validate_checkpoint
Before you resume a crashed job, check that the checkpoint you are about to resume FROM is not the one the crash corrupted. Give it ls -la of the checkpoint directory, and optionally sha256sum -c output and any load errors. Returns which checkpoints are valid, which are corrupt, and the newest sa...
This record as markdown: /tools/denpex-mcp/validate-checkpoint.md
What validate_checkpoint does on Denpex
AI agents call validate_checkpoint to retrieve information from Denpex 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 |
|---|---|---|---|
loadErrors | string | — | Any error output from trying to load a checkpoint. |
failureType | string | — | The diagnosed failure type, if you have one — it sharpens the verdict. |
sha256Output | string | — | Output of `sha256sum -c MANIFEST.sha256`, if you keep a manifest. |
directoryListing | string | — | Output of `ls -la` (or `ls -la --time-style=full-iso`) on the checkpoint directory. |
Parameters from the server's own tool schema.
Why validate_checkpoint is rated Low
Even though validate_checkpoint only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
The rule that runs validate_checkpoint safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Denpex, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For validate_checkpoint, this is the rule to start with:
validate_checkpoint 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 Denpex, apply this rule, and every validate_checkpoint call is checked against it from then on.
Questions about validate_checkpoint
Before you resume a crashed job, check that the checkpoint you are about to resume FROM is not the one the crash corrupted. Give it ls -la of the checkpoint directory, and optionally sha256sum -c output and any load errors. Returns which checkpoints are valid, which are corrupt, and the newest safe resume point. Resuming from a mid-write checkpoint costs days and is the single most expensive avoidable mistake after a crash. It is categorised as a Read tool in the Denpex MCP Server, which means it retrieves data without modifying state.
validate_checkpoint accepts 4 parameters: loadErrors, failureType, sha256Output, directoryListing. The full parameter table on this page comes from the server's own tool schema.
Register the Denpex MCP server in PolicyLayer and add a rule for validate_checkpoint: 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 Denpex. Nothing to install.
validate_checkpoint 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 validate_checkpoint 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 validate_checkpoint. 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.
validate_checkpoint is provided by the Denpex MCP server (denpex-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Denpex, and thousands of servers like it.
This server
Across the catalogue