The trust score for AI-generated code. One command verifies what your coding agent shipped: security findings with file:line evidence, Docker-sandboxed build/boot checks, and claim receipts that catch agents lying about tests.
MCP server Claude CodeCodexCursor
Gives the agent read and write access to a set of allowed directories on the local filesystem. Runs locally from the @modelcontextprotocol/server-filesystem npm package. Needs 1 environment variable to run.
MCP server Claude CodeCodexCursor
MCP server "no-autoyes" as configured in elberacasa/umbra. Runs locally from the some-mcp-server npm package.
MCP server Claude CodeCodexCursor
Trust score for AI-generated code: scan repos, guard agent file writes, get a 0-100 score. Runs locally from the @elberacasa/umbra npm package.