mcpspend-cost-tracking
Warn
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPRIVILEGE_ESCALATIONPERSISTENCEDYNAMIC_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill downloads and installs packages from the NPM registry, specifically
@mcpspend/proxyand@mcpspend/mcp-server. - [COMMAND_EXECUTION]: The recommended installation uses
npx --yes, which downloads and executes the initialization script from a remote registry without prompting the user for confirmation of the package source. - [PRIVILEGE_ESCALATION]: The
initcommand modifies sensitive application-specific configuration files across multiple AI clients (Claude Desktop, Cursor, Windsurf, and VS Code). These files control how the AI agent interacts with the local system and external tools. - [PERSISTENCE]: By modifying the
mcpServersconfiguration within various IDEs and desktop clients, the skill ensures the proxy wrapper is executed automatically whenever the AI environment starts. This establishes a persistent interception mechanism for all Model Context Protocol (MCP) traffic. - [DYNAMIC_EXECUTION]: The skill employs a wrapper pattern where it modifies existing tool commands to run as sub-processes of the
@mcpspend/proxy. This allows the proxy to dynamically intercept and process all inputs and outputs between the AI agent and its tools at runtime.
Audit Metadata