Get detailed metadata for all tokens from Velar SDK
AI agents call velar_get_tokens_metadata to retrieve information from Stacks AI MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves token metadata from the Velar SDK without creating, modifying, deleting, or executing any operations. It has no side effects and presents minimal security risk even if misused by an AI agent, as it only returns informational data about tokens.
From the tool's definition Tool name contains 'get' and description states 'Get detailed metadata for all tokens' — a retrieval operation with no modification or execution capability.
Attacks that exploit this kind of access
Get detailed metadata for all tokens from Velar SDK. It is categorised as a Read tool in the Stacks AI MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Stacks AI MCP Server MCP server in PolicyLayer and add a rule for velar_get_tokens_metadata: 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 Stacks AI MCP Server. Nothing to install.
velar_get_tokens_metadata 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 velar_get_tokens_metadata 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 velar_get_tokens_metadata. 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.
velar_get_tokens_metadata is provided by the Stacks AI MCP Server MCP server (stack-ai-mcp/stacks-mcp-server). 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 →