debug
[Requires authentication] This tool needs OAuth. If it returns an authentication error, prompt the user to connect/authenticate this MCP server (OAuth), then retry. Look up production API request logs for your 1inch Business organization to troubleshoot integration issues. Results are always scop...
This record as markdown: /tools/com-1inch-business-mcp/debug.md
What debug does on 1inch MCP
AI agents call debug to retrieve information from 1inch MCP without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
limit | number | — | Max log lines (max 100) |
endTime | string | — | RFC3339 end of query window. Defaults to now when omitted. |
logLevel | string | — | Filter by log level: "info", "warn", or "error". Omit to return all levels. Only applies to time-window mode (ignored when requestId is set). |
requestId | string | — | Production x-request-id (or correlation id) to find logs for. When set, searches JSON logs for this value scoped to your organization. |
startTime | string | — | RFC3339 start of query window. With requestId, defaults to 24h before endTime. |
Parameters from the server's own tool schema.
Why debug is rated Low
The tool retrieves and queries existing API request logs — a read-only operation. No data is created, modified, or deleted. Severity is medium because production logs may contain sensitive request/response details, API keys, or business intelligence, making misuse potentially harmful even though the action itself is non-destructive.
From the tool's definition Look up production API request logs for your 1inch Business organization to troubleshoot integration issues. Results are always scoped to your authenticated organization.
Attacks that exploit this kind of access
The rule that runs debug safely
PolicyLayer is an MCP gateway: it sits between your AI agents and 1inch MCP, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For debug, this is the rule to start with:
debug is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect 1inch MCP, apply this rule, and every debug call is checked against it from then on.
Questions about debug
[Requires authentication] This tool needs OAuth. If it returns an authentication error, prompt the user to connect/authenticate this MCP server (OAuth), then retry. Look up production API request logs for your 1inch Business organization to troubleshoot integration issues. Results are always scoped to your authenticated organization. Two modes: 1) By request id: pass requestId (the x-request-id header returned on 1inch API responses). Optionally narrow startTime/endTime (defaults: last 24 hours ending now). 2) Logs in a time window: omit requestId and pass both startTime and endTime (RFC3339). Optionally set logLevel ("info", "warn", or "error") to filter by severity; omit to return all levels. Limits: each call covers at most a 24-hour window; how far back you can query depends on your plan's log retention. It is categorised as a Read tool in the 1inch MCP MCP Server, which means it retrieves data without modifying state.
debug accepts 5 parameters: limit, endTime, logLevel, requestId, startTime. The full parameter table on this page comes from the server's own tool schema.
Register the 1inch MCP server in PolicyLayer and add a rule for debug: 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 1inch MCP. Nothing to install.
debug 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 debug 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 debug. 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.
debug is provided by the 1inch MCP server (https://api.1inch.com/mcp/protocol). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on 1inch, and thousands of servers like it.
This server
Across the catalogue