recon.continue_multiview_search
Queue or resume isolated render-and-compare evaluation for a planned search.
This record as markdown: /tools/visionmcp/recon.continue-multiview-search.md
What recon.continue_multiview_search does on Visionmcp
AI agents invoke recon.continue_multiview_search to trigger actions in Visionmcp. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.
Why recon.continue_multiview_search is rated High
The tool queues or resumes an active evaluation process (render-and-compare), which involves triggering external operations (rendering and comparing views). This is an execution action rather than a simple read, as it initiates computational work. The 'isolated' qualifier and 'planned search' context suggest a controlled process, limiting blast radius to medium.
From the tool's definition Queue or resume isolated render-and-compare evaluation for a planned search
Attacks that exploit this kind of access
The rule that runs recon.continue_multiview_search 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 recon.continue_multiview_search, this is the rule to start with:
recon.continue_multiview_search stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. 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 recon.continue_multiview_search call is checked against it from then on.
Questions about recon.continue_multiview_search
Queue or resume isolated render-and-compare evaluation for a planned search. It is categorised as a Execute tool in the Visionmcp MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Vision MCP server in PolicyLayer and add a rule for recon.continue_multiview_search: 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.
recon.continue_multiview_search is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the recon.continue_multiview_search 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 recon.continue_multiview_search. 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.
recon.continue_multiview_search 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.
Across the catalogue