github-ghas-tools

github-ghas-tools is an MCP server for Claude Code from devantler-tech/agent-plugins. Its token cost is not measured, scanned A, original, Apache-2.0.

A read-only connection to GitHub security tools. GitHub is a service for hosting code and coordinating software projects; these tools cover code security, exposed secrets, security advisories, and dependency updates.

In plain words
What is it for?
Use it to search code, review security alerts, check for leaked secrets, inspect security advisories, and examine dependency-update information.
Why use it?
It gives the agent a central way to inspect security findings and related code without allowing it to change the repository.

MCP server for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: listed in a Claude config.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the agentic-engineering plugin — 87 skills, 4 agents, 11 MCP servers shipped together

One of 11 entries in .mcp.json upstream. Installing this one merges just its entry into your config; the other 10 are separate, each on its own page.

Good fit Use it to search code, review security alerts, check for leaked secrets, inspect security advisories, and examine dependency-update information.

Compare 6 mcp servers from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add devantler-tech/agent-plugins
Claude Code
/plugin install agentic-engineering

Made for: Claude Code.

Or install agentic-engineering, the plugin that ships this one along with the rest of its 87 skills, 4 agents, 11 MCP servers.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for github-ghas-tools

README.md
[![agentmods](https://agentmods.dev/badge/mcp/devantler-tech/agent-plugins/agentic-engineering-github-ghas-tools/github.svg)](https://agentmods.dev/mcp/devantler-tech/agent-plugins/agentic-engineering-github-ghas-tools)
Your own site
<a href="https://agentmods.dev/mcp/devantler-tech/agent-plugins/agentic-engineering-github-ghas-tools"><img src="https://agentmods.dev/badge/mcp/devantler-tech/agent-plugins/agentic-engineering-github-ghas-tools/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for github-ghas-tools

Your own site · 80×15
<a href="https://agentmods.dev/mcp/devantler-tech/agent-plugins/agentic-engineering-github-ghas-tools"><img src="https://agentmods.dev/badge/mcp/devantler-tech/agent-plugins/agentic-engineering-github-ghas-tools.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

github-ghas-tools scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

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.

plugins/agentic-engineering/.mcp.json · 11 lines

What it actually says

{
  "github-ghas-tools": {
    "type": "http",
    "url": "https://api.githubcopilot.com/mcp/readonly",
    "headers": {
      "X-MCP-Toolsets": "code_security,secret_protection,security_advisories,dependabot",
      "X-MCP-Readonly": "true"
    },
    "headersHelper": "bash \"${CLAUDE_PLUGIN_ROOT}/scripts/github-mcp-headers.sh\" \"${CLAUDE_PLUGIN_DATA}\""
  }
}
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. yesterday First seen · 11 lines scan A b7dc4ebe3c93

Subscribe to this mod's changes

github-ghas-tools is an MCP server published in the GitHub repository devantler-tech/agent-plugins (3 stars, last pushed yesterday), licensed Apache-2.0. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. 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 2026-11-05.

Related

github-ghas-tools compared with mcp servers from other repositories

github-ghas-tools next to 6 mcp servers from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
github-ghas-toolsdevantler-tech/agent-pluginsMCP server3yesterdayApache-2.0A—Claude Code
docs-langchainlangchain-ai/langchainMCP server149kyesterdayMITA—Claude Code, Codex, Cursor, Gemini CLI, OpenCode
component-explorermicrosoft/vscodeMCP server195kyesterdayMITA—Claude Code, Codex, Cursor, Gemini CLI, OpenCode
codex_message_boardopenai/codexMCP server133kyesterdayApache-2.0A—Claude Code, Codex, Cursor, Gemini CLI, OpenCode
playwright-testmicrosoft/playwrightMCP server99kyesterdayApache-2.0A—Claude Code, Codex, Cursor, Gemini CLI, OpenCode
reference-langchainlangchain-ai/langchainMCP server149kyesterdayMITA—Claude Code, Codex, Cursor, Gemini CLI, OpenCode
reamorluto/reaMCP server435kyesterdayMITA—Claude Code