Fetch a merge request by ID from the given provider.
AI agents call get_merge_request to retrieve information from Ubuntu MCP Servers without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves (fetches) an existing merge request by its ID from a specified provider. This is a read-only query operation that does not modify, delete, or execute any code. The term 'fetch' confirms data retrieval without side effects.
From the tool's definition Tool name is 'get_merge_request' and description states 'Fetch a merge request by ID' — these are unambiguous retrieval operations with no side effects.
Attacks that exploit this kind of access
Fetch a merge request by ID from the given provider. It is categorised as a Read tool in the Ubuntu MCP Servers MCP Server, which means it retrieves data without modifying state.
Register the Ubuntu MCP Servers MCP server in PolicyLayer and add a rule for get_merge_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 Ubuntu MCP Servers. Nothing to install.
get_merge_request 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_merge_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 get_merge_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.
get_merge_request is provided by the Ubuntu MCP Servers MCP server (lvoytek/ubuntu-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 →