Fetch and summarize an AgentBridge manifest from a URL. Use this first to understand what actions a site exposes.
AI agents call discover_manifest to retrieve information from AgentBridge MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only operation that retrieves and displays structured information (a manifest) from a URL to help understand available actions. It has no side effects, does not execute code or commands, and does not modify any data.
From the tool's definition Tool name and description indicate 'Fetch and summarize' — retrieval and inspection of metadata. No modification, deletion, or execution of external actions occurs; the tool only queries and reads a manifest document from a URL.
Attacks that exploit this kind of access
Fetch and summarize an AgentBridge manifest from a URL. Use this first to understand what actions a site exposes. It is categorised as a Read tool in the AgentBridge MCP Server MCP Server, which means it retrieves data without modifying state.
Register the AgentBridge MCP Server MCP server in PolicyLayer and add a rule for discover_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 AgentBridge MCP Server. Nothing to install.
discover_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 discover_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 discover_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.
discover_manifest is provided by the AgentBridge MCP Server MCP server (marmar9615-cloud/agentbridge-protocol). 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 →