Mcp Audit
io.github.archonicsPublished by GitHub account archonicsv0.1.4Updated Oct 24, 2026
Free context-engineering audits for AI agents. BYOK Anthropic key. Top-3 findings per scan.
The publisher's own server: audit.domains - Domain Valuation
Overview
A local MCP server that audits AI agent system prompts, tool definitions and context payloads, returning the top three context-engineering issues per scan.
- What you can do
- Audit a pasted system prompt for role clarity, instruction conflicts, priority structure and token efficiency, returning three ranked issues with recommendations. Audit a pasted tool or function definition for description quality, parameter schema precision, error response design and discoverability. Audit a pasted or structurally described context payload for redundancy, freshness, ordering, truncation risk and prompt-cache use. Each scan returns the top three findings for one dimension.
- When to use it
- Useful when building or reviewing a production AI agent and wanting a quick second opinion on prompt wording, tool schemas or context packing before shipping or changing them. It is a lightweight free check, not a full audit or regression test suite.
- Requirements
- Runs locally via npx from the npm package, so Node.js is needed. Requires an Anthropic API key supplied in the ANTHROPIC_API_KEY environment variable; the audit engine calls Claude directly from the user's machine. No account or Archonics login is needed.
Installation
In SourceWeft
- Open Mcp Audit in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
Archonics MCP Audit Server
Free-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.
What you get: top-3 findings on your system prompts, tool definitions, or context packing, on demand, no account needed.
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.
Why this exists
Most 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.
The underlying audit engine applies Archonics Audit Methodology v1.0, the same spec that drives our paid audits.
Tools
audit_system_prompt
Paste a system prompt. Get back the three most important context engineering issues in it, ranked by severity, with specific recommendations.
Covers: role clarity, instruction conflicts, negative space, priority structure when instructions conflict, token efficiency, format specification precision, failure-mode coverage.
audit_tool_definition
Paste a tool/function definition. Get back the three most important issues affecting how reliably the model will call it.
Covers: description quality (the "when to use this tool" question), parameter schema precision, parameter documentation, error response design, discoverability.
audit_context_packing
Paste a representative context payload (or describe it structurally). Get back the three most important efficiency and quality issues.
Covers: content inventory, redundancy across sections, freshness/relevance, ordering, truncation risk, prompt-cache utilization.
Installation
Claude Desktop
Add to your claude_desktop_config.json:
Cursor
Add to your .cursor/mcp.json:
Claude Code
Then set ANTHROPIC_API_KEY in your environment.
Why does it need my Anthropic API key?
The audit engine runs on Claude. You bring your own API key so:
- Audit submissions go directly from your machine to Anthropic's API, never through Archonics servers.
- Your costs are transparent — a typical audit uses 2,000–4,000 tokens, well under a penny.
- There's no "free but actually limited" rate-limit surprise. Your API key, your limits.
If 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.
Privacy
Submitted 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.
Aggregated, 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.
Details: archonics.ai/privacy
Upgrade paths
If the free scan surfaces issues worth fixing, two paid tiers go deeper:
- 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.
- Full Audit — $750. Human-reviewed audit of a complete agent system. 15-25 page report tuned to your team's context. Contact [email protected].
Contact
- Questions, feedback, or false-positive reports: [email protected]
- Methodology and full audit examples: archonics.ai
- Issues with this MCP server: github.com/archonics/mcp-audit/issues
License
MIT. Use it, fork it, audit yourself.
Source: README.md at commit 25fd10c
Tools
0Version history
1- v0.1.4LatestSep 16, 2026
Score
50% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts
Other Audit integrations
audit.domains - Domain Valuation
domains.auditOfficial publisher
Deterministic domain-name valuation: fair-value intervals, comparable recorded sales, availability checks, and a verified for-sale listing market.
Revenue Agent — OpenAPI Audit & Change Detection
news.prhOfficial publisher
A remote MCP endpoint that audits OpenAPI specifications and detects API changes, charging $0.10 USDC per analysis via x402 on Base.
Zovo Dependency Audit
Published by GitHub account theluckystrike
Audits pasted npm and PyPI dependency manifests for known vulnerabilities, licenses and outdated versions, returning Markdown, CSV and PDF reports.
SEO Audit & Broken Link Checker
Published by GitHub account prometheus-maker
An Apify-hosted MCP server that audits a website's pages for SEO metadata and finds broken links and images, returning per-page scores.
FinePrint AI Legal Risk & Contract Audit MCP Server
Published by GitHub account RitualDev-Lab
Local in-memory scanner that grades legal contracts, NDAs and leases for risk and drafts redline amendments for coding agents.