MCP Tool Discovery
MCP tool discovery is the process by which an AI agent queries an MCP server using the tools/list method to enumerate the tools the server exposes, their schemas, and descriptions.
Why this matters for AI agents
Agents use tool discovery to decide what actions are possible. Returning overly broad tool lists to agents increases the risk of tool misuse, prompt injection, and scope creep.
How AgntID relates
AgntID can filter the tools/list response, returning only the tools an agent is authorized to invoke for a given task—reducing the action surface before the agent reasons about it.
The static IAM gap
MCP tool discovery returns all tools the server exposes to an authenticated client. There is no per-agent or per-task filtering built into the protocol.
Related phrases
Related terms
Frequently asked questions
What is MCP tool discovery?
MCP tool discovery is the process by which an AI agent queries an MCP server using the tools/list method to enumerate the tools the server exposes, their schemas, and descriptions.
Why does an unrestricted tool list increase risk?
Agents use tool discovery to decide what actions are possible. Returning overly broad tool lists increases the risk of tool misuse, prompt injection, and scope creep.
How does AgntID filter tool discovery?
AgntID can filter the tools/list response, returning only the tools an agent is authorized to invoke for a given task. This prevents agents from seeing tools they should not use.
Secure every agent tool call at execution time.
AgntID gives infrastructure teams scoped, ephemeral access control for AI agents without replacing IAM, MCP servers, tools, or agent frameworks.