Fetch pull request details from GitHub/GitLab
AI agents call fetch_pull_request to retrieve information from GitLab 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 and queries pull request data without creating, modifying, deleting, or executing any operations. It is a read-only operation that returns information about pull requests. The worst-case misuse scenario (an AI agent fetching PR details it shouldn't access) poses minimal risk compared to other categories, making this low severity.
From the tool's definition Tool name is 'fetch_pull_request' and description states 'Fetch pull request details from GitHub/GitLab' — both indicate a retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
Fetch pull request details from GitHub/GitLab. It is categorised as a Read tool in the GitLab Review MCP MCP Server, which means it retrieves data without modifying state.
Register the GitLab Review MCP server in PolicyLayer and add a rule for fetch_pull_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 Review MCP. Nothing to install.
fetch_pull_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 fetch_pull_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 fetch_pull_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.
fetch_pull_request is provided by the GitLab Review MCP server (lininn/gitlab-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 →