PulseAugur
EN
LIVE 11:25:37

Okta targets AI agent token costs with new MCP scoping tool

Okta has introduced a new tool called Model Context Protocol (MCP) scoping to address the rising costs associated with AI agents. This protocol aims to reduce token expenses by filtering the list of available tools before they are presented to the AI model. By applying permissions based on agent identity and associated user roles, Okta's system can significantly decrease the number of tools an agent considers, potentially cutting token costs by over 90% according to internal modeling. AI

IMPACT This development could help organizations manage and reduce the operational costs associated with deploying AI agents by optimizing token usage.

RANK_REASON Okta's announcement of a new tool to manage AI agent costs.

Read on Artificial Intelligence News →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

Okta targets AI agent token costs with new MCP scoping tool

COVERAGE [1]

  1. Artificial Intelligence News TIER_1 English(EN) · Ryan Daws ·

    Okta targets AI agent token costs with MCP scoping

    <p>Okta says identity-scoped Model Context Protocol (MCP) tool lists can reduce AI agent token costs. Each model call made by an AI agent can include schemas, names, descriptions and parameters for every tool exposed by a MCP server. Okta calls the resulting prompt overhead the “…