save_generated_test
Ingest the model-generated test variants for a ticket (submit them as variants: [{model, content}]). Tags each with its model, dedupes identical/near-identical assertions across variants (whitespace + variable names normalized; a fully-duplicate test block is dropped and noted), and returns the r...
This record as markdown: /tools/ai-featureboard-featureboard/save-generated-test.md
What save_generated_test does on FeatureBoard
AI agents use save_generated_test to create or update resources in FeatureBoard, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your FeatureBoard environment.
Why save_generated_test is rated Medium
This tool creates new test files and manifest metadata files in the test directory. While the description clarifies these are returned 'for you to write' (suggesting read-only output generation), the practical effect is creating or modifying test artifacts that form part of the project state. This is a reversible write operation (files can be edited or deleted), but not destructive or read-only.
From the tool's definition Tool description states it 'Ingest[s] the model-generated test variants', 'dedupes', and 'returns the runnable files to write (test/<ticket>.<model>.test.js) plus a queryable manifest'.
Attacks that exploit this kind of access
The rule that runs save_generated_test safely
PolicyLayer is an MCP gateway: it sits between your AI agents and FeatureBoard, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For save_generated_test, this is the rule to start with:
save_generated_test stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect FeatureBoard, apply this rule, and every save_generated_test call is checked against it from then on.
Questions about save_generated_test
Ingest the model-generated test variants for a ticket (submit them as variants: [{model, content}]). Tags each with its model, dedupes identical/near-identical assertions across variants (whitespace + variable names normalized; a fully-duplicate test block is dropped and noted), and returns the runnable files to write (test/<ticket>.<model>.test.js) plus a queryable manifest (test/<ticket>.variants.json). Read-only: it returns file contents for you to write. It is categorised as a Write tool in the FeatureBoard MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the FeatureBoard MCP server in PolicyLayer and add a rule for save_generated_test: 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 FeatureBoard. Nothing to install.
save_generated_test is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the save_generated_test 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 save_generated_test. 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.
save_generated_test is provided by the FeatureBoard MCP server (https://github.com/valentil/featureboard-mcp/releases/download/v0.7/featureboard.plugin). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on FeatureBoard, and thousands of servers like it.
This server
Across the catalogue