create_file_tool
AI agents use create_file_tool to create or update resources in MCP Gitlab — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Gitlab environment.
File creation is a write operation that modifies repository state but is reversible (files can be deleted). It is not destructive since deletion is possible, not financial, and does not execute arbitrary code. Severity is high because creating files in a repository could introduce malicious code, overwrite critical configuration, or affect deployment pipelines if the agent misuses this without proper validation.
From the tool's definition Tool name is 'create_file_tool' which performs file creation. Sibling tools on the GitLab MCP server include create_branch_tool, create_issue_tool, create_merge_request_tool, and create_label_tool—all write operations.
Attacks that exploit this kind of access
create_file_tool. It is categorised as a Write tool in the MCP Gitlab MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP Gitlab MCP server in PolicyLayer and add a rule for create_file_tool: 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 Gitlab. Nothing to install.
create_file_tool 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_file_tool 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_file_tool. 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_file_tool is provided by the MCP Gitlab MCP server (mcp-gitlab-crunchtools). 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 →