Check Python code for errors and inconsistencies using Pyrefly.
AI agents call check_code to retrieve information from MCP Pyrefly without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs static analysis and returns diagnostic information about code without modifying, deleting, executing, or moving resources. While the broader server context mentions 'gamification' and 'psychological manipulation,' those are motivational design patterns in the server—the tool itself is purely a read operation that checks code and reports results.
From the tool's definition Tool name is 'check_code' with description stating it 'Check[s] Python code for errors and inconsistencies using Pyrefly.' This is a code analysis/querying operation with no modification, deletion, or execution of external systems.
Attacks that exploit this kind of access
Check Python code for errors and inconsistencies using Pyrefly. It is categorised as a Read tool in the MCP Pyrefly MCP Server, which means it retrieves data without modifying state.
Register the MCP Pyrefly MCP server in PolicyLayer and add a rule for check_code: 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 MCP Pyrefly. Nothing to install.
check_code 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 check_code 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 check_code. 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.
check_code is provided by the MCP Pyrefly MCP server (kimasplund/mcp-pyrefly). 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 →