Текущее состояние блокчейна TON (номер блока, шард)
AI agents call get_blockchain_info to retrieve information from TON Data MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves blockchain metadata (block height and shard information) without modifying any state, executing code, or causing side effects. It is a straightforward read operation on immutable blockchain state, consistent with other query tools on the server like get_balance, get_token_price, and get_transactions.
From the tool's definition Tool description states 'Текущее состояние блокчейна TON (номер блока, шард)' (Current state of TON blockchain - block number, shard).
Attacks that exploit this kind of access
Текущее состояние блокчейна TON (номер блока, шард). It is categorised as a Read tool in the TON Data MCP Server MCP Server, which means it retrieves data without modifying state.
Register the TON Data MCP Server MCP server in PolicyLayer and add a rule for get_blockchain_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 TON Data MCP Server. Nothing to install.
get_blockchain_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_blockchain_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_blockchain_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_blockchain_info is provided by the TON Data MCP Server MCP server (m1mino/ton-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 →