GitHub MCP Server

github_list_prs

List pull requests in a GitHub repository, with optional filters for state, base branch, and sorting, to quickly locate relevant PRs for review or tracking.

Instructions

List pull requests in a repository with optional filters for state, base branch, and sorting

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "owner": "<owner>",
      "repo": "<repo>"
    },
    "name": "github_list_prs"
  }
}

Input Schema

Name	Required	Description	Default
`base`	No	Filter by base branch (e.g., "main")
`page`	No	Page number
`repo`	Yes	Repository name
`sort`	No	Sort by field	updated
`owner`	Yes	Repository owner (organization or username)
`state`	No	Filter by PR state	all
`per_page`	No	Results per page (max 100)
`direction`	No	Sort direction	desc

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Sep 6, 2026

TDQS

A3.5/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden of behavioral disclosure. It establishes that this is a read/list operation, but it does not mention pagination behavior, result shape, sorting defaults, or any rate-limit or scoping caveats. The five-word core leaves significant behavioral context undisclosed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single efficient sentence that front-loads the core operation and then lists the key filter dimensions. There is no filler, repetition, or unnecessary detail.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a list operation, the description plus a fully covered input schema gives the agent the essentials: required owner/repo and available filters. However, with no output schema and no mention of pagination or return contents, some context is missing, and the absence of any relationship to siblings leaves the tool somewhat contextually incomplete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the input schema fully documents owner, repo, state, sort, direction, page, per_page, and base. The description adds a high-level grouping of filters (state, base branch, sorting) but no syntax or meaning beyond the schema, so the baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('List'), a clear resource ('pull requests in a repository'), and names the optional filters (state, base branch, sorting). This distinguishes it from siblings like github_get_pr (single PR) and github_list_commits (commits) even without explicitly naming them.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies when to use it: whenever you need a list of pull requests with optional filtering. However, it provides no explicit guidance on when not to use it or when a sibling like github_get_pr would be more appropriate, so usage guidance is only implied rather than stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server