# Security Recipes

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

- name: io.github.stevologic/security-recipes
- version: 1.0.0
- connection class: R0 (autonomous)
- trust: 94/100
- quality: 75/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.stevologic%2Fsecurity-recipes
- tools: https://api.protogrid.dev/v1/servers/io.github.stevologic%2Fsecurity-recipes/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "security-recipes": {
      "type": "http",
      "url": "https://security-recipes.ai/mcp"
    }
  }
}
```


## Trust

- hygiene: 100
- liveness: 100
- freshness: 85
- provenance: 90
- drivers: +repository +namespace-matches-repo +website +reachable +uptime-100% ~updated-55d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 75/100 (good)

### protocol: 88 (weight 25)

- pass `protocol.modern`: supports 2026-07-28 (server/discover)
- pass `protocol.stateless`: answers without a session
- pass `protocol.transport`: streamable HTTP
- warn `protocol.list_ttl`: tools/list declares ttlMs 0, so clients re-fetch it on every use

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 64 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- fail `tools.annotations`: no tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: recipes_mcp_servers_list (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); recipes_refresh (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); recipes_list (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
- warn `tools.token_cost`: about 8,820 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 75 (weight 15)

- warn `stability.changes`: 75 tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 75, about 8,820 tokens to load them all
- tool set hash: b5f8b41a7b4594e12b4f915b5533c496
- tools last changed: 2026-09-27T17:28:52.838Z
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.stevologic/security-recipes.svg)](https://protogrid.dev/servers/io.github.stevologic/security-recipes)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-09-27 `recipes_match_finding` changed (title)
- 2026-09-27 `recipes_hosted_mcp_readiness_pack` changed (title)
- 2026-09-27 `recipes_secure_context_evidence_contract` changed (title)
- 2026-09-27 `recipes_secure_context_customer_proof_pack` changed (title)
- 2026-09-27 `recipes_secure_context_buyer_diligence_brief` changed (title)
- 2026-09-27 `recipes_design_partner_pilot_pack` changed (title)
- 2026-09-27 `recipes_secure_context_value_model` changed (title)
- 2026-09-27 `recipes_enterprise_trust_center_export` changed (title)
- 2026-09-27 `recipes_agentic_soc_detection_pack` changed (title)
- 2026-09-27 `recipes_agentic_telemetry_contract` changed (title)

Full history: https://api.protogrid.dev/v1/servers/io.github.stevologic%2Fsecurity-recipes/changes

## Remotes

- https://security-recipes.ai/mcp (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

_none_

## Tools (75)

- `recipes_a2a_agent_card_trust_profile`: Return A2A Agent Card intake profiles, trust controls, and sample decisions.
- `recipes_agent_capability_risk_register`: Return capability-based residual risk scores for agentic workflows.
- `recipes_agent_handoff_boundary_pack`: Return agent handoff boundary profiles, protocol controls, and workflow maps.
- `recipes_agentic_action_runtime_pack`: Return action classes, workflow action envelopes, runtime policy, and evidence.
- `recipes_agentic_aivss_risk_scoring_pack`: Return AIVSS-aligned agentic risk scores, SLAs, evidence, and hosted MCP wedges.
- `recipes_agentic_app_intake_pack`: Return generated agentic app launch-review profiles and decisions.
- `recipes_agentic_approval_receipt_pack`: Return scope-bound approval receipt profiles, workflow requirements, and evidence.
- `recipes_agentic_assurance_pack`: Return enterprise assurance controls, workflow evidence, and AI/Agent BOM seed.
- `recipes_agentic_catastrophic_risk_annex`: Return the severe-risk annex for high-impact agentic AI runtime decisions.
- `recipes_agentic_control_plane_blueprint`: Return the acquisition-ready agentic control plane architecture and buyer evidence map.
- `recipes_agentic_entitlement_review_pack`: Return expiring agent entitlement leases, access reviews, and scope evidence.
- `recipes_agentic_exposure_graph`: Return risk-ranked agentic exposure paths across context, identities, MCP tools, and evidence.
- `recipes_agentic_incident_response_pack`: Return agentic incident response classes, phases, workflow matrix, and evidence.
- `recipes_agentic_measurement_probe_pack`: Return measurement probes for agentic workflow traceability and readiness.
- `recipes_agentic_posture_snapshot`: Return the generated enterprise posture snapshot for agentic AI and MCP operations.
- `recipes_agentic_protocol_conformance_pack`: Return MCP/A2A protocol conformance evidence and buyer-ready drift controls.
- `recipes_agentic_readiness_scorecard`: Return generated scale, pilot, gate, or block decisions for agentic workflows.
- `recipes_agentic_red_team_drill_pack`: Return adversarial drills for agentic remediation workflows and MCP controls.
- `recipes_agentic_red_team_replay_harness`: Return replay fixtures, expected decisions, and evidence gates for red-team drills.
- `recipes_agentic_run_receipt_pack`: Return agent run receipt templates for identity, context, tools, egress, approval, and evidence.
- `recipes_agentic_soc_detection_pack`: Return SIEM-ready detections for agentic AI and MCP telemetry.
- `recipes_agentic_source_freshness_watch`: Return source-freshness and standards-drift evidence for SecurityRecipes.
- `recipes_agentic_standards_crosswalk`: Return standards-to-evidence mappings for agentic AI, MCP, and prompt-injection guidance.
- `recipes_agentic_system_bom`: Return the Agentic System BOM for workflows, agents, identities, MCP tools, and evidence.
- `recipes_agentic_telemetry_contract`: Return the OpenTelemetry-aligned agentic telemetry and redaction contract.
- `recipes_agentic_threat_radar`: Return current source-backed agentic AI threat signals and product priorities.
- `recipes_agent_identity_ledger`: Return agent non-human identity, delegation, scope, and audit contracts.
- `recipes_agent_memory_boundary_pack`: Return agent memory classes, workflow profiles, TTLs, and persistence decisions.
- `recipes_agent_skill_supply_chain_pack`: Return agent skill provenance, permission, isolation, and supply-chain decisions.
- `recipes_agent_trust_fabric_pack`: Return Agent Trust Fabric dimensions, workflow tiers, source evidence, and buyer proof.
- `recipes_browser_agent_boundary_pack`: Return browser-agent workspace classes, task profiles, controls, and evidence.
- `recipes_context_egress_boundary_pack`: Return context egress data classes, destination classes, and workflow boundary policy.
- `recipes_context_poisoning_guard_pack`: Return context-poisoning scan results for registered secure-context sources.
- `recipes_critical_infrastructure_secure_context_pack`: Return the generated critical-infrastructure secure-context profile.
- `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.
- `recipes_cve_search`: Search every in-scope Medium/High/Critical CVE; use recipes_cve_get for complete details.
- `recipes_design_partner_pilot_pack`: Return the design partner pilot motion for buyer proof and hosted MCP validation.
- `recipes_enterprise_trust_center_export`: Return the bundled enterprise trust-center export for buyer and platform diligence.
- `recipes_get`: Get a full recipe record by slug or path.
- `recipes_hosted_mcp_readiness_pack`: Return the hosted MCP readiness plan for enterprise product rollout.
- `recipes_list`: List recipes with optional metadata filtering.
- `recipes_match_finding`: Heuristic matcher that suggests best-fit recipes for a security finding.
- `recipes_mcp_authorization_conformance_pack`: Return MCP authorization conformance, scope-drift, and token-boundary evidence.
- `recipes_mcp_connector_intake_pack`: Return MCP connector intake decisions, risk findings, gaps, and promotion plans.
- `recipes_mcp_connector_trust_pack`: Return MCP connector trust tiers, controls, evidence, and workflow namespace coverage.
- `recipes_mcp_elicitation_boundary_pack`: Return MCP form-mode and URL-mode elicitation boundary evidence.
- `recipes_mcp_gateway_policy`: Return generated MCP gateway policy for scoped tool access and runtime controls.
- `recipes_mcp_risk_coverage_pack`: Return OWASP MCP and agentic-skill risk coverage mapped to generated evidence.
- `recipes_mcp_server_get`: Return one publicly documented MCP server with official setup and safety guidance.
- `recipes_mcp_servers_list`: Search the bundled catalog of publicly documented MCP servers and ecosystems.
- `recipes_mcp_stdio_launch_boundary_pack`: Return MCP STDIO launch boundaries, profiles, decisions, and evidence.
- `recipes_mcp_tool_risk_contract`: Return MCP tool annotation, trust, and session-combination risk evidence.
- `recipes_mcp_tool_surface_drift_pack`: Return pinned MCP tool descriptions, schemas, annotations, and drift evidence.
- `recipes_mcp_upstream_call`: Call an allowed read-only tool on a configured upstream MCP server.
- `recipes_mcp_upstream_context`: Collect bounded context from configured upstream MCP servers for a remediation query.
- `recipes_mcp_upstream_servers`: List optional upstream MCP servers configured for this Security Recipes server.
- `recipes_mcp_upstream_tools`: List tools exposed by a configured upstream MCP server and show local allow decisions.
- `recipes_model_provider_routing_pack`: Return model-provider route profiles, workflow mappings, and required evidence.
- `recipes_playbook_get`: Get one complete remediation workflow, evidence, output, and Python contract.
- `recipes_playbook_plan`: Build a deterministic, read-only phase, gate, and evidence checklist for a finding.
- `recipes_playbooks_list`: List concise remediation playbook records, optionally filtered by query or category.
- `recipes_quality_report`: Summarize recipe quality tiers and list recipes missing world-class signals.
- `recipes_refresh`: Refresh the in-memory copy of recipes-index.json.
- `recipes_search`: Full-text search over security-recipes documents.
- `recipes_secure_context_attestation_pack`: Return secure-context attestation subjects, verification policy, and recertification state.
- `recipes_secure_context_buyer_diligence_brief`: Return buyer and acquirer diligence evidence for the secure context layer.
- `recipes_secure_context_customer_proof_pack`: Return the customer proof contract for design partner and acquisition evidence.
- `recipes_secure_context_eval_pack`: Return scenario-backed secure-context evals for retrieval, attestation, egress, and handoffs.
- `recipes_secure_context_evidence_contract`: Return the secure context evidence API and release contract.
- `recipes_secure_context_lineage_ledger`: Return context lineage, reuse policy, stage requirements, hashes, and workflow envelopes.
- `recipes_secure_context_trust_pack`: Return context provenance, retrieval policy, source hashes, and workflow context packages.
- `recipes_secure_context_value_model`: Return the secure context value model for buyer, ROI, and acquisition diligence.
- `recipes_server_info`: Return MCP server metadata and source-index configuration.
- `recipes_workflow_control_plane`: Return workflow control-plane policy for agents, reviewers, and MCP gateways.