coverage
Runs tests with coverage and returns structured coverage summary per file.
This record as markdown: /tools/io-github-dave-london-github/coverage.md
What coverage does on Github
AI agents invoke coverage to trigger actions in Github. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.
Why coverage is rated High
The tool runs tests (executing code) and collects coverage results. While it doesn't directly modify or delete data, executing arbitrary test suites can trigger side effects depending on the tests. Classified as Execute with medium severity since the blast radius is generally limited to the test environment, but test execution can have unintended side effects.
From the tool's definition "Runs tests with coverage" — the tool actively executes test suites and collects coverage data
Attacks that exploit this kind of access
The rule that runs coverage safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Github, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For coverage, this is the rule to start with:
coverage stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Github, apply this rule, and every coverage call is checked against it from then on.
Questions about coverage
Runs tests with coverage and returns structured coverage summary per file. It is categorised as a Execute tool in the Github MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Github MCP server in PolicyLayer and add a rule for coverage: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Github. Nothing to install.
coverage is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the coverage rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for coverage. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
coverage is provided by the Github MCP server (@paretools/github). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Github, and thousands of servers like it.
Across the catalogue