mypy
Runs mypy and returns structured type-check diagnostics (file, line, severity, message, code).
This record as markdown: /tools/io-github-dave-london-pare-test/mypy.md
What mypy does on Test
AI agents invoke mypy to trigger actions in Test. 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 mypy is rated High
The tool runs an external program (mypy) on code files. This is an execution action that invokes a subprocess. While mypy itself is read-only (it only analyzes code, doesn't modify it), the act of running an arbitrary tool against files qualifies as Execute.
From the tool's definition 'Runs mypy' — explicitly executes the mypy static type checker as an external process and returns structured diagnostics
Attacks that exploit this kind of access
The rule that runs mypy safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Test, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For mypy, this is the rule to start with:
mypy 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 Test, apply this rule, and every mypy call is checked against it from then on.
Questions about mypy
Runs mypy and returns structured type-check diagnostics (file, line, severity, message, code). It is categorised as a Execute tool in the Test MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Test MCP server in PolicyLayer and add a rule for mypy: 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 Test. Nothing to install.
mypy 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 mypy 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 mypy. 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.
mypy is provided by the Test MCP server (Dave-London/Pare). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Test, and thousands of servers like it.
This server
Across the catalogue