AI agents use create_or_update_file to create or update resources in Gitlab — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Gitlab environment.
This tool modifies data in a GitLab repository by creating new files or updating existing ones. These operations are reversible (files can be edited or deleted separately), placing it squarely in the Write category. Severity is high because an AI agent could inadvertently modify critical source code, configuration files, or documentation, potentially breaking builds or introducing bugs.
From the tool's definition Tool description states: "Create or update a single file in a GitLab project". The verbs "create" and "update" directly indicate reversible write operations on repository files.
Documented attack patterns abuse exactly the kind of access create_or_update_file gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Gitlab, and nothing reaches the server without passing your rules. This is the rule we recommend for create_or_update_file:
{
"version": "1",
"default": "deny",
"tools": {
"create_or_update_file": {
"limits": [
{
"counter": "create_or_update_file_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}create_or_update_file stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Create or update a single file in a GitLab project. It is categorised as a Write tool in the Gitlab MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Gitlab MCP server in PolicyLayer and add a rule for create_or_update_file: 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 Gitlab. Nothing to install.
create_or_update_file 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_or_update_file 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_or_update_file. 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_or_update_file is provided by the Gitlab MCP server (yoda-digital/mcp-gitlab-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 88 Gitlab tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
88 Gitlab tools catalogued and risk-classified — across an index of 42,500+ MCP servers.