AI agents call prismism_content to retrieve information from Prismism 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 retrieval of artifact content with no modification or deletion of data. It is categorized as Read rather than higher severity categories because the core function is fetching/retrieving content.
From the tool's definition Tool description states 'Fetch the raw content of an artifact' and 'Returns text for text formats... or base64 for binary formats'. The verb 'Fetch' indicates data retrieval.
Attacks that exploit this kind of access
Fetch the raw content of an artifact. Returns text for text formats (HTML, Markdown, text, JSON, CSV, SVG) or base64 for binary formats (PDF, images, video). Owner API key bypasses all gates. It is categorised as a Read tool in the Prismism MCP Server, which means it retrieves data without modifying state.
Register the Prismism MCP server in PolicyLayer and add a rule for prismism_content: 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 Prismism. Nothing to install.
prismism_content 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 prismism_content 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 prismism_content. 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.
prismism_content is provided by the Prismism MCP server (@prismism/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 →