ccxt_call

Call any existing method on the configured CCXT exchange. Mutating methods are subject to the trading gate.

SERVERCodex CCXT MCP SOURCEoci:ghcr.io/lucyfox199818-collab/ccxt-mcp:0.1.0

High RISK CLASS

Category Execute

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/io-github-lucyfox199818-collab-ccxt-mcp/ccxt-call.md

WHAT IT DOES

What ccxt_call does on Codex CCXT MCP

AI agents invoke ccxt_call to trigger actions in Codex CCXT MCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.

RISK

Why ccxt_call is rated High

This tool allows calling any method on a CCXT exchange object, which includes the full spectrum of operations: reads (fetch balances, prices), writes (create orders), destructive actions (cancel orders), and financial operations (place trades, withdraw funds).

From the tool's definition 'Call any existing method on the configured CCXT exchange. Mutating methods are subject to the trading gate.' — arbitrary method dispatch on a live exchange instance.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs ccxt_call safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Codex CCXT MCP, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For ccxt_call, this is the rule to start with:

ccxt_call Rate-limited

ccxt_call stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "ccxt_call": {
      "limits": [
        {
          "counter": "ccxt_call_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Codex CCXT MCP, apply this rule, and every ccxt_call call is checked against it from then on.

FAQ

Questions about ccxt_call

What does the ccxt_call tool do? +

Call any existing method on the configured CCXT exchange. Mutating methods are subject to the trading gate. It is categorised as a Execute tool in the Codex CCXT MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on ccxt_call? +

Register the Codex CCXT MCP server in PolicyLayer and add a rule for ccxt_call: 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 Codex CCXT MCP. Nothing to install.

What risk level is ccxt_call? +

ccxt_call is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit ccxt_call? +

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

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

ccxt_call is provided by the Codex CCXT MCP server (oci:ghcr.io/lucyfox199818-collab/ccxt-mcp:0.1.0). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Codex CCXT, and thousands of servers like it.

This server

All 113 Codex CCXT tools → High-risk tools on this server →

Across the catalogue

call_rpc on Frida Game Hacking MCP → All high-risk MCP tools → The MCP Attack Database →

Guides

Govern code and CI agents →Agent sandbox →Least privilege for MCP →