@pshkv/mcp-scanner

Parses and analyzes MCP (Model Context Protocol) server tool definitions to extract schema, parameters, and capabilities without executing the server. Uses AST-like traversal of tool manifests to build a semantic model of available functions, their input/output contracts, and permission requirements for downstream security evaluation.

Evaluates extracted tool definitions against a configurable risk taxonomy (likely OWASP-aligned or custom policy rules) to assign severity scores and risk categories. Implements pattern matching on tool names, parameters, and descriptions to detect high-risk operations (file system access, network calls, credential handling) and generates a scored risk report for policy decision-making.

Implements a policy evaluation engine that takes risk classifications and applies configurable allow/deny/require-approval rules to determine whether an LLM agent should be permitted to call a specific tool. Supports policy composition (e.g., 'block all file system tools', 'require approval for network calls') and integrates with MCP server request interception to enforce decisions at runtime.

Validates tool invocation parameters against extracted MCP tool schemas to detect parameter injection, type mismatches, and constraint violations before execution. Implements JSON schema validation with custom rules for dangerous parameter patterns (e.g., shell metacharacters in command parameters, file paths outside allowed directories) and generates detailed validation reports.

Records all tool access decisions (allowed, denied, approved) with context (agent identity, user, timestamp, tool name, parameters, risk classification) to an audit log. Generates compliance reports summarizing tool usage patterns, policy violations, and high-risk tool invocations for security review and regulatory compliance (SOC 2, HIPAA, etc.).

Provides a rule engine for defining custom risk classification and access control policies using a declarative configuration format (likely YAML or JSON DSL). Supports rule composition, conditional logic (e.g., 'block tool X if parameter Y contains Z'), and integration with external policy sources. Enables teams to define organization-specific security policies without code changes.