AI agents call get_manifest to retrieve information from Wasp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves structural metadata (a manifest/index) from a webpage. It is a read-only operation that queries and returns information about page structure without modifying data, executing code, or triggering external operations. The 'fetch' verb combined with the focus on 'structural index' confirms it is informational retrieval only, characteristic of the Read category.
From the tool's definition Tool name 'get_manifest' and description 'Fetch the WASP structural index for a webpage. Returns a manifest with the...' indicates data retrieval with no modification or execution capabilities.
Attacks that exploit this kind of access
Fetch the WASP structural index for a webpage. Returns a manifest with the. It is categorised as a Read tool in the Wasp MCP Server, which means it retrieves data without modifying state.
Register the Wasp MCP server in PolicyLayer and add a rule for get_manifest: 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 Wasp. Nothing to install.
get_manifest 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 get_manifest 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 get_manifest. 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.
get_manifest is provided by the Wasp MCP server (sfeeney1897/wasp-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 →