Security Recipes MCP MCP server

Provides read-only access to a CVE database, AI vulnerability remediation playbooks, and agent setup guides. It allows AI agents to discover vulnerabilities, assess risk, and retrieve bounded remediation workflows with evidence requirements, without acting as a scanner or mutation surface.

Endpoint and access

No sign-in: your client connects and lists tools immediately, with no account or key.

No sign-inEndpoint checked 2026-10-05Operated by Security Recipes

MCP endpoint (Streamable HTTP)

https://security-recipes.ai/mcp

Vendor documentation

What you can do with it

Search and retrieve details for specific CVEs
Access reviewed remediation workflows for vulnerabilities
Obtain agent setup guides for security tools
Retrieve bounded context for AI vulnerability assessment

Tools advertised by the last live check:

recipes_server_info
recipes_mcp_upstream_servers
recipes_mcp_servers_list
recipes_mcp_server_get
recipes_mcp_upstream_tools
recipes_mcp_upstream_call
recipes_mcp_upstream_context
recipes_refresh
recipes_search
recipes_list
recipes_get
recipes_playbooks_list
recipes_playbook_get
recipes_playbook_plan
recipes_cve_catalog_info
recipes_cve_search
recipes_cve_get
recipes_quality_report
recipes_workflow_control_plane
recipes_mcp_gateway_policy
recipes_agentic_assurance_pack
recipes_agent_identity_ledger
recipes_agentic_entitlement_review_pack
recipes_agentic_approval_receipt_pack
recipes_mcp_connector_trust_pack
recipes_mcp_connector_intake_pack
recipes_mcp_stdio_launch_boundary_pack
recipes_mcp_authorization_conformance_pack
recipes_mcp_elicitation_boundary_pack
recipes_mcp_tool_risk_contract
recipes_mcp_tool_surface_drift_pack
recipes_agentic_red_team_drill_pack
recipes_agentic_red_team_replay_harness
recipes_agentic_readiness_scorecard
recipes_agent_capability_risk_register
recipes_agent_memory_boundary_pack
recipes_agent_skill_supply_chain_pack
recipes_agent_handoff_boundary_pack
recipes_a2a_agent_card_trust_profile
recipes_agentic_system_bom
recipes_agentic_run_receipt_pack
recipes_secure_context_trust_pack
recipes_secure_context_attestation_pack
recipes_secure_context_lineage_ledger
recipes_secure_context_eval_pack
recipes_context_poisoning_guard_pack
recipes_context_egress_boundary_pack
recipes_agentic_threat_radar
recipes_agentic_standards_crosswalk
recipes_agentic_source_freshness_watch
recipes_mcp_risk_coverage_pack
recipes_agentic_protocol_conformance_pack
recipes_agentic_control_plane_blueprint
recipes_agentic_exposure_graph
recipes_agentic_posture_snapshot
recipes_agentic_aivss_risk_scoring_pack
recipes_agentic_app_intake_pack
recipes_model_provider_routing_pack
recipes_agentic_catastrophic_risk_annex
recipes_critical_infrastructure_secure_context_pack
recipes_agentic_incident_response_pack
recipes_agentic_action_runtime_pack
recipes_agent_trust_fabric_pack
recipes_browser_agent_boundary_pack
recipes_agentic_measurement_probe_pack
recipes_agentic_telemetry_contract
recipes_agentic_soc_detection_pack
recipes_enterprise_trust_center_export
recipes_secure_context_value_model
recipes_design_partner_pilot_pack
recipes_secure_context_buyer_diligence_brief
recipes_secure_context_customer_proof_pack
recipes_secure_context_evidence_contract
recipes_hosted_mcp_readiness_pack
recipes_match_finding

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers a Streamable HTTP server. Use --scope project to write .mcp.json for the repo.

Claude Code configuration

claude mcp add --transport http security-recipes-mcp https://security-recipes.ai/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).

Codex configuration

codex mcp add security-recipes-mcp --url https://security-recipes.ai/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable security-recipes-mcp in your MCP settings.

Cursor configuration

{
  "mcpServers": {
    "security-recipes-mcp": {
      "url": "https://security-recipes.ai/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure). The type must be streamableHttp for a remote HTTP server.

Cline configuration

{
  "mcpServers": {
    "security-recipes-mcp": {
      "type": "streamableHttp",
      "url": "https://security-recipes.ai/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start security-recipes-mcp and inspect its tools.

VS Code configuration

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

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.

Gemini CLI configuration

gemini mcp add --transport http security-recipes-mcp https://security-recipes.ai/mcp

Claude Desktop

Merge this into claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\), then restart Claude Desktop.

Claude Desktop configuration

{
  "mcpServers": {
    "security-recipes-mcp": {
      "url": "https://security-recipes.ai/mcp"
    }
  }
}

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.

Windsurf configuration

{
  "mcpServers": {
    "security-recipes-mcp": {
      "serverUrl": "https://security-recipes.ai/mcp"
    }
  }
}

See all 957

Do you run Security Recipes MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing