discover_vision_env
Discover available vision-capable AI SDKs and API keys in the current environment. Returns which providers can be used for screenshot analysis. Call this before analyze_screenshot to know what
This record as markdown: /tools/io-github-homenshum-nodebench/discover-vision-env.md
What discover_vision_env does on Nodebench
AI agents call discover_vision_env to retrieve information from Nodebench without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why discover_vision_env is rated Low
This tool queries the environment to enumerate available vision AI SDKs and API keys, then returns that information. It has no side effects, does not execute code or trigger external operations, and does not modify any state. This is a pure read operation that gathers environmental metadata, similar to a 'list' or 'detect' action. The low severity reflects minimal blast radius even if misused by an agent.
From the tool's definition Tool name 'discover_vision_env' and description 'Discover available vision-capable AI SDKs and API keys in the current environment.
Attacks that exploit this kind of access
The rule that runs discover_vision_env safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Nodebench, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For discover_vision_env, this is the rule to start with:
discover_vision_env 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 Nodebench, apply this rule, and every discover_vision_env call is checked against it from then on.
Questions about discover_vision_env
Discover available vision-capable AI SDKs and API keys in the current environment. Returns which providers can be used for screenshot analysis. Call this before analyze_screenshot to know what. It is categorised as a Read tool in the Nodebench MCP Server, which means it retrieves data without modifying state.
Register the Nodebench MCP server in PolicyLayer and add a rule for discover_vision_env: 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 Nodebench. Nothing to install.
discover_vision_env 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 discover_vision_env 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 discover_vision_env. 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.
discover_vision_env is provided by the Nodebench MCP server (nodebench-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Nodebench, and thousands of servers like it.
This server
Across the catalogue