Is GitHub official MCP server (Go) safe?

What GitHub official MCP server (Go) does

GitHub's MCP server connects AI tools to the GitHub platform so agents can read repositories and code, manage issues and pull requests, analyze code and automate workflows. It is published in the github/github-mcp-server repository and runs either as a remote server or locally, for example from the ghcr.io/github/github-mcp-server Docker image. It authenticates with OAuth or a GitHub personal access token and acts with that account's access. Before installing, give the token minimum scopes, as the README recommends, and use --toolsets to enable only the groups you need, or --read-only to offer read tools only.

Partially analyzed - Go code not checked for shell, network or file access

Notable — review in context (a capability is not a malicious indicator):

MCP tool surface detected

What to do: The Go code was not checked for shell, network or file access, so this result is incomplete. Review that code before installing.

GitHub official MCP server (Go) is an MCP server analyzed by SkillTotal's deterministic static scanner. The scan found no malicious indicators. Its Go code was not checked for shell, network or file access, so this result is partial. It can: mcp tools detected — capabilities are what the code can do, not a verdict on intent. Risk score 0/100 (low).

github-mcp-server

GitHub repository, read as a Go project · https://github.com/github/github-mcp-server

LOW

/ 100 risk score

Snapshot · scanned Nov 13, 2026 · github-mcp-server@0663b83 · engine 1.1.0 / ruleset 100

Get notified when this component changes

Change alerts aren't live yet. Leave your email and we'll let you know when they launch. We use it only for this and delete it on request.

Automated static-analysis result. It can contain false positives and false negatives, and is not a claim about the intent of GitHub official MCP server (Go)'s authors. Report a false positive.

Capabilities — what this component can do (not a risk score):

mcp tools detected

Behavioral traits

How this component maps to the CSA agentic threat model. Descriptive — it never affects the risk score.

Tool surface

Tool Usage

Findings (1)

CapabilityMCP tool surface detectednot scored · severity lowST-MCP-DETECTED

An MCP tool surface (manifest or tool definitions) was found.

agent-plugin/mcp.json:3

"mcpServers": {

agent-plugin/mcp.json:1

gemini-extension.json:4

"mcpServers": {

server.json:1

Why it matters: Just context — review which tools it offers and their permissions.

Fix: Review the declared MCP tools and their permissions.

Maintain GitHub official MCP server (Go)?

Check the next package before your agent installs it

The free Claude Code plugin scans each npm, PyPI or MCP package with this report's open-source engine before the install command runs. It runs on your machine and needs no account.

Set up the plugin Or scan pull requests in CI with the GitHub Action

Check your own component

Run the same evidence-backed scan on any MCP server, agent skill, or package.

Scan your own component

How we determine this: deterministic static analysis (regex + AST), evidence-anchored, no code execution. Methodology →