Audits MCP server configurations and packages for security risks such as typosquats, credential exposure, and malicious code, with zero dependencies and no execution.
Enables auditing MCP server configurations and tool descriptions from inside an AI assistant, surfacing poisoned tools, leaked secrets, risky launch commands, over-broad access, hidden Unicode, and silent tool changes with redacted evidence and concrete fixes.
Lets an agent inspect and audit MCP servers before connecting to them, checking their exposed tools, prompts and resources for tool poisoning, shadowing, excessive permissions, leaked secrets and unsafe transports against 24 deterministic rules. Results are returned as findings with evidence, remediation and CWE/OWASP references, and can fail CI with SARIF, Markdown or standalone HTML reports.
Enables static, read-only auditing of MCP servers’ registry entries, package metadata, client configurations, and tool definitions for supply-chain security indicators. It returns merged reports with transparent skipped checks and never executes the inspected code.
A read-only MCP server that lets an agent audit its own environment by discovering local MCP configurations and skill folders on Windows, macOS, and Linux and running offline static checks for prompt injection, hidden instructions, hardcoded secrets, dangerous commands, unpinned packages, and excessive filesystem or transport permissions. It exposes tools to scan everything discovered, list configurations, vet a single skill, or analyze supplied text, returning text, JSON, SARIF, or HTML findings with CI-friendly severity levels.
Enables agents to inspect and diagnose their own MCP setup by exposing read-only tools that audit configured servers, report which coding agents have configs, surface misplaced or duplicated registrations, and list curated preset packs. It also powers CLI workflows for checking handshake, tool lint, and tool-surface quality scores of any stdio server.