Prefab card: SOTA manifest and tool surface summary.
AI agents call observability_capabilities_card to retrieve information from Observability MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool generates or retrieves a summary card showing the state-of-the-art (SOTA) manifest and tool surface summary. It is a read-only operation that provides information about the observability system without executing queries, modifying data, or triggering external actions. The term 'prefab card' suggests it returns pre-built informational content rather than performing active monitoring or changes.
From the tool's definition Tool name 'observability_capabilities_card' and description 'Prefab card: SOTA manifest and tool surface summary' indicate this retrieves and displays a static or pre-generated summary/manifest of capabilities.
Attacks that exploit this kind of access
Prefab card: SOTA manifest and tool surface summary. It is categorised as a Read tool in the Observability MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Observability MCP Server MCP server in PolicyLayer and add a rule for observability_capabilities_card: 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 Observability MCP Server. Nothing to install.
observability_capabilities_card 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 observability_capabilities_card 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 observability_capabilities_card. 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.
observability_capabilities_card is provided by the Observability MCP Server MCP server (sandraschi/observability-mcp). 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 →