get_supported_chains
AI agents call get_supported_chains to retrieve information from Blocknative without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to query system capabilities or configuration to determine supported blockchain networks. This is a non-destructive information retrieval operation with no ability to modify state or execute transactions. The empty description lowers confidence slightly, but the tool name is explicit enough to classify reliably as Read.
From the tool's definition Tool name 'get_supported_chains' indicates a query/list operation. Description is empty, but the name clearly suggests retrieving configuration or state information (which chains are supported). This is typical of a Read operation with no side effects.
Attacks that exploit this kind of access
get_supported_chains. It is categorised as a Read tool in the Blocknative MCP Server, which means it retrieves data without modifying state.
Register the Blocknative MCP server in PolicyLayer and add a rule for get_supported_chains: 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 Blocknative. Nothing to install.
get_supported_chains 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_supported_chains 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_supported_chains. 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_supported_chains is provided by the Blocknative MCP server (kukapay/blocknative-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 →