Security Recipes is a remote MCP server that gives an AI agent 75 tools, among them recipes_a2a_agent_card_trust_profile, recipes_agent_capability_risk_register, recipes_agent_handoff_boundary_pack. It answers at https://security-recipes.ai/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 6 of 6 times since 11 September 2026; the last check, on 24 October 2026, succeeded.
Read-only CVE intelligence, remediation playbooks, and agent setup guides. Not a scanner.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
recipes_a2a_agent_card_trust_profile | Return A2A Agent Card intake profiles, trust controls, and sample decisions. Inputs: profile_id, decision, risk_tier |
recipes_agent_capability_risk_register | Return capability-based residual risk scores for agentic workflows. Inputs: workflow_id, risk_tier, decision, minimum_residual_score |
recipes_agent_handoff_boundary_pack | Return agent handoff boundary profiles, protocol controls, and workflow maps. Inputs: profile_id, workflow_id, protocol, decision |
recipes_agent_identity_ledger | Return agent non-human identity, delegation, scope, and audit contracts. Inputs: identity_id, workflow_id, agent_class |
recipes_agent_memory_boundary_pack | Return agent memory classes, workflow profiles, TTLs, and persistence decisions. Inputs: memory_class_id, workflow_id, decision, persistent |
recipes_agent_skill_supply_chain_pack | Return agent skill provenance, permission, isolation, and supply-chain decisions. Inputs: skill_id, platform, decision, risk_tier, minimum_score |
recipes_agent_trust_fabric_pack | Return Agent Trust Fabric dimensions, workflow tiers, source evidence, and buyer proof. Inputs: dimension_id, workflow_id, trust_tier, status |
recipes_agentic_action_runtime_pack | Return action classes, workflow action envelopes, runtime policy, and evidence. Inputs: action_class_id, workflow_id, risk_tier, decision |
recipes_agentic_aivss_risk_scoring_pack | Return AIVSS-aligned agentic risk scores, SLAs, evidence, and hosted MCP wedges. Inputs: scenario_id, severity, runtime_default_decision, minimum_score, owner |
recipes_agentic_app_intake_pack | Return generated agentic app launch-review profiles and decisions. Inputs: app_id, decision, risk_tier, buyer_stage, minimum_score |
recipes_agentic_approval_receipt_pack | Return scope-bound approval receipt profiles, workflow requirements, and evidence. Inputs: approval_profile_id, workflow_id, action_class, risk_tier, decision |
recipes_agentic_assurance_pack | Return enterprise assurance controls, workflow evidence, and AI/Agent BOM seed. Inputs: control_id, workflow_id |
recipes_agentic_catastrophic_risk_annex | Return the severe-risk annex for high-impact agentic AI runtime decisions. Inputs: scenario_id, control_id, buyer_view_id, impact_domain, status |
recipes_agentic_control_plane_blueprint | Return the acquisition-ready agentic control plane architecture and buyer evidence map. Inputs: layer_id, question_id, status |
recipes_agentic_entitlement_review_pack | Return expiring agent entitlement leases, access reviews, and scope evidence. Inputs: entitlement_id, identity_id, workflow_id, namespace, access_mode, risk_tier |
recipes_agentic_exposure_graph | Return risk-ranked agentic exposure paths across context, identities, MCP tools, and evidence. Inputs: path_id, workflow_id, identity_id, namespace, decision, path_class_id |
recipes_agentic_incident_response_pack | Return agentic incident response classes, phases, workflow matrix, and evidence. Inputs: incident_class_id, workflow_id, severity, decision |
recipes_agentic_measurement_probe_pack | Return measurement probes for agentic workflow traceability and readiness. Inputs: probe_id, workflow_id, decision, class_id, status, minimum_score |
recipes_agentic_posture_snapshot | Return the generated enterprise posture snapshot for agentic AI and MCP operations. Inputs: workflow_id, posture_decision, minimum_score, risk_factor_id, finding_id |
recipes_agentic_protocol_conformance_pack | Return MCP/A2A protocol conformance evidence and buyer-ready drift controls. Inputs: protocol_id, check_id, source_id, decision |
recipes_agentic_readiness_scorecard | Return generated scale, pilot, gate, or block decisions for agentic workflows. Inputs: workflow_id, decision, minimum_score |
recipes_agentic_red_team_drill_pack | Return adversarial drills for agentic remediation workflows and MCP controls. Inputs: scenario_id, workflow_id, attack_family |
recipes_agentic_red_team_replay_harness | Return replay fixtures, expected decisions, and evidence gates for red-team drills. Inputs: replay_id, workflow_id, scenario_id, attack_family, severity |
recipes_agentic_run_receipt_pack | Return agent run receipt templates for identity, context, tools, egress, approval, and evidence. Inputs: workflow_id, receipt_id, minimum_score |
recipes_agentic_soc_detection_pack | Return SIEM-ready detections for agentic AI and MCP telemetry. Inputs: rule_id, workflow_id, severity, decision, event_class |
recipes_agentic_source_freshness_watch | Return source-freshness and standards-drift evidence for SecurityRecipes. Inputs: watched_source_id, source_id, primary_watchlist_id, publisher_family, source_class_family, freshness_class |
recipes_agentic_standards_crosswalk | Return standards-to-evidence mappings for agentic AI, MCP, and prompt-injection guidance. Inputs: standard_id, control_id, capability_id, source_id, status |
recipes_agentic_system_bom | Return the Agentic System BOM for workflows, agents, identities, MCP tools, and evidence. Inputs: component_type, workflow_id, agent_class, namespace |
recipes_agentic_telemetry_contract | Return the OpenTelemetry-aligned agentic telemetry and redaction contract. Inputs: workflow_id, signal_class_id, check_id, decision, required_attribute |
recipes_agentic_threat_radar | Return current source-backed agentic AI threat signals and product priorities. Inputs: signal_id, priority, horizon, capability_id, minimum_score |
recipes_browser_agent_boundary_pack | Return browser-agent workspace classes, task profiles, controls, and evidence. Inputs: workspace_class_id, task_profile_id, risk_tier, decision |
recipes_context_egress_boundary_pack | Return context egress data classes, destination classes, and workflow boundary policy. Inputs: data_class, destination_class, source_id, workflow_id |
recipes_context_poisoning_guard_pack | Return context-poisoning scan results for registered secure-context sources. Inputs: source_id, decision, severity, rule_id, actionable_only, limit |
recipes_critical_infrastructure_secure_context_pack | Return the generated critical-infrastructure secure-context profile. Inputs: sector_id, control_id, buyer_view_id, decision, readiness_status |
recipes_cve_catalog_info | Return the complete Medium/High/Critical CVE catalog scope, coverage, provenance, and counts. |
recipes_cve_get | Get evidence, recipe authority, and a bounded code/config/file change plan for one exact CVE. Inputs: cve |
recipes_cve_search | Search every in-scope Medium/High/Critical CVE; use recipes_cve_get for complete details. Inputs: query, severity, published_year, kev_only, limit |
recipes_design_partner_pilot_pack | Return the design partner pilot motion for buyer proof and hosted MCP validation. Inputs: segment_id, phase_id, wedge_id, metric_id, question_id, risk_id |
recipes_enterprise_trust_center_export | Return the bundled enterprise trust-center export for buyer and platform diligence. Inputs: section_id, pack_id, question_id, category, status |
recipes_get | Get a full recipe record by slug or path. Inputs: slug_or_path |
recipes_hosted_mcp_readiness_pack, recipes_list, recipes_match_finding, recipes_mcp_authorization_conformance_pack, recipes_mcp_connector_intake_pack, recipes_mcp_connector_trust_pack, recipes_mcp_elicitation_boundary_pack, recipes_mcp_gateway_policy, recipes_mcp_risk_coverage_pack, recipes_mcp_server_get, recipes_mcp_servers_list, recipes_mcp_stdio_launch_boundary_pack, recipes_mcp_tool_risk_contract, recipes_mcp_tool_surface_drift_pack, recipes_mcp_upstream_call, recipes_mcp_upstream_context, recipes_mcp_upstream_servers, recipes_mcp_upstream_tools, recipes_model_provider_routing_pack, recipes_playbook_get, recipes_playbook_plan, recipes_playbooks_list, recipes_quality_report, recipes_refresh, recipes_search, recipes_secure_context_attestation_pack, recipes_secure_context_buyer_diligence_brief, recipes_secure_context_customer_proof_pack, recipes_secure_context_eval_pack, recipes_secure_context_evidence_contract, recipes_secure_context_lineage_ledger, recipes_secure_context_trust_pack, recipes_secure_context_value_model, recipes_server_info, recipes_workflow_control_plane
Every block below points at https://security-recipes.ai/mcp. Pick your client and copy.
claude mcp add --transport http security-recipes https://security-recipes.ai/mcp
{
"mcpServers": {
"security-recipes": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://security-recipes.ai/mcp"]
}
}
}{
"mcpServers": {
"security-recipes": {
"url": "https://security-recipes.ai/mcp"
}
}
}{
"servers": {
"security-recipes": {
"type": "http",
"url": "https://security-recipes.ai/mcp"
}
}
}{
"context_servers": {
"security-recipes": {
"url": "https://security-recipes.ai/mcp"
}
}
}{
"mcpServers": {
"security-recipes": {
"serverUrl": "https://security-recipes.ai/mcp"
}
}
}{
"mcpServers": {
"security-recipes": {
"url": "https://security-recipes.ai/mcp"
}
}
}name: Security Recipes
version: 0.0.1
schema: v1
mcpServers:
- name: Security Recipes
type: streamable-http
url: https://security-recipes.ai/mcp{
"mcpServers": {
"security-recipes": {
"httpUrl": "https://security-recipes.ai/mcp"
}
}
}{
"mcpServers": {
"security-recipes": {
"type": "http",
"url": "https://security-recipes.ai/mcp"
}
}
}{
"mcpServers": {
"security-recipes": {
"url": "https://security-recipes.ai/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fsecurity-recipes.ai%2Fmcp&type=streamable_http&id=security-recipes&name=Security%20Recipes
It answered our last check on 24 October 2026 in 551 ms. Over 6 checks since 11 September 2026 it answered 6. Status here comes from Neuronto's own probes, not from the publisher.
75, as returned by the server's own tools/list on 21 September 2026: recipes_a2a_agent_card_trust_profile, recipes_agent_capability_risk_register, recipes_agent_handoff_boundary_pack, recipes_agent_identity_ledger, recipes_agent_memory_boundary_pack, recipes_agent_skill_supply_chain_pack, recipes_agent_trust_fabric_pack, recipes_agentic_action_runtime_pack, and 67 more.
It answered our last check on 24 October 2026 in 551 ms. Over 6 checks since 11 September 2026 it answered 6.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://security-recipes.ai/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: io.github.stevologic. Endpoint host: security-recipes.ai. ARD identifier: urn:air:io.github.stevologic:mcp:security-recipes.
First indexed 10 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.