get_tag
AI agents call get_tag to retrieve information from GitHub MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The 'get_' prefix strongly indicates a retrieval operation with no side effects. Tags are metadata/references in Git repositories, and fetching them is a non-destructive read operation. While confidence is slightly reduced due to empty description, the naming pattern and context make it clear this is a query tool. Classified as Read with low severity since unauthorized tag retrieval poses minimal risk.
From the tool's definition Tool name 'get_tag' indicates retrieval of tag information from a repository. The naming convention aligns with read-only operations typical in GitHub API (get_* prefix). No description provided, but sibling tools on the server (create_*, add_*, cancel_*, etc.
Attacks that exploit this kind of access
get_tag. It is categorised as a Read tool in the GitHub MCP Server MCP Server, which means it retrieves data without modifying state.
Register the GitHub MCP Server MCP server in PolicyLayer and add a rule for get_tag: 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 MCP Server. Nothing to install.
get_tag is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_tag 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.
Set action: deny in the PolicyLayer policy for get_tag. 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.
get_tag is provided by the GitHub MCP Server MCP server (software-engineer-mj/github-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →