correctover-audit
OfficialClick on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@correctover-audit audit https://mcp.example.com/mcp for session-security issues"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
correctover-audit-mcp
Free self-service MCP session-security audit as an MCP server. Ask your agent to audit an MCP endpoint and get a re-verifiable verdict (e.g. unauthenticated-surface) from 3 read-only probes — no handshake forgery, no exploit payloads.
Part of the Session-as-Identity research line: DSHCorrectover/mcp-session-audit (protocol + CI action + evidence).
Install (one line)
claude mcp add correctover-audit -- npx -y github:DSHCorrectover/correctover-audit-mcpThen ask your agent: "audit https://your-server.example/mcp for session-security issues".
Related MCP server: passmcp-server
What it checks
probe | meaning |
| does the server issue a session at all? |
| can an anonymous client enumerate the full tool inventory? |
Verdict classes: unauthenticated-surface (exposed) / authenticated-ok / error-*.
Honest scope
Read-only probes only; audit endpoints you own or are authorized to test.
The verdict is evidence-grade (timestamps + reproduction command), not a certification.
Deeper fail-closed review with signed evidence dossiers: wangguigui@correctover.com
MIT © 2026 Guigui Wang (Correctover) — "We sell the verdict, and you can re-verify it yourself."
Available Tools
1 toolaudit_mcp_serverA
Run a free, read-only session-security audit against an MCP server endpoint (3 probes, no handshake forgery). Returns a re-verifiable verdict such as "unauthenticated-surface". Use on endpoints you own or are authorized to test.
Inputs: url (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 1 tool
There is only one tool, so there is no possibility of misselection between tools. Its purpose (run a read-only security audit against an MCP endpoint) is stated unambiguously in the description.
A single tool named audit_mcp_server follows a clear verb_noun snake_case convention. With one tool there is no mixed convention to create inconsistency, though the pattern is only weakly demonstrated.
The server is intentionally narrow, but a surface of exactly one tool is thin by the rubric's standards and leaves no supporting operations. It is borderline rather than mismatched, since the single tool does define the whole product.
For the stated purpose, one call returns a verdict, but the surface offers no way to list or re-fetch prior audits, compare results over time, or scope/configure probes. These are workable gaps but notable omissions for an audit-oriented service.
Related MCP Connectors
Check an A2A agent before you delegate, or an MCP server's measured conduct. Free, no key.
Scan any website or MCP server for agent-trust-readiness; returns a signed, verifiable scorecard.
Scans remote MCP servers for protocol, security, and TLS issues; exposes scan tools via MCP.
Experimental MCP server for current empirical verification of explicit public HTTPS endpoint claims.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceProvides safe network reconnaissance through DNS resolution, TLS inspection, HTTP security header grading, and bounded port scanning over the stateless MCP protocol.MIT
- AlicenseNot gradedqualityBmaintenanceEnables an agent to evaluate a target MCP server and verify attestations about it from inside the editor, using read-only, allowlisted tools that never send credentials.GPL 3.0
- AlicenseAqualityBmaintenanceEnables AI assistants to run read-only exposure scans against MCP servers that front databases, surfacing unauthenticated access, role/tool leaks, write-capable tools, and locally stored credentials, then returning plain-language findings.3Apache 2.0
- AlicenseBqualityCmaintenanceEnables read-only security assessment of a public MCP endpoint by sending initialize and tools/list requests and returning a 0–100 score covering transport, auth, overly broad tools, injection phrasing, and rug-pull definition changes, plus a 12-probe prompt-injection suite against a bot you own that flags leaked system prompts, tool dumps, secrets, exfiltration channels, and canary obedience.2MIT