Check the code for JijModeling rules.
AI agents call jm_check to retrieve information from Jij MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs static code analysis and validation against JijModeling rules. It retrieves and analyzes code to identify compliance issues without modifying, executing, or deleting any data. Static code checkers are inherently Read operations—they query and examine code without side effects. No data is created, modified, deleted, or executed; the tool merely inspects and reports findings.
From the tool's definition Tool name 'jm_check' and description 'Check the code for JijModeling rules' indicate static analysis/validation with no side effects.
Attacks that exploit this kind of access
Check the code for JijModeling rules. It is categorised as a Read tool in the Jij MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Jij MCP Server MCP server in PolicyLayer and add a rule for jm_check: 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 Jij MCP Server. Nothing to install.
jm_check is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the jm_check 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 jm_check. 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.
jm_check is provided by the Jij MCP Server MCP server (jij-inc/jij-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 →