AI agents invoke api_request to trigger actions in Gitlab Api. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
With an empty description, the exact behavior is unknown. However, 'api_request' on a GitLab API server likely allows making arbitrary API requests, which could span Read, Write, Destructive, or Execute actions depending on the HTTP method and endpoint used.
From the tool's definition Tool name is 'api_request' on a GitLab API MCP server; description is empty and uninformative.
Documented attack patterns abuse exactly the kind of access api_request gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Gitlab Api, and nothing reaches the server without passing your rules. This is the rule we recommend for api_request:
{
"version": "1",
"default": "deny",
"tools": {
"api_request": {
"limits": [
{
"counter": "api_request_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}api_request stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
api_request. It is categorised as a Execute tool in the Gitlab Api MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Gitlab Api MCP server in PolicyLayer and add a rule for api_request: 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 Api. Nothing to install.
api_request is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the api_request 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 api_request. 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.
api_request is provided by the Gitlab Api MCP server (knuckles-team/gitlab-api). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Gitlab Api, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
26 Gitlab Api tools catalogued and risk-classified — across an index of 43,000+ MCP servers.