mcp-tool-surface-testing SKILL.md skillA
mcp-tool-surface-testing from arasz/ai-badger is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add arasz/ai-badger/mcp-tool-surface-testing@v1.0.0Pins v1.0.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- arasz/ai-badger
- Path
features/mcp/skills/mcp-tool-surface-testing/SKILL.md- Versions recorded
- 4
- Latest version
- v1.0.0, committed Aug 7, 2026
- First version recorded
- Aug 7, 2026
- Size
- 7,074 bytes
- Repository stars
- 3
- License
- MIT
Use when testing every tool an MCP server exports: black-box expectations-first audit (expectations → call → compare), live contract vs docs-drift findings, destructive-tool safety controls, dependency-ordered execution, and a results doc committed to the repo. Triggers: 'test all tools', 'does every MCP tool work', server surface changed.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# MCP tool-surface testing Systematic black-box test of every tool an MCP server exports, with the expectations written down before any call and a results doc as the deliverable. The user's explicit method (verified on a 21-tool surface, 2026-08-06): **expectations first, then call, then compare** — never reverse the order, or the test degenerates into exploratory guessing. ## When to use - "test all tools exported by X", "full-test-all-tools", "does every MCP tool work" - A server's surface changed (tools added/removed) and you want a live contract audit - Before writing agent guidance that depends on tool response shapes ## Procedure 1. **Enumerate the surface.** Sources, in order: the project's mcp-index (`.ai-badger/mcp-tools.json` — per-server tool lists), the host's tool catalog (deferred tool list), `list_prompts` for prompt tools. Note the count (e.g. 19 memory tools + 2 prompts = 21). 2. **Gather the contract, then write expectations.** Three sources, all read BEFORE any call: - the docs tool table (often stale — flag drift as a finding, don't silently follow it) - live tool schemas (`tool_describe` per tool — exact param names, required flags) …
Read the whole file at its exact version.
How to install
mdr add arasz/ai-badger/mcp-tool-surface-testing@sha256:dd7784b0d4ad992bThe line at the top of this page pins the label v1.0.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_7lktxmq7ddhjaqhk)
0 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 4 versions of this file, all committed on Aug 7, 2026.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.0.0 latest | 2026-08-07 | bf192ea | 7,074 B | A | view · diff |
| v1.0.0 | 2026-08-07 | 6c187e9 | 7,093 B | A | view · diff |
| v1.0.0 | 2026-08-07 | 7cebf20 | 7,160 B | A | view · diff |
| git:20260807.bfbf1be | 2026-08-07 | bfbf1be | 6,877 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (7074 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
arasz/ai-badger · 3 stars · license MIT · pushed 2026-10-20 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_7lktxmq7ddhjaqhk GET https://markdownregistry.com/api/v1/resolve?ref=arasz/ai-badger/mcp-tool-surface-testing GET https://markdownregistry.com/api/v1/blob/dd7784b0d4ad992bd054f477f5e90c7b867d609e08cf5be2f215f6076563d0ac
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.