mcp-research — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited mcp-research (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Use MCP-provided tools to retrieve current, verifiable information instead of relying on memory for fast-changing libraries, APIs, and ecosystem guidance.
mcp-research.Skip the notice when the user asked for the skill by name or slash command; spelling and spacing need not match. A phrase from this skill's own trigger list is not a name — naming the work is not naming the skill.
Inventory the docs and research tools present at runtime and match on capability, not on an exact tool name. The same server is named differently depending on how it is installed — user scope gives mcp__jina__read_url, a plugin-bundled copy gives mcp__plugin_<plugin>_jina__read_url, and other harnesses namespace differently again. If tools are deferred or hidden, discover and load them first.
| Capability need | What to look for (examples, not an exhaustive list) |
|---|---|
| Library / API docs | a docs tool with library-id resolution (e.g. Context7 resolve-library-id, then query-docs) |
| Code-centric examples | a code-context search tool (e.g. Exa get-code-context) across docs, GitHub, and Q&A sites |
| Broad current web context | a web-search tool (e.g. Exa web-search, Jina search-web) for announcements and release notes |
| Clean page extraction | a reader that returns full page text (e.g. Jina read-url) |
| Papers / PDFs | academic search or PDF extraction (e.g. Jina search-arxiv, extract-pdf) |
Use the papers/PDF row only when the task needs paper-level or PDF-structured research. When none of these is available, fall back to native web search and fetch, and say so in the answer.
/org/project form, or the equivalent) is already provided.~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.