{
  "markdown": "# Archonics MCP Audit Server\n\nFree-tier context engineering audits for production AI agents, delivered as MCP tools you can call from Claude Desktop, Cursor, Claude Code, or any MCP-compatible client.\n\n**What you get:** top-3 findings on your system prompts, tool definitions, or context packing, on demand, no account needed.\n\n**What it costs:** nothing. The free scan is genuinely free. Upgrade paths to the $49 Instant Audit and $750 Full Audit are surfaced in the response footer; they're not paywalls on this tool.\n\n## Why this exists\n\nMost production agent failures aren't model failures — they're context engineering failures. Ambiguous instructions, underspecified tools, bloated context, no regression tests on prompt changes. Those problems are spottable by a trained reader. Archonics has trained that reader and published it as an MCP tool so you can get a second opinion on your agent's context without filing a support ticket.\n\nThe underlying audit engine applies Archonics Audit Methodology v1.0, the same spec that drives our paid audits.\n\n## Tools\n\n### `audit_system_prompt`\n\nPaste a system prompt. Get back the three most important context engineering issues in it, ranked by severity, with specific recommendations.\n\n**Covers:** role clarity, instruction conflicts, negative space, priority structure when instructions conflict, token efficiency, format specification precision, failure-mode coverage.\n\n### `audit_tool_definition`\n\nPaste a tool/function definition. Get back the three most important issues affecting how reliably the model will call it.\n\n**Covers:** description quality (the \"when to use this tool\" question), parameter schema precision, parameter documentation, error response design, discoverability.\n\n### `audit_context_packing`\n\nPaste a representative context payload (or describe it structurally). Get back the three most important efficiency and quality issues.\n\n**Covers:** content inventory, redundancy across sections, freshness/relevance, ordering, truncation risk, prompt-cache utilization.\n\n## Installation\n\n### Claude Desktop\n\nAdd to your `claude_desktop_config.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"archonics-audit\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"@archonics/mcp-audit\"],\n      \"env\": {\n        \"ANTHROPIC_API_KEY\": \"your-anthropic-api-key-here\"\n      }\n    }\n  }\n}\n```\n\n### Cursor\n\nAdd to your `.cursor/mcp.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"archonics-audit\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"@archonics/mcp-audit\"],\n      \"env\": {\n        \"ANTHROPIC_API_KEY\": \"your-anthropic-api-key-here\"\n      }\n    }\n  }\n}\n```\n\n### Claude Code\n\n```bash\nclaude mcp add archonics-audit npx -y @archonics/mcp-audit\n```\n\nThen set `ANTHROPIC_API_KEY` in your environment.\n\n## Why does it need my Anthropic API key?\n\nThe audit engine runs on Claude. You bring your own API key so:\n\n1. Audit submissions go directly from your machine to Anthropic's API, never through Archonics servers.\n2. Your costs are transparent — a typical audit uses 2,000–4,000 tokens, well under a penny.\n3. There's no \"free but actually limited\" rate-limit surprise. Your API key, your limits.\n\nIf you'd rather not bring your own key, use the $49 Instant Audit at agent.market — we cover the API costs and return a full-methodology audit PDF.\n\n## Privacy\n\nSubmitted content is processed ephemerally. No prospect content is retained on Archonics infrastructure or used to train any model. The API call pattern is: your client → your Anthropic API key → Anthropic → your client. Archonics servers are not in this path.\n\nAggregated, anonymized patterns across many audits may inform improvements to the methodology — \"18 of 20 audited systems lacked prompt-regression tests\" — but specific content never feeds that process.\n\nDetails: [archonics.ai/privacy](https://archonics.ai/privacy)\n\n## Upgrade paths\n\nIf the free scan surfaces issues worth fixing, two paid tiers go deeper:\n\n- **Instant Audit — $49 USDC via x402.** Full methodology applied programmatically to a system you submit. 5-10 page PDF report covering all four dimensions (prompt, tools, context, eval) rather than just three findings in one dimension. Listed at [agent.market/archonics](https://agent.market/archonics).\n- **Full Audit — $750.** Human-reviewed audit of a complete agent system. 15-25 page report tuned to your team's context. Contact audits@archonics.ai.\n\n## Contact\n\n- Questions, feedback, or false-positive reports: audits@archonics.ai\n- Methodology and full audit examples: [archonics.ai](https://archonics.ai)\n- Issues with this MCP server: [github.com/archonics/mcp-audit/issues](https://github.com/archonics/mcp-audit)\n\n## License\n\nMIT. Use it, fork it, audit yourself.\n",
  "bytes": 4704,
  "sha": "3863b355e600b798d4450e3884b0e92fbe97197c9e15d46bd57e5126274182bf",
  "repo_slug": "archonics/mcp-audit",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_archonics_mcp_audit_75f57c95/readme"
}