# AgentDoctor > Local CLI that audits coding-agent configuration for security, instructions, context, and MCP β€” no API key or code upload by default. - **Type:** MCP server - **Install:** `agentstack add mcp-pranee54-agentdoctor` - **Verified:** Yes β€” security-reviewed for prompt injection and unsafe behavior - **Seller:** [pranee54](https://agentstack.voostack.com/s/pranee54) - **Installs:** 0 - **Category:** [Integrations](https://agentstack.voostack.com/c/integrations) - **Latest version:** 0.1.0 - **License:** MIT - **Upstream author:** [pranee54](https://github.com/pranee54) - **Source:** https://github.com/pranee54/AgentDoctor - **Website:** https://www.npmjs.com/package/@praneeth_54/agentdoctor ## Install ```sh agentstack add mcp-pranee54-agentdoctor ``` Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent. ## About # AgentDoctor [](https://www.npmjs.com/package/@praneeth_54/agentdoctor) [](https://www.npmjs.com/package/@praneeth_54/agentdoctor) [](https://github.com/pranee54/AgentDoctor/actions) [](https://nodejs.org) [](LICENSE) **Lighthouse for AI coding agents.** Audit coding-agent configuration before it becomes a repository problem. AgentDoctor is a local CLI that inspects project-level AI coding agent setup β€” Cursor, Claude Code, and Codex β€” for security, instructions, context, and MCP configuration. Deterministic static analysis. No API key. No code upload by default. ```bash npx @praneeth_54/agentdoctor ``` Public beta (`0.1.x-beta`). Readiness scoring and automatic fixes are not available yet. --- ## What you get _Real scan of the included `insecure-agent-project` fixture using AgentDoctor v0.1.3-beta._ ```text $ npx @praneeth_54/agentdoctor 🩺 AgentDoctor v0.1.3-beta Scanning repository... Repository Framework: Node.js Language: JavaScript Package manager: npm Files scanned: 7 AI Coding Agents βœ“ Cursor configured βœ“ Claude Code configured βœ“ Codex configured Findings CRITICAL βœ— Sensitive environment file may enter agent context .env Affected: Claude Code, Codex Fix: Add an agent-specific exclusion (for example .cursorignore or a Claude Code Read deny rule), keep the file out of version control, and rotate any credentials that may have been exposed. βœ— Private key or credential file present in repository test-private-key.pem Affected: Claude Code, Codex, Cursor WARNING ! Claude Code bypassPermissions mode enabled .claude/settings.json Summary 3 critical 1 warning 0 info Scoring: not included in this release ``` Abbreviated text example from the same fixture for accessibility and search. Secret values are never printed. --- ## Why AgentDoctor? Repositories accumulate agent configuration quickly: - Multiple instruction formats (`.cursor/rules`, `CLAUDE.md`, `AGENTS.md`) - Stale path references in always-on instructions - Ignore differences between `.gitignore`, `.cursorignore`, and agent defaults - MCP filesystem scopes that are broader than intended - Generated directories and large logs that waste context - Credential-like files that may be readable by agents - Conflicting assumptions about what each agent can see Manually reviewing all of that across Cursor, Claude Code, and Codex is slow and inconsistent. AgentDoctor provides one deterministic local audit with stable rule IDs, evidence paths, and affected-agent information. | Analogy | Domain | | --------------- | -------------------------------- | | Lighthouse | Web pages | | `npm audit` | Dependencies | | ESLint | Source code | | **AgentDoctor** | **AI coding agent environments** | AgentDoctor analyzes configuration. It does not run agents, call an LLM, or modify your repository in this release. --- ## Before / after **Before** A repository may contain: ```text .cursor/rules/ AGENTS.md CLAUDE.md .claude/settings.json .mcp.json .env ``` Potential problems stay invisible until something leaks into model context, CI, or a teammate’s agent session: - environment or credential-like files reachable by agents - stale instruction path references - broad MCP filesystem access - oversized always-on context **Run** ```bash npx @praneeth_54/agentdoctor ``` **After** You get deterministic findings with: - stable rule IDs (for example `security/env-file-exposure`) - evidence paths - affected agents when exposure claims are supported - conservative recommendations Automatic repair is **not** included in this beta. Findings tell you what to review; you decide what to change. --- ## Quick start ### One-shot (recommended) ```bash npx @praneeth_54/agentdoctor ``` Pin a beta version when you need a fixed install: ```bash npx @praneeth_54/agentdoctor@0.1.3-beta ``` ### Global (optional) ```bash npm install -g @praneeth_54/agentdoctor agentdoctor ``` ### Common commands ```bash agentdoctor . agentdoctor . --json agentdoctor . --verbose agentdoctor explain security/env-file-exposure agentdoctor doctor ``` Package name: `@praneeth_54/agentdoctor` (npm blocks the unscoped name). CLI binary: `agentdoctor`. Requires **Node.js 20+**. ### Programmatic API ```bash npm install @praneeth_54/agentdoctor ``` ```ts import { scan } from "@praneeth_54/agentdoctor"; const result = await scan({ cwd: process.cwd() }); console.log(result.summary); console.log(result.agentSecurityAnalysis); // "full" | "limited" ``` --- ## Supported agents Project-level configuration only (repository files). Global user settings are not scanned. | Agent | What AgentDoctor inspects | | --------------- | ---------------------------------------------------------------------- | | **Cursor** | `.cursor/rules/*.mdc`, `.cursorignore`, Cursor MCP config, `AGENTS.md` | | **Claude Code** | `CLAUDE.md`, `.claude/settings*.json`, `.claude/rules`, MCP config | | **Codex** | `AGENTS.md` / overrides, project `.codex/` configuration | Additional adapters are planned β€” see [ROADMAP.md](ROADMAP.md). --- ## Finding categories | Category | Examples | | ---------------- | --------------------------------------------------------------------- | | **Security** | Env-file exposure, private-key filenames, broad MCP filesystem scopes | | **Context** | Large instruction files, large logs, unignored generated directories | | **Instructions** | Empty instructions, duplicate content, missing path references | | **MCP** | Malformed MCP config, high-risk filesystem path arguments | Full catalog with severities and fixability: [docs/rules.md](docs/rules.md). Explain any rule: ```bash npx @praneeth_54/agentdoctor explain security/env-file-exposure ``` --- ## Privacy and trust **Scans run locally on your machine.** AgentDoctor: - does not require an API key - does not upload repository contents by default - does not call an LLM for core scanning - does not execute MCP servers - does not execute project code - never prints secret values from files it flags by name - enforces repository boundary checks for path references and symlink escape This is still software that reads untrusted repository trees. Treat findings as guidance, not a security certification. AgentDoctor is **not** a complete secret-content scanner. --- ## CI usage Use JSON for automation: ```bash npx @praneeth_54/agentdoctor --json ``` `--ci` runs non-interactively. Until readiness scoring ships, successful scans exit `0` even when findings exist, and `--min-score` is accepted but ignored. There is no packaged GitHub Action yet (planned β€” [ROADMAP.md](ROADMAP.md)). Exit codes: [docs/exit-codes.md](docs/exit-codes.md). Compatibility promises: [docs/compatibility.md](docs/compatibility.md). --- ## Beta limitations Honest limits of the current public beta: | Limitation | Status | | ----------------------------------- | --------------------------------------------------------------- | | Readiness scoring | Not available (`scores` is `null`, `scoringAvailable: false`) | | `--min-score` | Accepted, ignored until scoring ships | | Automatic fixes (`agentdoctor fix`) | Stub only β€” does not modify files | | Secret-content scanning | Filename / config heuristics only | | Detection style | Intentionally conservative; false security findings are avoided | | Agent coverage | Cursor, Claude Code, Codex project configs | See [CHANGELOG.md](CHANGELOG.md) and [docs/release-notes-v0.1.3-beta.md](docs/release-notes-v0.1.3-beta.md). --- ## Architecture ```text Discovery β†’ Project detect β†’ Agent adapters β†’ Rule engine β†’ Findings β†’ Terminal / JSON ``` Details: [docs/architecture.md](docs/architecture.md) --- ## Documentation | Doc | Contents | | ------------------------------------------------------------------ | ------------------------------ | | [docs/README.md](docs/README.md) | Documentation index | | [docs/architecture.md](docs/architecture.md) | Scan pipeline | | [docs/rules.md](docs/rules.md) | Stable rule IDs | | [docs/exit-codes.md](docs/exit-codes.md) | Process exit codes | | [docs/compatibility.md](docs/compatibility.md) | Beta compatibility promises | | [docs/development.md](docs/development.md) | Local development | | [docs/github-launch-checklist.md](docs/github-launch-checklist.md) | GitHub About / topics / launch | | [ROADMAP.md](ROADMAP.md) | Near- and medium-term plans | | [CHANGELOG.md](CHANGELOG.md) | Release history | --- ## Contributing Issues and pull requests are welcome. 1. Read [CONTRIBUTING.md](CONTRIBUTING.md) and the [Code of Conduct](CODE_OF_CONDUCT.md) 2. Prefer [good first issues](docs/good-first-issues.md) ideas 3. Report security issues via [SECURITY.md](SECURITY.md) β€” never paste real secrets into issues ```bash git clone https://github.com/pranee54/AgentDoctor.git cd AgentDoctor npm install npm run verify node dist/cli/index.js ./fixtures/clean-configured-project ``` --- ## Next steps - **Try it:** `npx @praneeth_54/agentdoctor` - **Report a false positive / false negative:** use the issue templates (include version, rule ID, anonymized evidence β€” no secrets) - **Propose a rule or adapter:** [feature request](.github/ISSUE_TEMPLATE/feature_request.md) / [rule proposal](.github/ISSUE_TEMPLATE/rule_proposal.md) - **Contribute:** [CONTRIBUTING.md](CONTRIBUTING.md) - **Useful?** Star or watch the repository so you see updates --- ## License [MIT](LICENSE) Β© AgentDoctor Contributors ## Source & license This open-source MCP server is cataloged on AgentStack and links to its original source β€” we do not rehost the code. - **Author:** [pranee54](https://github.com/pranee54) - **Source:** [pranee54/AgentDoctor](https://github.com/pranee54/AgentDoctor) - **License:** MIT - **Homepage:** https://www.npmjs.com/package/@praneeth_54/agentdoctor Install and usage instructions live in the source repository linked above. ## Pricing - **Free** β€” Free ## Security capabilities Automated source analysis of v0.1.0 β€” what this tool can access: - **Network access:** no - **Filesystem access:** no - **Shell / process execution:** no - **Environment & secrets:** yes - **Dynamic code execution:** no *"Yes" means the capability is present in the source β€” more access means more to trust, not that it is unsafe.* ## Versions - **0.1.0** β€” security scan: passed β€” Imported from the upstream source. ## Links - Listing page: https://agentstack.voostack.com/l/mcp-pranee54-agentdoctor - Seller: https://agentstack.voostack.com/s/pranee54 - Browse the marketplace: https://agentstack.voostack.com/browse --- Listed on AgentStack β€” the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.