Erstellt eine neue Semgrep-Regel
AI agents use create_rule to create or update resources in Semgrep MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Semgrep MCP Server environment.
The tool creates new Semgrep rules, which are reversibly writable configuration objects. This is a Write operation rather than Execute because it creates the rule definition itself, not executes code analysis. However, it carries high severity because malicious rules could be injected to suppress legitimate security findings or introduce false positives that degrade analysis integrity in the development environment.
From the tool's definition Tool name 'create_rule' and description state it 'creates' ('Erstellt') a new Semgrep rule. This is a data creation operation that modifies the rule configuration state.
Attacks that exploit this kind of access
Erstellt eine neue Semgrep-Regel. It is categorised as a Write tool in the Semgrep MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Semgrep MCP Server MCP server in PolicyLayer and add a rule for create_rule: 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 Semgrep MCP Server. Nothing to install.
create_rule is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the create_rule 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 create_rule. 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.
create_rule is provided by the Semgrep MCP Server MCP server (stefanskiasan/semgrep-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →