Security Recipes
io.github.stevologic/security-recipes · v1.0.0 · score 89/100 · checked 2026-11-22
Automated, read-only signal from public data, not an audit or an accusation. Maintainers can dispute any finding. How grading works
Read-only CVE intelligence, remediation playbooks, and agent setup guides. Not a scanner.
Source: https://github.com/stevologic/security-recipes.ai
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 75 tool(s) to anyone, no credentials needed. |
| Medium | MW102 | 1 tool(s) can execute commands or delete data (recipes_secure_context_eval_pack). Require confirmation before the agent calls them. |
What was checked
- https://security-recipes.ai/mcp: answers without auth
Public tools: 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
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/io-github-stevologic-security-recipes-49fe9d25)