MCP Server Manifest & Tool Security Linter API
Audit MCP server manifests for hidden tool poisoning, shell risks, and excessive permissions.
Audit Model Context Protocol (MCP) manifests for tool poisoning, validate LLM tool-call arguments, inspect shell/SQL commands before execution, and sign tamper-evident agent action receipts.
| Endpoint | Capability | Tier | Action |
|---|---|---|---|
POST /v1/mcp-manifest-linter |
Audit MCP manifests for tool poisoning and over-broad permissions | All-Access | Try live → |
POST /v1/command-sql-guard |
Audit agent shell commands and SQL queries before execution | All-Access | Try live → |
POST /v1/tool-call-validator |
Validate and auto-repair LLM tool-call arguments against JSON Schema | All-Access | Docs |
POST /v1/agent-action-receipts/issue |
Issue signed, hash-chained compliance receipts for agent actions | All-Access | Docs |
POST /v1/agent-action-receipts/verify |
Verify single receipts or hash-linked agent execution chains | All-Access | Docs |
POST /v1/content-provenance |
Inspect C2PA manifests, IPTC tags, and AI generator metadata | All-Access | Docs |
POST /v1/agent-code-guard |
Audit AI-generated Python, JS/TS, Bash, and GitHub Actions code | Live | Docs |
Audit MCP server manifests for hidden tool poisoning, shell risks, and excessive permissions.
Audit agent shell commands and Text-to-SQL queries for RCE, reverse shells, and destructive SQL.
Validate and auto-repair broken LLM tool-call arguments against your JSON Schema.
Issue and verify tamper-evident HMAC-signed receipts for autonomous AI agent actions.
Detect C2PA manifests, AI generator EXIF/XMP tags, and stripped metadata in files or headers.
Audit LLM-generated Python, JS/TS, Shell, or GitHub Actions code for sandbox escapes before execution.