black
Runs Black code formatter and returns structured results (files changed, unchanged, would reformat).
This record as markdown: /tools/io-github-dave-london-github/black.md
What black does on Github
AI agents invoke black 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 black is rated High
The tool executes the Black formatter, which rewrites source files in place. This is an Execute action (running an external tool/process) that also has Write side effects (modifying files). Since it can alter file contents across potentially many files, severity is medium.
From the tool's definition 'Runs Black code formatter' — actively executes an external code formatting tool that modifies files on disk
Attacks that exploit this kind of access
The rule that runs black 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 black, this is the rule to start with:
black 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 black call is checked against it from then on.
Questions about black
Runs Black code formatter and returns structured results (files changed, unchanged, would reformat). 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 black: 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.
black 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 black 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 black. 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.
black 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