get_project_merge_requests
AI agents call get_project_merge_requests to retrieve information from GitLab Code Review MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or lists merge requests from a GitLab project with no side effects. No modifications, deletions, approvals, or external executions are implied. The absence of a description is mitigated by the clear intent from the tool name and context of sibling read-only tools.
From the tool's definition Tool name 'get_project_merge_requests' indicates data retrieval; listed alongside tools like 'fetch_merge_request' and 'fetch_merge_request_diff' which are read operations.
Attacks that exploit this kind of access
get_project_merge_requests. It is categorised as a Read tool in the GitLab Code Review MCP MCP Server, which means it retrieves data without modifying state.
Register the GitLab Code Review MCP server in PolicyLayer and add a rule for get_project_merge_requests: 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 Code Review MCP. Nothing to install.
get_project_merge_requests 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 get_project_merge_requests 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 get_project_merge_requests. 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.
get_project_merge_requests is provided by the GitLab Code Review MCP server (lininn/gitlab-code-review-mcp). 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 →