Read-only CVE intelligence, remediation playbooks, and agent setup guides. Not a scanner.
Scored across 75 tools
The set contains many similarly named agentic security packs that return overlapping profiles, evidence, controls, and decisions, making boundaries hard to distinguish. Some tools are clearly distinct (CVE lookup, MCP upstream access, recipe list/get/search), but the large cluster of 'agentic_*_pack' tools creates significant misselection risk.
All tools use the recipes_ prefix and snake_case, which is highly consistent. However, the naming mixes descriptive noun phrases with verbs such as get, list, search, match, and refresh, so it is not a single predictable verb_noun pattern.
With 75 tools, the surface is far beyond a well-scoped set and well into extreme mismatch territory. Even if each tool maps to a distinct security artifact, the sheer volume makes discovery and selection costly for an agent.
The server covers a broad content domain: recipes can be listed, searched, fetched, matched, refreshed, and quality-reported; CVEs, playbooks, MCP servers, and upstream MCP interactions also have dedicated tools. Minor gaps may exist around write/update lifecycle operations, but for a read-oriented security recipes server the retrieval surface is largely complete.
Return A2A Agent Card intake profiles, trust controls, and sample decisions.
Inputs: decision, risk_tier, profile_id. Returns: object
Return capability-based residual risk scores for agentic workflows.
Inputs: decision, risk_tier, workflow_id, minimum_residual_score. Returns: object
Return agent handoff boundary profiles, protocol controls, and workflow maps.
Inputs: decision, protocol, profile_id, workflow_id. Returns: object
Return action classes, workflow action envelopes, runtime policy, and evidence.
Inputs: decision, risk_tier, workflow_id, action_class_id. Returns: object
Return AIVSS-aligned agentic risk scores, SLAs, evidence, and hosted MCP wedges.
Inputs: owner, severity, scenario_id, minimum_score, +1 more. Returns: object
Return generated agentic app launch-review profiles and decisions.
Inputs: app_id, decision, risk_tier, buyer_stage, +1 more. Returns: object
Return scope-bound approval receipt profiles, workflow requirements, and evidence.
Inputs: decision, risk_tier, workflow_id, action_class, +1 more. Returns: object
Return enterprise assurance controls, workflow evidence, and AI/Agent BOM seed.
Inputs: control_id, workflow_id. Returns: object
Return the severe-risk annex for high-impact agentic AI runtime decisions.
Inputs: status, control_id, scenario_id, buyer_view_id, +1 more. Returns: object
Return the acquisition-ready agentic control plane architecture and buyer evidence map.
Inputs: status, layer_id, question_id. Returns: object
Return expiring agent entitlement leases, access reviews, and scope evidence.
Inputs: namespace, risk_tier, access_mode, identity_id, +2 more. Returns: object
Return risk-ranked agentic exposure paths across context, identities, MCP tools, and evidence.
Inputs: node_id, path_id, decision, namespace, +4 more. Returns: object
Return agentic incident response classes, phases, workflow matrix, and evidence.
Inputs: decision, severity, workflow_id, incident_class_id. Returns: object
Return measurement probes for agentic workflow traceability and readiness.
Inputs: status, class_id, decision, probe_id, +2 more. Returns: object
Return the generated enterprise posture snapshot for agentic AI and MCP operations.
Inputs: finding_id, workflow_id, minimum_score, risk_factor_id, +1 more. Returns: object
Return MCP/A2A protocol conformance evidence and buyer-ready drift controls.
Inputs: check_id, decision, source_id, protocol_id. Returns: object
Return generated scale, pilot, gate, or block decisions for agentic workflows.
Inputs: decision, workflow_id, minimum_score. Returns: object
Return adversarial drills for agentic remediation workflows and MCP controls.
Inputs: scenario_id, workflow_id, attack_family. Returns: object
Return replay fixtures, expected decisions, and evidence gates for red-team drills.
Inputs: severity, replay_id, scenario_id, workflow_id, +1 more. Returns: object
Return agent run receipt templates for identity, context, tools, egress, approval, and evidence.
Inputs: receipt_id, workflow_id, minimum_score. Returns: object
Return SIEM-ready detections for agentic AI and MCP telemetry.
Inputs: rule_id, decision, severity, event_class, +1 more. Returns: object
Return source-freshness and standards-drift evidence for SecurityRecipes.
Inputs: decision, source_id, freshness_class, publisher_family, +3 more. Returns: object
Return standards-to-evidence mappings for agentic AI, MCP, and prompt-injection guidance.
Inputs: status, source_id, control_id, standard_id, +1 more. Returns: object
Return the Agentic System BOM for workflows, agents, identities, MCP tools, and evidence.
Inputs: namespace, agent_class, workflow_id, component_type. Returns: object
Return the OpenTelemetry-aligned agentic telemetry and redaction contract.
Inputs: check_id, decision, workflow_id, signal_class_id, +1 more. Returns: object
Return current source-backed agentic AI threat signals and product priorities.
Inputs: horizon, priority, signal_id, capability_id, +1 more. Returns: object
Return agent non-human identity, delegation, scope, and audit contracts.
Inputs: agent_class, identity_id, workflow_id. Returns: object
Return agent memory classes, workflow profiles, TTLs, and persistence decisions.
Inputs: decision, persistent, workflow_id, memory_class_id. Returns: object
Return agent skill provenance, permission, isolation, and supply-chain decisions.
Inputs: decision, platform, skill_id, risk_tier, +1 more. Returns: object
Return Agent Trust Fabric dimensions, workflow tiers, source evidence, and buyer proof.
Inputs: status, trust_tier, workflow_id, dimension_id. Returns: object
Return browser-agent workspace classes, task profiles, controls, and evidence.
Inputs: decision, risk_tier, task_profile_id, workspace_class_id. Returns: object
Return context egress data classes, destination classes, and workflow boundary policy.
Inputs: source_id, data_class, workflow_id, destination_class. Returns: object
Return context-poisoning scan results for registered secure-context sources.
Inputs: limit, rule_id, decision, severity, +2 more. Returns: object
Return the generated critical-infrastructure secure-context profile.
Inputs: decision, sector_id, control_id, buyer_view_id, +1 more. Returns: object
Return the complete Medium/High/Critical CVE catalog scope, coverage, provenance, and counts.
Inputs: no named parameters. Returns: object
Get evidence, recipe authority, and a bounded code/config/file change plan for one exact CVE.
Inputs: cve (required). Returns: object
Search every in-scope Medium/High/Critical CVE; use recipes_cve_get for complete details.
Inputs: query (required), limit, kev_only, severity, +1 more. Returns: object
Return the design partner pilot motion for buyer proof and hosted MCP validation.
Inputs: status, risk_id, phase_id, wedge_id, +3 more. Returns: object
Return the bundled enterprise trust-center export for buyer and platform diligence.
Inputs: status, pack_id, category, section_id, +1 more. Returns: object
Get a full recipe record by slug or path.
Inputs: slug_or_path (required). Returns: object
Return the hosted MCP readiness plan for enterprise product rollout.
Inputs: status, gate_id, risk_id, stage_id, +2 more. Returns: object
List recipes with optional metadata filtering.
Inputs: tags, agent, limit, facets, +3 more. Returns: object
Heuristic matcher that suggests best-fit recipes for a security finding.
Inputs: cve, limit, facets, package, +4 more. Returns: object
Return MCP authorization conformance, scope-drift, and token-boundary evidence.
Inputs: decision, namespace, workflow_id, connector_id. Returns: object
Return MCP connector intake decisions, risk findings, gaps, and promotion plans.
Inputs: decision, namespace, candidate_id. Returns: object
Return MCP connector trust tiers, controls, evidence, and workflow namespace coverage.
Inputs: namespace, workflow_id, connector_id. Returns: object
Return MCP form-mode and URL-mode elicitation boundary evidence.
Inputs: mode, decision, risk_tier, profile_id, +1 more. Returns: object
Return generated MCP gateway policy for scoped tool access and runtime controls.
Inputs: workflow_id. Returns: object
Return OWASP MCP and agentic-skill risk coverage mapped to generated evidence.
Inputs: status, risk_id, risk_tier, source_id, +2 more. Returns: object
Return one publicly documented MCP server with official setup and safety guidance.
Inputs: server_id (required). Returns: object
Search the bundled catalog of publicly documented MCP servers and ecosystems.
Inputs: limit, query, availability. Returns: object
Return MCP STDIO launch boundaries, profiles, decisions, and evidence.
Inputs: decision, launch_id, profile_id. Returns: object
Return MCP tool annotation, trust, and session-combination risk evidence.
Inputs: decision, namespace, risk_tier, workflow_id, +1 more. Returns: object
Return pinned MCP tool descriptions, schemas, annotations, and drift evidence.
Inputs: decision, namespace, tool_name, surface_id, +1 more. Returns: object
Call an allowed read-only tool on a configured upstream MCP server.
Inputs: server_id (required), tool_name (required), arguments. Returns: object
Collect bounded context from configured upstream MCP servers for a remediation query.
Inputs: query (required), max_chars, server_ids. Returns: object
List optional upstream MCP servers configured for this Security Recipes server.
Inputs: no named parameters. Returns: object
List tools exposed by a configured upstream MCP server and show local allow decisions.
Inputs: server_id (required). Returns: object
Return model-provider route profiles, workflow mappings, and required evidence.
Inputs: decision, model_id, route_id, risk_tier, +2 more. Returns: object
Get one complete remediation workflow, evidence, output, and Python contract.
Inputs: playbook_id (required). Returns: object
Build a deterministic, read-only phase, gate, and evidence checklist for a finding.
Inputs: playbook_id (required), finding. Returns: object
List concise remediation playbook records, optionally filtered by query or category.
Inputs: limit, query, category. Returns: object
Summarize recipe quality tiers and list recipes missing world-class signals.
Inputs: tier, facet, limit. Returns: object
Refresh the in-memory copy of recipes-index.json.
Inputs: force. Returns: object
Full-text search over security-recipes documents.
Inputs: query (required), tags, agent, limit, +3 more. Returns: object
Return secure-context attestation subjects, verification policy, and recertification state.
Inputs: status, source_id, artifact_id, workflow_id, +1 more. Returns: object
Return buyer and acquirer diligence evidence for the secure context layer.
Inputs: bet_id, status, buyer_id, source_id, +2 more. Returns: object
Return the customer proof contract for design partner and acquisition evidence.
Inputs: status, gate_id, risk_id, claim_id, +2 more. Returns: object
Return scenario-backed secure-context evals for retrieval, attestation, egress, and handoffs.
Inputs: decision, scenario_id, workflow_id, minimum_score, +1 more. Returns: object
Return the secure context evidence API and release contract.
Inputs: status, channel_id, artifact_id, endpoint_id, +1 more. Returns: object
Return context lineage, reuse policy, stage requirements, hashes, and workflow envelopes.
Inputs: decision, stage_id, source_id, reuse_class, +1 more. Returns: object
Return context provenance, retrieval policy, source hashes, and workflow context packages.
Inputs: decision, source_id, trust_tier, workflow_id. Returns: object
Return the secure context value model for buyer, ROI, and acquisition diligence.
Inputs: status, wedge_id, driver_id, segment_id, +2 more. Returns: object
Return MCP server metadata and source-index configuration.
Inputs: no named parameters. Returns: object
Return workflow control-plane policy for agents, reviewers, and MCP gateways.
Inputs: workflow_id. Returns: object
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Read-only vulnerability intelligence: CVEs, exploitation evidence, fixes and product matches.
Live CVE, CISA KEV and exploit intelligence, SBOM scans, patch prioritization and IOC checks.
Free CVE lookups, package checks and patch priorities from public sources. No account or API key.
CVE, KEV, EPSS, SBOM and advisory lookups; per-CVE exposure from Shodan data (© Shodan). Keyless.
Add one secure layer between your agents and this server.
