search_gitlab_merge_requests
AI agents call search_gitlab_merge_requests to retrieve information from DCI MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Search operations are read-only by nature—they retrieve and query data without side effects. Even though the description is empty (which slightly lowers confidence), the tool name is explicit enough to classify confidently. The low severity reflects that reading merge request metadata poses minimal risk of unintended harm when misused by an AI agent.
From the tool's definition Tool name 'search_gitlab_merge_requests' indicates a query operation on GitLab merge requests. No description provided, but the 'search' prefix and 'merge_requests' object strongly suggest retrieval and analysis of existing data without modification.
Attacks that exploit this kind of access
search_gitlab_merge_requests. It is categorised as a Read tool in the DCI MCP Server MCP Server, which means it retrieves data without modifying state.
Register the DCI MCP Server MCP server in PolicyLayer and add a rule for search_gitlab_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 DCI MCP Server. Nothing to install.
search_gitlab_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 search_gitlab_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 search_gitlab_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.
search_gitlab_merge_requests is provided by the DCI MCP Server MCP server (redhat-community-ai-tools/dci-mcp-server). 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 →