AI agents call get_token_info to retrieve information from Flow MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries token information using a contract address as input. It retrieves and returns data about a token without creating, modifying, deleting, or executing any operations. The read-only nature and limited scope (token metadata lookup) result in low severity with high confidence.
From the tool's definition Tool name 'get_token_info' and description 'Get token info on Flow EVM chain with token contract address' indicate data retrieval. The verb 'get' and absence of modification, deletion, or execution language confirm read-only operation.
Attacks that exploit this kind of access
Get token info on Flow EVM chain with token contract address. It is categorised as a Read tool in the Flow MCP MCP Server, which means it retrieves data without modifying state.
Register the Flow MCP server in PolicyLayer and add a rule for get_token_info: 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 Flow MCP. Nothing to install.
get_token_info 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_token_info 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_token_info. 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_token_info is provided by the Flow MCP server (outblock/flow-mcp-monorepo). 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 →