vision.establish_correspondence
Match target and candidate regions from semantics, text, layout, IDs, and visual features.
This record as markdown: /tools/visionmcp/vision.establish-correspondence.md
What vision.establish_correspondence does on Visionmcp
AI agents call vision.establish_correspondence to retrieve information from Visionmcp without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why vision.establish_correspondence is rated Low
This tool reads and analyzes visual regions to establish correspondences but does not create, modify, delete, or execute operations. It is a pure analysis/comparison function that retrieves information about visual elements, fitting the Read category. The severity is low because misuse would only result in incorrect matching analysis without side effects.
From the tool's definition Tool performs matching and comparison of visual regions using semantic, textual, layout, and visual features.
Attacks that exploit this kind of access
The rule that runs vision.establish_correspondence safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Visionmcp, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For vision.establish_correspondence, this is the rule to start with:
vision.establish_correspondence 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 Visionmcp, apply this rule, and every vision.establish_correspondence call is checked against it from then on.
Questions about vision.establish_correspondence
Match target and candidate regions from semantics, text, layout, IDs, and visual features. It is categorised as a Read tool in the Visionmcp MCP Server, which means it retrieves data without modifying state.
Register the Vision MCP server in PolicyLayer and add a rule for vision.establish_correspondence: 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 Visionmcp. Nothing to install.
vision.establish_correspondence 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 vision.establish_correspondence 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 vision.establish_correspondence. 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.
vision.establish_correspondence is provided by the Vision MCP server (joshuahickscorp/visionmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Vision, and thousands of servers like it.
This server
Across the catalogue