system_bomReturn the Agentic System BOM for workflows, agents, identities, MCP tools, and evidence.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it Return the Agentic System BOM for workflows, agents, identities, MCP tools, and evidence.
recipes_agentic_telemetry_contractReturn the OpenTelemetry-aligned agentic telemetry and redaction contract.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it Return the OpenTelemetry-aligned agentic telemetry and redaction contract.
recipes_agentic_threat_radarReturn current source-backed agentic AI threat signals and product priorities.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it Return current source-backed agentic AI threat signals and product priorities.
recipes_browser_agent_boundary_packReturn browser-agent workspace classes, task profiles, controls, and evidence.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it Return browser-agent workspace classes, task profiles, controls, and evidence.
recipes_context_egress_boundary_packReturn context egress data classes, destination classes, and workflow boundary policy.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it Return context egress data classes, destination classes, and workflow boundary policy.
recipes_context_poisoning_guard_packReturn context-poisoning scan results for registered secure-context sources.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it Return context-poisoning scan results for registered secure-context sources.
recipes_critical_infrastructure_secure_context_packReturn the generated critical-infrastructure secure-context profile.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it Return the generated critical-infrastructure secure-context profile.
recipes_cve_catalog_infoReturn the complete Medium/High/Critical CVE catalog scope, coverage, provenance, and counts.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it Return the complete Medium/High/Critical CVE catalog scope, coverage, provenance, and counts.
recipes_cve_getGet evidence, recipe authority, and a bounded code/config/file change plan for one exact CVE.No findings
Why it is in this group
- The name "recipes_cve_get" says "get": a word for reading.
Description, as the server wrote it Get evidence, recipe authority, and a bounded code/config/file change plan for one exact CVE.
recipes_cve_searchSearch every in-scope Medium/High/Critical CVE; use recipes_cve_get for complete details.No findings
Why it is in this group
- The name "recipes_cve_search" says "search": a word for reading.
Description, as the server wrote it Search every in-scope Medium/High/Critical CVE; use recipes_cve_get for complete details.
recipes_design_partner_pilot_packReturn the design partner pilot motion for buyer proof and hosted MCP validation.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it Return the design partner pilot motion for buyer proof and hosted MCP validation.
recipes_enterprise_trust_center_exportReturn the bundled enterprise trust-center export for buyer and platform diligence.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it Return the bundled enterprise trust-center export for buyer and platform diligence.
recipes_getGet a full recipe record by slug or path.No findings
Why it is in this group
- The name "recipes_get" says "get": a word for reading.
Description, as the server wrote it Get a full recipe record by slug or path.
recipes_hosted_mcp_readiness_packReturn the hosted MCP readiness plan for enterprise product rollout.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it Return the hosted MCP readiness plan for enterprise product rollout.
recipes_listList recipes with optional metadata filtering.No findings
Why it is in this group
- The name "recipes_list" says "list": a word for reading.
Description, as the server wrote it List recipes with optional metadata filtering.
recipes_mcp_authorization_conformance_packReturn MCP authorization conformance, scope-drift, and token-boundary evidence.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it Return MCP authorization conformance, scope-drift, and token-boundary evidence.
recipes_mcp_connector_intake_packReturn MCP connector intake decisions, risk findings, gaps, and promotion plans.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it Return MCP connector intake decisions, risk findings, gaps, and promotion plans.
recipes_mcp_connector_trust_packReturn MCP connector trust tiers, controls, evidence, and workflow namespace coverage.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it Return MCP connector trust tiers, controls, evidence, and workflow namespace coverage.
recipes_mcp_elicitation_boundary_packReturn MCP form-mode and URL-mode elicitation boundary evidence.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it Return MCP form-mode and URL-mode elicitation boundary evidence.
recipes_mcp_gateway_policyReturn generated MCP gateway policy for scoped tool access and runtime controls.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it Return generated MCP gateway policy for scoped tool access and runtime controls.
recipes_mcp_risk_coverage_packReturn OWASP MCP and agentic-skill risk coverage mapped to generated evidence.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it Return OWASP MCP and agentic-skill risk coverage mapped to generated evidence.
recipes_mcp_server_getReturn one publicly documented MCP server with official setup and safety guidance.No findings
Why it is in this group
- The name "recipes_mcp_server_get" says "get": a word for reading.
Description, as the server wrote it Return one publicly documented MCP server with official setup and safety guidance.
recipes_mcp_servers_listSearch the bundled catalog of publicly documented MCP servers and ecosystems.No findings
Why it is in this group
- The name "recipes_mcp_servers_list" says "list": a word for reading.
Description, as the server wrote it Search the bundled catalog of publicly documented MCP servers and ecosystems.
recipes_mcp_stdio_launch_boundary_packReturn MCP STDIO launch boundaries, profiles, decisions, and evidence.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it Return MCP STDIO launch boundaries, profiles, decisions, and evidence.
recipes_mcp_tool_risk_contractReturn MCP tool annotation, trust, and session-combination risk evidence.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it Return MCP tool annotation, trust, and session-combination risk evidence.
recipes_mcp_tool_surface_drift_packReturn pinned MCP tool descriptions, schemas, annotations, and drift evidence.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it Return pinned MCP tool descriptions, schemas, annotations, and drift evidence.
recipes_mcp_upstream_serversList optional upstream MCP servers configured for this Security Recipes server.No findings
Why it is in this group
- The description's first verb is "list": a word for reading.
Description, as the server wrote it List optional upstream MCP servers configured for this Security Recipes server.
recipes_mcp_upstream_toolsList tools exposed by a configured upstream MCP server and show local allow decisions.No findings
Why it is in this group
- The description's first verb is "list": a word for reading.
Description, as the server wrote it List tools exposed by a configured upstream MCP server and show local allow decisions.
recipes_model_provider_routing_packReturn model-provider route profiles, workflow mappings, and required evidence.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it Return model-provider route profiles, workflow mappings, and required evidence.
recipes_playbook_getGet one complete remediation workflow, evidence, output, and Python contract.No findings
Why it is in this group
- The name "recipes_playbook_get" says "get": a word for reading.
Description, as the server wrote it Get one complete remediation workflow, evidence, output, and Python contract.
recipes_playbooks_listList concise remediation playbook records, optionally filtered by query or category.No findings
Why it is in this group
- The name "recipes_playbooks_list" says "list": a word for reading.
Description, as the server wrote it List concise remediation playbook records, optionally filtered by query or category.
recipes_quality_reportSummarize recipe quality tiers and list recipes missing world-class signals.No findings
Why it is in this group
- The description's first verb is "summarize": a word for reading.
Description, as the server wrote it Summarize recipe quality tiers and list recipes missing world-class signals.
recipes_searchFull-text search over security-recipes documents.No findings
Why it is in this group
- The name "recipes_search" says "search": a word for reading.
Description, as the server wrote it Full-text search over security-recipes documents.
recipes_secure_context_attestation_packReturn secure-context attestation subjects, verification policy, and recertification state.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it Return secure-context attestation subjects, verification policy, and recertification state.
recipes_secure_context_buyer_diligence_briefReturn buyer and acquirer diligence evidence for the secure context layer.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it Return buyer and acquirer diligence evidence for the secure context layer.
recipes_secure_context_customer_proof_packReturn the customer proof contract for design partner and acquisition evidence.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it Return the customer proof contract for design partner and acquisition evidence.
recipes_secure_context_eval_packReturn scenario-backed secure-context evals for retrieval, attestation, egress, and handoffs.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it Return scenario-backed secure-context evals for retrieval, attestation, egress, and handoffs.
recipes_secure_context_evidence_contractReturn the secure context evidence API and release contract.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it Return the secure context evidence API and release contract.
recipes_secure_context_lineage_ledgerReturn context lineage, reuse policy, stage requirements, hashes, and workflow envelopes.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it Return context lineage, reuse policy, stage requirements, hashes, and workflow envelopes.
recipes_secure_context_trust_packReturn context provenance, retrieval policy, source hashes, and workflow context packages.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it Return context provenance, retrieval policy, source hashes, and workflow context packages.
recipes_secure_context_value_modelReturn the secure context value model for buyer, ROI, and acquisition diligence.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it Return the secure context value model for buyer, ROI, and acquisition diligence.
recipes_server_infoReturn MCP server metadata and source-index configuration.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it Return MCP server metadata and source-index configuration.
recipes_workflow_control_planeReturn workflow control-plane policy for agents, reviewers, and MCP gateways.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it Return workflow control-plane policy for agents, reviewers, and MCP gateways.
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http security-recipes https://security-recipes.ai/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__security-recipes__recipes_server_info",
"mcp__security-recipes__recipes_mcp_upstream_servers",
"mcp__security-recipes__recipes_mcp_servers_list",
"mcp__security-recipes__recipes_mcp_server_get",
"mcp__security-recipes__recipes_mcp_upstream_tools",
"mcp__security-recipes__recipes_search",
"mcp__security-recipes__recipes_list",
"mcp__security-recipes__recipes_get",
"mcp__security-recipes__recipes_playbooks_list",
"mcp__security-recipes__recipes_playbook_get",
"mcp__security-recipes__recipes_cve_catalog_info",
"mcp__security-recipes__recipes_cve_search",
"mcp__security-recipes__recipes_cve_get",
"mcp__security-recipes__recipes_quality_report",
"mcp__security-recipes__recipes_workflow_control_plane",
"mcp__security-recipes__recipes_mcp_gateway_policy",
"mcp__security-recipes__recipes_agentic_assurance_pack",
"mcp__security-recipes__recipes_agent_identity_ledger",
"mcp__security-recipes__recipes_agentic_entitlement_review_pack",
"mcp__security-recipes__recipes_agentic_approval_receipt_pack",
"mcp__security-recipes__recipes_mcp_connector_trust_pack",
"mcp__security-recipes__recipes_mcp_connector_intake_pack",
"mcp__security-recipes__recipes_mcp_stdio_launch_boundary_pack",
"mcp__security-recipes__recipes_mcp_authorization_conformance_pack",
"mcp__security-recipes__recipes_mcp_elicitation_boundary_pack",
"mcp__security-recipes__recipes_mcp_tool_risk_contract",
"mcp__security-recipes__recipes_mcp_tool_surface_drift_pack",
"mcp__security-recipes__recipes_agentic_red_team_drill_pack",
"mcp__security-recipes__recipes_agentic_red_team_replay_harness",
"mcp__security-recipes__recipes_agentic_readiness_scorecard",
"mcp__security-recipes__recipes_agent_capability_risk_register",
"mcp__security-recipes__recipes_agent_memory_boundary_pack",
"mcp__security-recipes__recipes_agent_skill_supply_chain_pack",
"mcp__security-recipes__recipes_agent_handoff_boundary_pack",
"mcp__security-recipes__recipes_a2a_agent_card_trust_profile",
"mcp__security-recipes__recipes_agentic_system_bom",
"mcp__security-recipes__recipes_secure_context_trust_pack",
"mcp__security-recipes__recipes_secure_context_attestation_pack",
"mcp__security-recipes__recipes_secure_context_lineage_ledger",
"mcp__security-recipes__recipes_secure_context_eval_pack",
"mcp__security-recipes__recipes_context_poisoning_guard_pack",
"mcp__security-recipes__recipes_context_egress_boundary_pack",
"mcp__security-recipes__recipes_agentic_threat_radar",
"mcp__security-recipes__recipes_agentic_standards_crosswalk",
"mcp__security-recipes__recipes_agentic_source_freshness_watch",
"mcp__security-recipes__recipes_mcp_risk_coverage_pack",
"mcp__security-recipes__recipes_agentic_protocol_conformance_pack",
"mcp__security-recipes__recipes_agentic_control_plane_blueprint",
"mcp__security-recipes__recipes_agentic_exposure_graph",
"mcp__security-recipes__recipes_agentic_posture_snapshot",
"mcp__security-recipes__recipes_agentic_aivss_risk_scoring_pack",
"mcp__security-recipes__recipes_agentic_app_intake_pack",
"mcp__security-recipes__recipes_model_provider_routing_pack",
"mcp__security-recipes__recipes_agentic_catastrophic_risk_annex",
"mcp__security-recipes__recipes_critical_infrastructure_secure_context_pack",
"mcp__security-recipes__recipes_agentic_incident_response_pack",
"mcp__security-recipes__recipes_agentic_action_runtime_pack",
"mcp__security-recipes__recipes_agent_trust_fabric_pack",
"mcp__security-recipes__recipes_browser_agent_boundary_pack",
"mcp__security-recipes__recipes_agentic_measurement_probe_pack",
"mcp__security-recipes__recipes_agentic_telemetry_contract",
"mcp__security-recipes__recipes_agentic_soc_detection_pack",
"mcp__security-recipes__recipes_enterprise_trust_center_export",
"mcp__security-recipes__recipes_secure_context_value_model",
"mcp__security-recipes__recipes_design_partner_pilot_pack",
"mcp__security-recipes__recipes_secure_context_buyer_diligence_brief",
"mcp__security-recipes__recipes_secure_context_customer_proof_pack",
"mcp__security-recipes__recipes_secure_context_evidence_contract",
"mcp__security-recipes__recipes_hosted_mcp_readiness_pack"
],
"ask": [
"mcp__security-recipes__recipes_mcp_upstream_call",
"mcp__security-recipes__recipes_mcp_upstream_context",
"mcp__security-recipes__recipes_refresh",
"mcp__security-recipes__recipes_playbook_plan",
"mcp__security-recipes__recipes_agentic_run_receipt_pack",
"mcp__security-recipes__recipes_match_finding"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as security-recipes. Review it before you use it.