Preview a composition by URL
AI agents call preview-composition to retrieve information from EuConquisto Composer MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays a composition for viewing purposes only. There is no indication it modifies, deletes, executes code, or triggers external operations. Previewing content is fundamentally a read operation with minimal security risk if misused.
From the tool's definition Tool name 'preview-composition' and description 'Preview a composition by URL' indicate a retrieval/viewing operation with no modification capability.
Attacks that exploit this kind of access
Preview a composition by URL. It is categorised as a Read tool in the EuConquisto Composer MCP MCP Server, which means it retrieves data without modifying state.
Register the EuConquisto Composer MCP server in PolicyLayer and add a rule for preview-composition: 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 EuConquisto Composer MCP. Nothing to install.
preview-composition 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 preview-composition 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 preview-composition. 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.
preview-composition is provided by the EuConquisto Composer MCP server (rkm097git/euconquisto-composer-mcp-poc). 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 →