list_global_security_advisories

List global security advisories from GitHub.

SERVERGitHub SOURCEoci:ghcr.io/github/github-mcp-server:1.3.0

Low RISK CLASS

Category Read

Parameters 110 required

Recommended Allowedsee the rule below

Registry record Grade D, identity verified Pull the record →

This record as markdown: /tools/github/list-global-security-advisories.md

WHAT IT DOES

What list_global_security_advisories does on GitHub

AI agents call list_global_security_advisories 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
`cwes`	array	—	Filter by Common Weakness Enumeration IDs (e.g. ["79", "284", "22"]).
`type`	string	—	Advisory type.
`cveId`	string	—	Filter by CVE ID.
`ghsaId`	string	—	Filter by GitHub Security Advisory ID (format: GHSA-xxxx-xxxx-xxxx).
`affects`	string	—	Filter advisories by affected package or version (e.g. "package1,package2@1.0.0").
`updated`	string	—	Filter by update date or date range (ISO 8601 date or range).
`modified`	string	—	Filter by publish or update date or date range (ISO 8601 date or range).
`severity`	string	—	Filter by severity.
`ecosystem`	string	—	Filter by package ecosystem.
`published`	string	—	Filter by publish date or date range (ISO 8601 date or range).
`isWithdrawn`	boolean	—	Whether to only return withdrawn advisories.

Parameters from the server's own tool schema.

RISK

Why list_global_security_advisories is rated Low

This tool retrieves data from GitHub's public security advisory database. It performs a read-only query operation without modifying, deleting, or executing any code. The data returned is informational and already public. The blast radius of misuse is minimal — an agent querying this endpoint cannot cause harm beyond excessive API consumption.

From the tool's definition Tool name contains 'list', description states 'List global security advisories' — this is a query operation that retrieves publicly available security advisory information with no side effects.

Risk signalsHigh parameter count (11 properties)

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs list_global_security_advisories 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 list_global_security_advisories, this is the rule to start with:

list_global_security_advisories Allowed

list_global_security_advisories is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "list_global_security_advisories": {}
  }
}

ALLOW ONLY THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect GitHub, apply this rule, and every list_global_security_advisories call is checked against it from then on.

FAQ

Questions about list_global_security_advisories

What does the list_global_security_advisories tool do? +

List global security advisories from GitHub. It is categorised as a Read tool in the GitHub MCP Server, which means it retrieves data without modifying state.

What parameters does list_global_security_advisories accept? +

list_global_security_advisories accepts 11 parameters: cwes, type, cveId, ghsaId, affects, updated, modified, severity, ecosystem, published, isWithdrawn. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on list_global_security_advisories? +

Register the GitHub MCP server in PolicyLayer and add a rule for list_global_security_advisories: 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.

What risk level is list_global_security_advisories? +

list_global_security_advisories is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit list_global_security_advisories? +

Yes. Add a rate_limit block to the list_global_security_advisories 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.

How do I block list_global_security_advisories completely? +

Set action: deny in the PolicyLayer policy for list_global_security_advisories. 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.

What MCP server provides list_global_security_advisories? +

list_global_security_advisories 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.

KEEP EXPLORING

More on GitHub, and thousands of servers like it.

This server

All 86 GitHub tools →

Across the catalogue

aiva_list_affiliates on AIVA MCP Server →list_agents on 0rca Dojo MCP Server → The MCP Attack Database →

Guides

Roll out MCP under one policy →Data exfiltration →MCP token cost →