Borrowing it
Nothing to install: this file belongs to alitiknazoglu/mcprobe. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/alitiknazoglu/mcprobe/main/.agents/skills/mcp-audit/SKILL.mdgit clone --depth 1 https://github.com/alitiknazoglu/mcprobeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/alitiknazoglu/mcprobe/mcp-audit)<a href="https://agentmods.dev/skills/alitiknazoglu/mcprobe/mcp-audit"><img src="https://agentmods.dev/badge/skills/alitiknazoglu/mcprobe/mcp-audit.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00091 | $0.01447 |
| Opus 5 | $0.00046 | $0.00724 |
| Sonnet 5 | $0.00018 | $0.00289 |
| Haiku 4.5 | $0.00009 | $0.00145 |
Grade A, and why
mcp-audit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit an MCP server (MCProbe)
MCProbe scores an MCP server's conformance — how reliably an AI agent can actually use it — across schema quality and behavioral robustness. Reach for it whenever the user wants to evaluate, test, compare, or debug an MCP server.
Pick the path that's available
A. MCProbe is connected as an MCP server (you have probe_* tools).
Run the four core tools in order:
probe_connect— dial the target: an HTTPS URL, or a stdio command.probe_report— the one-shot audit: lints the schemas, fuzzes behavior, and returns the full report + 0–100 score. (Useprobe_lint/probe_fuzzindividually if you want just one phase.)probe_disconnectwhen finished.
B. The mcprobe CLI is available (no MCP tools connected).
# Remote HTTP(S) server
npx mcprobe audit https://example.com/mcp --fuzz
# Local stdio server (the `npx some-server` style)
npx mcprobe audit --stdio "npx @acme/my-mcp-server" --fuzz
# A server that requires an API key
npx mcprobe audit https://api.acme.com/mcp --bearer "$ACME_TOKEN" --fuzz
npx mcprobe audit https://api.acme.com/mcp --header "X-API-Key: $ACME_KEY"
# Machine-readable output (for scripting / CI gates)
npx mcprobe audit https://example.com/mcp --fuzz --json
Omit --fuzz for a fast static (schema-only) audit. Add --json to parse the
result programmatically.
Auditing a server that needs credentials
If a target answers 401/Unauthorized, it needs a credential: pass it with
--bearer <token> (sends Authorization: Bearer …) or --header "Name: Value"
for anything else. MCPROBE_TARGET_TOKEN works instead of --bearer.
Three things to get right:
- Never invent or guess a credential, and never reuse one the user hasn't offered for this purpose. Ask the user for it, and prefer an environment variable over pasting the literal value into a command you echo back.
--bearerand--tokenare different keys.--bearerauthenticates to the server being audited;--tokenauthenticates to mcprobe.org forpush. Passing the MCProbe token as--bearerwould hand it to a third party.- A stdio server takes credentials through its own environment, not these
flags — the CLI rejects them for
--stdiotargets.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago First seen · 114 lines · 91 tokens per session scan A 451800062b52
mcp-audit is a skill published in the GitHub repository alitiknazoglu/mcprobe (6 stars, last pushed 1mo ago), licensed MIT. It adds 91 tokens to every session and 1,447 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.