the discovery tool can create a test case on a given test target with a test case description or prompt. One can either start from the predefined url for that test case or provide a new entry point url.
AI agents use discovery to create or update resources in Octomind — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Octomind environment.
The tool creates a new test case resource on the platform, which is a reversible write operation. It does not execute tests, delete data, or involve financial transactions. Severity is medium because misuse could generate unwanted test cases on production targets.
From the tool's definition 'create a test case on a given test target with a test case description or prompt'
Documented attack patterns abuse exactly the kind of access discovery gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Octomind, and nothing reaches the server without passing your rules. This is the rule we recommend for discovery:
{
"version": "1",
"default": "deny",
"tools": {
"discovery": {
"limits": [
{
"counter": "discovery_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}discovery 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.
Free to start. No card required.
the discovery tool can create a test case on a given test target with a test case description or prompt. One can either start from the predefined url for that test case or provide a new entry point url. It is categorised as a Write tool in the Octomind MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Octomind MCP server in PolicyLayer and add a rule for discovery: 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 Octomind. Nothing to install.
discovery 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 discovery 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 discovery. 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.
discovery is provided by the Octomind MCP server (octomind-dev/octomind-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Octomind, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
21 Octomind tools catalogued and risk-classified — across an index of 43,000+ MCP servers.