testkit_last_failure
Read the most recent failed run from local history. Returns the spec name, the failing step, the screenshot path, and the error — exactly what an AI agent needs to propose a patch.
This record as markdown: /tools/io-github-kivanccakmak-yaver/testkit-last-failure.md
What testkit_last_failure does on Yaver
AI agents call testkit_last_failure to retrieve information from Yaver 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 |
|---|---|---|---|
root | string | — | Spec root (default: yaver-tests) |
Parameters from the server's own tool schema.
Why testkit_last_failure is rated Low
This tool only retrieves historical test failure data (spec name, failing step, screenshot path, error message) from local storage. It has no side effects, does not modify any data, and does not execute any code. Pure read operation with low blast radius.
From the tool's definition Read the most recent failed run from local history. Returns the spec name, the failing step, the screenshot path, and the error
Attacks that exploit this kind of access
The rule that runs testkit_last_failure safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Yaver, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For testkit_last_failure, this is the rule to start with:
testkit_last_failure 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 Yaver, apply this rule, and every testkit_last_failure call is checked against it from then on.
Questions about testkit_last_failure
Read the most recent failed run from local history. Returns the spec name, the failing step, the screenshot path, and the error — exactly what an AI agent needs to propose a patch. It is categorised as a Read tool in the Yaver MCP Server, which means it retrieves data without modifying state.
testkit_last_failure accepts 1 parameter: root. The full parameter table on this page comes from the server's own tool schema.
Register the Yaver MCP server in PolicyLayer and add a rule for testkit_last_failure: 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 Yaver. Nothing to install.
testkit_last_failure 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 testkit_last_failure 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 testkit_last_failure. 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.
testkit_last_failure is provided by the Yaver MCP server (yaver-cli). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Yaver, and thousands of servers like it.
This server
Across the catalogue