Mcp Audit
Connects to Anthropic's API using your own key to run context engineering audits on AI agent configurations. Exposes three tools: audit_system_prompt for finding instruction conflicts and role clarity issues, audit_tool_definition for checking function call reliability problems, and audit_context_packing for spotting redundancy and truncation risks. Returns top three findings per scan with severity rankings and specific recommendations. Useful when you're debugging why an agent isn't following instructions or when tools aren't getting called reliably. The audit engine applies Archonics' methodology but runs client side, so your prompts never hit their servers. Free tier gives you quick feedback; paid tiers available if you need full reports.
- tools
- 3
- auth
- Secret needed
- transport
- STDIO
- env var
- 1
- last updated
- Apr 25, 2026
Tools
3 toolsPublic tool metadata for what this MCP can expose to an agent.
audit_system_promptPaste a system prompt. Get back the three most important context engineering issues in it, ranked by severity, with specific recommendations.
Paste a system prompt. Get back the three most important context engineering issues in it, ranked by severity, with specific recommendations.
No parameter schema in public metadata yet.
audit_tool_definitionPaste a tool/function definition. Get back the three most important issues affecting how reliably the model will call it.
Paste a tool/function definition. Get back the three most important issues affecting how reliably the model will call it.
No parameter schema in public metadata yet.
audit_context_packingPaste a representative context payload (or describe it structurally). Get back the three most important efficiency and quality issues.
Paste a representative context payload (or describe it structurally). Get back the three most important efficiency and quality issues.
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageConfiguration
ANTHROPIC_API_KEY*secretYour Anthropic API key. Required — the audit engine calls Claude directly from your machine.
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
Details
- Repository
- github.com/archonics/mcp-audit
- Category
- AI & LLM Tools
- Package
@archonics/mcp-audit- Transport
- STDIO
- Auth
- Required
- Registry
- MCP registry, active
Related AI & LLM Tools MCP servers
View all
memexayushagrawal288/memexPersistent memory for AI agents — semantic + recency search, ONNX embeddings, Docker Compose.0stars
Conductor Graph Mcpbase76-research-lab/conductor-graph-mcpExposes a CognOS agent system as a machine-readable graph. Full system snapshot with one tool call.0stars
Mcp Grantiqbch1212/mcp-grantiqSearch US grants + federal contracts (Grants.gov + SAM.gov) from any LLM.0stars
Dear Userbleedmode/dearuserTells you how you and your Claude agent actually work together. Local-only, no API keys.0stars
Quarterbackbobbyrgoldsmith/quarterbackStrategic task prioritization and agent orchestration for multi-project operators0stars
Gonka Second Opinion (multi-model)bystray/gonka-mcp-serverA second opinion for AI agents: one prompt across several live Gonka models + roles, one call.0stars