Fetch visible text and image URLs from a public Axure share link.
AI agents call axure_fetch to retrieve information from Axure without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs read-only information retrieval from public Axure prototypes. It queries existing data without creating, modifying, deleting, or executing operations. The fact that the Axure link is public further mitigates risk. The worst-case misuse would be extracting content from unintended prototypes, which is a confidentiality concern but not a destructive or system-level risk.
From the tool's definition Tool description states it 'Fetch[es] visible text and image URLs from a public Axure share link' — a retrieval operation with no data modification or deletion.
Documented attack patterns abuse exactly the kind of access axure_fetch gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Axure, and nothing reaches the server without passing your rules. This is the rule we recommend for axure_fetch:
{
"version": "1",
"default": "deny",
"tools": {
"axure_fetch": {}
}
}axure_fetch is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Fetch visible text and image URLs from a public Axure share link. It is categorised as a Read tool in the Axure MCP Server, which means it retrieves data without modifying state.
Register the Axure MCP server in PolicyLayer and add a rule for axure_fetch: 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 Axure. Nothing to install.
axure_fetch 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 axure_fetch 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 axure_fetch. 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.
axure_fetch is provided by the Axure MCP server (six-ben/axure-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Axure, 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.
3 Axure tools catalogued and risk-classified — across an index of 43,000+ MCP servers.