list_pull_requests
List pull requests in a GitHub repository. If the user specifies an author, then DO NOT use this tool and use the search_pull_requests tool instead.
This record as markdown: /tools/github/list-pull-requests.md
What list_pull_requests does on GitHub
AI agents call list_pull_requests to retrieve information from GitHub without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
base | string | — | Filter by base branch |
head | string | — | Filter by head user/org and branch |
page | number | — | Page number for pagination (min 1) |
repo | string | — | Repository name |
sort | string | — | Sort by |
owner | string | — | Repository owner |
state | string | — | Filter by state |
perPage | number | — | Results per page for pagination (min 1, max 100) |
direction | string | — | Sort direction |
Parameters from the server's own tool schema.
Why list_pull_requests is rated Low
This tool retrieves and queries pull request data from a GitHub repository without modifying, deleting, or executing any operations. It is a straightforward read-only data retrieval function, making it low severity with minimal blast radius if misused by an AI agent.
From the tool's definition Tool name is 'list_pull_requests' and description states 'List pull requests in a GitHub repository' — listing is a retrieval operation with no side effects.
Attacks that exploit this kind of access
The rule that runs list_pull_requests safely
PolicyLayer is an MCP gateway: it sits between your AI agents and GitHub, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For list_pull_requests, this is the rule to start with:
list_pull_requests is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect GitHub, apply this rule, and every list_pull_requests call is checked against it from then on.
Questions about list_pull_requests
List pull requests in a GitHub repository. If the user specifies an author, then DO NOT use this tool and use the search_pull_requests tool instead. It is categorised as a Read tool in the GitHub MCP Server, which means it retrieves data without modifying state.
list_pull_requests accepts 9 parameters: base, head, page, repo, sort, owner, state, perPage, direction. The full parameter table on this page comes from the server's own tool schema.
Register the GitHub MCP server in PolicyLayer and add a rule for list_pull_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 GitHub. Nothing to install.
list_pull_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 list_pull_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 list_pull_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.
list_pull_requests is provided by the GitHub MCP server (oci:ghcr.io/github/github-mcp-server:1.3.0). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on GitHub, and thousands of servers like it.
This server
Across the catalogue