Blog/Tools & MCP

Tools & MCP

Browse 29 articles in tools & mcp.

Tools & MCP Articles

29 articles · Page 1 of 3

Developer working at a laptop wiring up an MCP client and server, sticky notes mapping sampling, roots, and elicitation flows

Tools & MCP·12 min read

How to Use MCP Sampling, Roots, and Elicitation in CX Agents

Most MCP tutorials cover only server-side features: tools, resources, prompts. The three client capabilities (Sampling, Roots, Elicitation) unlock human-in-the-loop patterns that server tools alone can't. Here's how to use them.

Stateless MCP Servers Behind a Load Balancer With Task Handles Flowing Between Agent and Server

Tools & MCP·16 min read

How to Migrate Your MCP Server to Stateless Mode

The MCP 2026 release candidate makes stateless the recommended default. Your MCP server can now scale behind any load balancer without sticky routing. Here's how to migrate and use the new Tasks extension for async CX work.

Engineering team at a whiteboard mapping how AI agents call tools through a single governance layer

Tools & MCP·10 min read

MCP Without a Gateway Is a Production Liability

Raw MCP is great for prototyping. But production agents need audit trails, per-user identity, tool-level RBAC, and rate limiting, none of which the spec provides. Here's the gateway pattern that fills the gap.

Inline Return Confirmation Widget Rendered in an AI Chat Conversation

Tools & MCP·13 min read

How to Build an MCP Apps Widget for Your CX Agent

MCP Apps (SEP-1865) lets your MCP server deliver interactive forms, dashboards, and buttons inside AI chat conversations. Here's how to build one for CX agents.

Diagram of an event-driven MCP server receiving webhook notifications and pushing updates to an AI agent

Tools & MCP·19 min read

MCP Webhooks: Build Event-Driven Agents That React in Real Time

MCP's request-response model breaks when agents need to react to external events. Here's how to build event-driven agents today using stateless HTTP plus webhooks, and what the June 2026 spec will make native.

JSON code showing an MCP tool description with annotations marking quality issues in red

Tools & MCP·13 min read

How MCP Tool Descriptions Break Your Agent

New research shows 97% of MCP tool descriptions have quality issues that hurt agent accuracy. Here's what the smells look like, why they matter, and how to fix them.

A glowing terminal prompt floats above an AWS cloud diagram, agent tool calls fanning out to S3, DynamoDB, Bedrock, and Lambda nodes

Tools & MCP·12 min read read

AWS just gave your agent 15,000 cloud tools

The AWS MCP Server is now GA. One tool call reaches any of 15,000+ AWS APIs, sandboxed Python execution lets agents run multi-step operations, and Agent Skills replace heavyweight SOPs with on-demand guidance. Here's what changed and how to wire it.

An interactive booking confirmation card rendered inline inside an AI chat conversation

Tools & MCP·14 min read

MCP Apps: Build UIs That Render Inside AI Chat

MCP Apps let your tools return interactive HTML dashboards, forms, and visualizations that render inline in Claude, ChatGPT, and VS Code. Here's how to build them for CX agents.

A browser dashboard showing live agent tool calls and state updates streaming in real time

Tools & MCP·13 min read

AG-UI: The Protocol That Connects Agents to UIs

AG-UI is the open event-based protocol that streams AI agent state to any frontend in real time. Here's how it works, what events it defines, and how to wire it up in TypeScript.

Diagram showing an MCP server with OAuth 2.0 token validation, per-tenant tool scoping, and multi-tenant isolation layers

Tools & MCP·15 min read

MCP Auth in Production: Scopes, Tokens, and Tenant Isolation

Most MCP servers ship with no auth. Here's how to add OAuth 2.0 scopes, per-tenant tool sets, and client isolation before your MCP server becomes load-bearing production infrastructure.