Low Risk

fetch_config

Retrieve the current bot configuration. Parameters: ctx (Context): MCP context object for logging and client access. Returns: str: Stringified JSON response with configuration data, or None if failed.

How to control fetch_config ↓

What fetch_config does on Freqtrade

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

Low Risk

Why fetch_config needs a policy

This tool retrieves configuration data without modifying it. However, severity is elevated to medium (rather than low) because cryptocurrency trading bot configurations may contain sensitive information such as API keys, exchange credentials, or trading parameters that could enable financial attacks if exposed to an untrusted agent.

From the tool's definition Tool name is 'fetch_config' and description states 'Retrieve the current bot configuration' with no modification or side effects. The verb 'Retrieve' and 'fetch' are consistent with Read category operations.

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

How to control fetch_config

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

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

fetch_config 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 Freqtrade — 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 fetch_config

What does the fetch_config tool do? +

Retrieve the current bot configuration. Parameters: ctx (Context): MCP context object for logging and client access. Returns: str: Stringified JSON response with configuration data, or None if failed. It is categorised as a Read tool in the Freqtrade MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on fetch_config? +

Register the Freqtrade MCP server in PolicyLayer and add a rule for fetch_config: 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 Freqtrade. Nothing to install.

What risk level is fetch_config? +

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

Can I rate-limit fetch_config? +

Yes. Add a rate_limit block to the fetch_config 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 fetch_config completely? +

Set action: deny in the PolicyLayer policy for fetch_config. 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 fetch_config? +

fetch_config is provided by the Freqtrade MCP server (kukapay/freqtrade-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Freqtrade tool call.

Start from Freqtrade, 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.

17 Freqtrade 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.