Download and parse internal university proxies (PDFs, Images, URLs etc).
AI agents call resolve_proxy to retrieve information from Ekursy Mcp Py without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves and parses content from internal university proxy resources (documents, images, URLs). This is fundamentally a read/fetch operation with no side effects. Severity is medium because it accesses internal university resources that may contain sensitive academic materials, and the broad 'URLs etc' scope could allow fetching arbitrary internal endpoints.
From the tool's definition Download and parse internal university proxies (PDFs, Images, URLs etc)
Attacks that exploit this kind of access
Download and parse internal university proxies (PDFs, Images, URLs etc). It is categorised as a Read tool in the Ekursy Mcp Py MCP Server, which means it retrieves data without modifying state.
Register the Ekursy Mcp Py MCP server in PolicyLayer and add a rule for resolve_proxy: 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 Ekursy Mcp Py. Nothing to install.
resolve_proxy 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 resolve_proxy 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 resolve_proxy. 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.
resolve_proxy is provided by the Ekursy Mcp Py MCP server (markrz-0/ekursy-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →