AI agents call get_tag_registry to retrieve information from Codecks without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves tag definitions and mappings, which is a read-only query of reference data. No side effects, no code execution, no data modification. Low severity because tag taxonomy is metadata that an AI agent would need to understand the system but cannot directly cause harm by reading it.
From the tool's definition Tool description states 'Get the local tag taxonomy' — a retrieval operation with 'No auth needed', indicating it queries configuration data without modifying or executing anything.
Attacks that exploit this kind of access
Get the local tag taxonomy (definitions, hero tags, lane-tag mappings). No auth needed. It is categorised as a Read tool in the Codecks MCP Server, which means it retrieves data without modifying state.
Register the Codecks MCP server in PolicyLayer and add a rule for get_tag_registry: 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 Codecks. Nothing to install.
get_tag_registry 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_registry 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_registry. 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_registry is provided by the Codecks MCP server (rangogamedev/codecks-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 →