list_failed_requests
Inspect the dead-letter queue — write requests (POST/PATCH/DELETE) that exhausted all retries. Useful for forensics or manual replay. Backed by Redis if REDIS_URL is set, otherwise an in-memory ring buffer of up to 500 entries.
This record as markdown: /tools/digital-crew-technologies-max-mcp-server/list-failed-requests.md
What list_failed_requests does on Max MCP Server
AI agents call list_failed_requests to retrieve information from Max MCP Server without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why list_failed_requests is rated Low
This tool retrieves and displays information about failed requests from a dead-letter queue for diagnostic purposes. It has no side effects—it only reads from a queue (Redis or in-memory buffer) and returns data to the user. While the underlying failed requests may have been destructive operations (POST/PATCH/DELETE), this tool does not execute, replay, or modify anything; it merely inspects historical records.
From the tool's definition Tool description states 'Inspect the dead-letter queue' and 'Useful for forensics or manual replay.' The verb 'Inspect' indicates read-only access to historical failed requests stored in a queue.
Attacks that exploit this kind of access
The rule that runs list_failed_requests safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Max MCP Server, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For list_failed_requests, this is the rule to start with:
list_failed_requests 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 Max MCP Server, apply this rule, and every list_failed_requests call is checked against it from then on.
Questions about list_failed_requests
Inspect the dead-letter queue — write requests (POST/PATCH/DELETE) that exhausted all retries. Useful for forensics or manual replay. Backed by Redis if REDIS_URL is set, otherwise an in-memory ring buffer of up to 500 entries. It is categorised as a Read tool in the Max MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Max MCP Server MCP server in PolicyLayer and add a rule for list_failed_requests: 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 Max MCP Server. Nothing to install.
list_failed_requests 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 list_failed_requests 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 list_failed_requests. 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.
list_failed_requests is provided by the Max MCP Server MCP server (digital-crew-technologies/max-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Max MCP Server, and thousands of servers like it.
This server
Across the catalogue