semgrep
Runs Semgrep static analysis with structured rules and findings. Returns structured finding data with severity summary.
This record as markdown: /tools/io-github-dave-london-github/semgrep.md
What semgrep does on Github
AI agents invoke semgrep 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 semgrep is rated High
The tool executes an external program (Semgrep) that performs static analysis on code. While read-like in intent (finding security issues), it actively runs a process/command with arguments that could be pointed at arbitrary code or repositories. Misuse could involve scanning sensitive codebases, leaking code contents, or being used as a stepping stone in an attack chain.
From the tool's definition 'Runs Semgrep static analysis' — actively executes a static analysis tool against code
Attacks that exploit this kind of access
The rule that runs semgrep 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 semgrep, this is the rule to start with:
semgrep 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 semgrep call is checked against it from then on.
Questions about semgrep
Runs Semgrep static analysis with structured rules and findings. Returns structured finding data with severity summary. 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 semgrep: 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.
semgrep 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 semgrep 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 semgrep. 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.
semgrep 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