Free read-only check of a public GitHub repo for eight security signals related to the EU CRA.
Scored across 1 tool
There is only one tool, so there is nothing to confuse it with. Its purpose (read a public GitHub repo and report eight CRA-related security signals) is stated precisely enough that an agent knows exactly when to call it.
The single name check_github_repo follows a clear verb_noun snake_case convention that matches the read-only checking behavior it performs. No competing conventions exist to conflict with it.
One tool is a thin surface for a server, even a narrowly scoped one; the entire product is a single call. It earns its place, but there is no auxiliary operation (e.g. checking several repos or fetching the raw signal detail) to round out the set.
For its stated purpose the single check is self-contained, with per-signal remediation hints and explicit 'not measured' handling. However, the surface has notable gaps: one repository per call with no batch or org-wide sweep, no way to re-read a partially fetched signal on demand, and rate limiting that forces agents to pace themselves.
Reads up to about thirty public pages of a public GitHub repository and reports which of eight security signals are visible: a security policy that names a contact or a reporting link, a software bill of materials, proof of where releases come from, a lockfile, automatic updates of dependencies, security scans in CI, recent maintenance and a licence. For each signal that is not visible the answer says what would make it visible; a signal that could not be read completely is marked not measured, never as a gap. The eight signals are a selection related to topics in the EU Cyber Resilience Act. This is an indication from public data, not a compliance check, not a certificate and not legal advice; private repositories and hosts other than GitHub cannot be checked. Read only. Limited to a few checks per ten minutes per address.
| Name | Required | Description | Default |
|---|---|---|---|
| repo | Yes | A public GitHub repository as owner/name, or its https://github.com/owner/name address |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the read-only annotations, the description discloses the approximate number of pages read, the exact signal categories, how gaps and unmeasured signals are represented, and that results are indications rather than compliance conclusions. It also discloses rate limiting and host restrictions, which are important operational traits not present in the annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is front-loaded with the core behavior and then adds necessary caveats about signal interpretation, scope, and rate limits. It is somewhat dense and long, but nearly every clause carries material information for correct use.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema, the description adequately explains what the tool returns: which of eight signals are visible, what makes missing signals visible, and how incomplete readings are marked. Combined with the annotations and simple schema, this is complete enough for an agent to invoke the tool correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
There is only one parameter and the schema already documents it at 100% coverage, including the owner/name or full URL format. The description adds only that the repository must be public, which is useful but does not add syntax or format detail beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb and resource: it reads public GitHub repository pages and reports eight named CRA-related security signals. It clearly distinguishes its scope from a compliance check, certificate, or legal advice, so an agent can identify exactly what the tool does.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It states clear boundaries: only public GitHub repositories can be checked, private repositories and non-GitHub hosts cannot, and usage is rate limited. It does not compare alternatives, but there are no sibling tools to contrast, so the guidance is strong though not exhaustive.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
check_github_repoFree deterministic security scan of public git repos: OSV.dev vulnerable deps, secrets, config lint.
Screens public GitHub repos and PRs to generate risk maps, findings, and merge-readiness signals.
Evaluates any GitHub repository for license risk, maintenance velocity, stars/forks, and supply-c.
Evaluates any GitHub repository for license risk, maintenance velocity, stars/forks, and security.
Add one secure layer between your agents and this server.
