Low Risk

kaspa_get_fee_recommendations

Get fee recommendations for different priority levels

How to control kaspa_get_fee_recommendations ↓

What kaspa_get_fee_recommendations does on Kaspa MCP Server

AI agents call kaspa_get_fee_recommendations to retrieve information from Kaspa MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Low Risk

Why kaspa_get_fee_recommendations needs a policy

This tool queries the Kaspa network for fee recommendation data. It performs a read-only operation that returns information to inform transaction decisions but does not execute transactions, move funds, or modify state. The blast radius of misuse is minimal—an attacker could only retrieve fee data, which is typically public information on blockchain networks.

From the tool's definition Tool name includes 'get' and description states 'Get fee recommendations' — retrieves data without side effects. No modification, execution, or financial transaction occurs; it only queries fee information.

Documented attack patterns abuse exactly the kind of access kaspa_get_fee_recommendations gives an agent:

How to control kaspa_get_fee_recommendations

PolicyLayer is an MCP gateway — it sits between your AI agents and Kaspa MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for kaspa_get_fee_recommendations:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "kaspa_get_fee_recommendations": {}
  }
}

kaspa_get_fee_recommendations is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

  1. Create a free account and register Kaspa MCP Server — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
CAP THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about kaspa_get_fee_recommendations

What does the kaspa_get_fee_recommendations tool do? +

Get fee recommendations for different priority levels. It is categorised as a Read tool in the Kaspa MCP Server MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on kaspa_get_fee_recommendations? +

Register the Kaspa MCP Server MCP server in PolicyLayer and add a rule for kaspa_get_fee_recommendations: 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 Kaspa MCP Server. Nothing to install.

What risk level is kaspa_get_fee_recommendations? +

kaspa_get_fee_recommendations is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit kaspa_get_fee_recommendations? +

Yes. Add a rate_limit block to the kaspa_get_fee_recommendations 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.

How do I block kaspa_get_fee_recommendations completely? +

Set action: deny in the PolicyLayer policy for kaspa_get_fee_recommendations. 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.

What MCP server provides kaspa_get_fee_recommendations? +

kaspa_get_fee_recommendations is provided by the Kaspa MCP Server MCP server (pichukov/kaspa-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Kaspa MCP Server tool call.

Start from Kaspa MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

Free to start. No card required.

15 Kaspa MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.