search_pull_requests
Search for pull requests in GitHub repositories using issues search syntax already scoped to is:pr
This record as markdown: /tools/github/search-pull-requests.md
What search_pull_requests does on GitHub
AI agents call search_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 |
|---|---|---|---|
page | number | — | Page number for pagination (min 1) |
repo | string | — | Optional repository name. If provided with owner, only pull requests for this repository are listed. |
sort | string | — | Sort field by number of matches of categories, defaults to best match |
order | string | — | Sort order |
owner | string | — | Optional repository owner. If provided with repo, only pull requests for this repository are listed. |
query | string | — | Search query using GitHub pull request search syntax |
perPage | number | — | Results per page for pagination (min 1, max 100) |
Parameters from the server's own tool schema.
Why search_pull_requests is rated Low
This tool retrieves and filters pull request data without creating, modifying, deleting, or executing any operations. The use of 'search' and read-only query syntax (GitHub issues search) confirms it is a Read operation with minimal security risk since it only exposes data accessible through standard GitHub APIs based on caller permissions.
From the tool's definition Tool description states it 'Search[es] for pull requests' and 'scoped to is:pr', indicating query/retrieval only with no mutation or execution capabilities.
Risk signalsAccepts freeform code/query input (query)
Attacks that exploit this kind of access
The rule that runs search_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 search_pull_requests, this is the rule to start with:
search_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 search_pull_requests call is checked against it from then on.
Questions about search_pull_requests
Search for pull requests in GitHub repositories using issues search syntax already scoped to is:pr. It is categorised as a Read tool in the GitHub MCP Server, which means it retrieves data without modifying state.
search_pull_requests accepts 7 parameters: page, repo, sort, order, owner, query, perPage. 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 search_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.
search_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 search_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 search_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.
search_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