Submit fixes for a blocked session. Must explain what was fixed and why.
AI agents use submit_fixes to create or update resources in MCP Pyrefly — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Pyrefly environment.
The tool creates or modifies data (code fixes, session state) in a reversible manner. It does not execute arbitrary code, delete data irreversibly, or move money. While it operates within a gamified error-checking system, the tool's core action is to accept and record corrections—a write operation.
From the tool's definition Tool name 'submit_fixes' and description 'Submit fixes for a blocked session' indicate modification of code or session state. The requirement to 'explain what was fixed' confirms it modifies data (code corrections, session state).
Attacks that exploit this kind of access
Submit fixes for a blocked session. Must explain what was fixed and why. It is categorised as a Write tool in the MCP Pyrefly MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP Pyrefly MCP server in PolicyLayer and add a rule for submit_fixes: 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.
submit_fixes 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 submit_fixes 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 submit_fixes. 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.
submit_fixes 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 →