| FMRS | 56 / 100 · C | 79 / 100 · B |
|---|
| Reliability | 8 / 20 | 12 / 20 |
|---|
| Security and permissions | 10 / 20 | 18 / 20 |
|---|
| Maintenance | 10 / 20 | 16 / 20 |
|---|
| Documentation | 15 / 20 | 18 / 20 |
|---|
| Setup experience | 13 / 20 | 15 / 20 |
|---|
| Best for | - Teams already using the Codacy platform for code quality and security management
- Developers who want Codacy analysis results directly inside Cursor, Windsurf, VS Code Copilot, or Claude Desktop
- Teams that want to check pull request issues and coverage as part of an AI coding assistant workflow
| - Engineering teams scaling AI coding agents while controlling spend
- Platform teams that need auditable, rollback-aware agent execution records
- Organizations using multiple agents (Claude, Codex, Gemini) under one governed flow
|
|---|
| Not for | - Users without a Codacy account, or who don't intend to register repositories with Codacy
- Scenarios requiring generic static analysis or security scanning independent of the Codacy platform
- Restricted environments where Node.js/npx or the Codacy CLI cannot be installed
| - Developers who just want a simple code-completion helper without run governance
- Teams unwilling to accept local JSONL run records with HMAC signing
- Environments without a supported adapter (Claude/Codex/Gemini CLIs, direct provider, or verifier-only)
|
|---|
| Required permissions | - Accesses organizations and repositories the user has permission to on Codacy, via the CODACY_ACCOUNT_TOKEN personal account token
- Reads repository analysis results, issues, coverage, security findings, and pull request data
- Executes the Codacy CLI locally to analyze code on the filesystem (attempts automatic installation of the CLI)
| - Read/write access to the configured repo root (writable scope restrictable via --allow-path/--deny-path)
- Ability to invoke the chosen agent CLI (Claude/Codex/Gemini, etc.) and its underlying model account
- Local disk writes for run records, receipts, and share outputs (share/run-receipt., etc.)
- Execution of user-configured verifier commands (e.g. npm test)
|
|---|
| Risks and side effects | - CODACY_ACCOUNT_TOKEN is a sensitive credential; if leaked it could grant access to all Codacy organizations and repositories tied to the account
- codacy_cli_analyze installs and runs the Codacy CLI locally, which involves executing a third-party binary
- Security-related tools (SRM items) surface repository vulnerability and secret-scanning results, so access and downstream handling should be controlled
- The server depends on network access to the Codacy API; misconfigured credentials could expose data to unintended clients
| - Verifier commands are executed; poorly chosen verifier commands carry security risk despite preflight policy checks
- Cost and token figures may be estimates (labeled with provenance) and should not be treated as settled accounting
- Receipt integrity must be verified before use as trustworthy evidence; missing rollback evidence is flagged as EVIDENCE_BOUNDARY
- Policy defaults come from martin.config.yaml and can be overridden by CLI flags; misconfiguration can loosen safety boundaries
|
|---|
| Supported clients | Claude Desktop, Cursor, Windsurf, GitHub Copilot | Claude Code, Codex, Gemini CLI, Cursor, VS Code, GitHub Copilot, Continue |
|---|
| Tools | 23 | 0 |
|---|