Tool poisoning: how MCP tool descriptions hijack agents
Tool poisoning hides instructions inside MCP tool descriptions the agent reads as trusted context. The MCPTox benchmark recorded a 72.8% attack success rate.
Further reading
Articles about MCP Server
5 articles from the Wire blog, sorted newest first. Return to the MCP Server definition for context.
One job per tool: why adding wire_navigate cut agent calls 24%
We restructured Wire's MCP surface from 2 overloaded tools to 3 single-purpose ones. The counterintuitive result: adding a tool cut total calls 24%.
Why MCP failures are a context engineering problem
New research analyzed 3,282 MCP bug reports across GitHub. The patterns reveal a context delivery problem, not a protocol problem. Here's what it means.
Five Ways to Give AI Access to Your Data
From copy-paste to context platforms, five approaches to giving AI access to your data. Covers security trade-offs, cost, and practical recommendations.
How to Get an MCP Server Without Writing Code
Over 17,000 MCP servers exist but most are generic dev tools. Here's how to create a custom one for your own data without writing a single line of code.
Put context into practice
Create your first context container and connect it to your AI tools in minutes.
Create Your First Container