Tag
MCP
AI Engineering Practice
Auditing MCP Server Permissions Before You Wire Them Into an Agent
Connecting a new tool server to an agent is a permissions decision, not just an integration step. Here's a practical checklist for scoping what an MCP server can actually do before it goes live.
Developer Tools
Tool Overload: When More Functions Make an Agent Worse, Not Better
Every tool you add competes for the same attention budget the model uses to pick the right one — past a certain roster size, that competition starts costing you accuracy.
MCP & Tool-Use
Designing Tool Error Messages an Agent Can Actually Act On
A tool error is the next input to the model. Here is what Anthropic recommends for actionable errors, plus a small schema that makes failures decidable.
MCP & Tool-Use
Model Context Protocol (MCP): A Universal Adapter for AI Tool Integration
MCP is an open standard for connecting AI applications to tools and data. Here are the roles, the features, and the security rules in the current specification.