mcp-github

A Cursor rule that defines how CursorRIPER connects to GitHub, a service for hosting code repositories and reviewing changes.

In plain words
What is it for?
Use it for GitHub-related work such as finding, creating, forking, or cloning repositories; creating branches; reading or pushing files; and opening, reviewing, merging, or listing pull requests.
Why use it?
It provides a consistent map from repository tasks to GitHub operations, so the agent knows how to handle files, branches, pull requests, and repository searches.

Cursor rule for Cursor

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add rules/omril321/automated-notebooklm/mcp-github
Clone the repo
git clone --depth 1 https://github.com/omril321/automated-notebooklm

Made for: Cursor.

Per session 979 This file is loaded in full into every session.
When invoked 979 The same file โ€” it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00979 $0.00979
Opus 5 $0.00490 $0.00490
Sonnet 5 $0.00196 $0.00196
Haiku 4.5 $0.00098 $0.00098

Measured 2d ago against content hash 6f3b8f08dac4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-github scanned grade A with 0 findings against 26 rules in 11 categories โ€” prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency โ€” measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.cursor/rules/riper/mcp-github.mdc ยท 127 lines

How it starts

The opening of the file, as written. The whole thing โ€” 127 lines โ€” stays where its author put it; the contents beside it link to each section on GitHub.

๐Ÿ™ GitHub MCP Integration for CursorRIPER ฮฃ

Symbol: ฮ˜ (Theta)

Version: 1.0.0

๐Ÿ“‹ Service Definition

service = "GitHub Operations"
symbol = "ฮ˜"
requires = "@modelcontextprotocol/server-github"

๐Ÿ”ง Operation Mapping

ฮ˜_ops = {
  repo: {
    create: "@modelcontextprotocol-server-github:create_repository",
    search: "@modelcontextprotocol-server-github:search_repositories", 
    fork: "@modelcontextprotocol-server-github:fork_repository",
    clone: "git clone via get_file_contents"
  },
  branch: {
    create: "@modelcontextprotocol-server-github:create_branch",
    list: "@modelcontextprotocol-server-github:list_commits",
    checkout: "via create_branch with from_branch"
  },
  file: {
    create: "@modelcontextprotocol-server-github:create_or_update_file",
    push: "@modelcontextprotocol-server-github:push_files",
    get: "@modelcontextprotocol-server-github:get_file_contents"
  },
  pr: {
    create: "@modelcontextprotocol-server-github:create_pull_request",
    review: "@modelcontextprotocol-server-github:create_pull_request_review",
    merge: "@modelcontextprotocol-server-github:merge_pull_request",
    list: "@modelcontextprotocol-server-github:list_pull_requests"
  },
  issue: {
    create: "@modelcontextprotocol-server-github:create_issue",
    update: "@modelcontextprotocol-server-github:update_issue",
    comment: "@modelcontextprotocol-server-github:add_issue_comment",
    list: "@modelcontextprotocol-server-github:list_issues"
  }
}

๐Ÿ”’ Mode Restrictions

Mฮ˜ = {
  ฮฉโ‚: [search_*, list_*, get_*],                    # RESEARCH: read-only
  ฮฉโ‚‚: [search_*, list_*, get_*, fork_repository],   # INNOVATE: read + fork
  ฮฉโ‚ƒ: [all_ops],                                    # PLAN: all operations
  ฮฉโ‚„: [create_*, update_*, push_*, merge_*],        # EXECUTE: write ops
  ฮฉโ‚…: [get_*, list_*, search_*]                     # REVIEW: read-only
}

๐Ÿ”‘ Permission Matrix

โ„™ฮ˜ = {
  create: [ฮฉโ‚ƒ, ฮฉโ‚„],
  read: [ฮฉโ‚, ฮฉโ‚‚, ฮฉโ‚ƒ, ฮฉโ‚„, ฮฉโ‚…],
  update: [ฮฉโ‚ƒ, ฮฉโ‚„],
  delete: [ฮฉโ‚ƒ]
}

Read the full file on GitHub ยท 127 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen ยท 127 lines ยท 979 tokens per session scan A 6f3b8f08dac4

Subscribe to this mod's changes

mcp-github is a cursor rule published in the GitHub repository omril321/automated-notebooklm (15 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 979 tokens to every session, about $0.0049 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.