Model Context Protocol (MCP)
ServiceModel Context Protocol (MCP) is an open specification that standardizes how AI agents communicate with external back-end services, databases, and tooling. It defines the message formats and server behaviors that let IDEs, CLIs, and autonomous agents reliably invoke tools, manage sessions, and enforce security policies.
Stories
Completed digest stories linked to this service.
-
Zep Graphiti shows a practical path to real-time agent memory—and a nudge toward...2026-06-20Zep’s Graphiti demonstrates real-time agent memory by combining knowledge graphs with vector-speed retrieval. ...
-
ARD lands: a common layer for agent tool discovery across enterprise silos2026-06-20Google, Microsoft, and others introduced ARD, a spec that lets AI agents discover enterprise tools via catalog...
-
Claude Code v2.1.181: in-session /config, reliability fixes, and safer writes2026-06-18Anthropic shipped Claude Code v2.1.181 with mid-session configuration and fixes for data-loss and flaky startu...
-
MCP turned scattered agent tools into a shared server with cleaner human gates2026-06-16A real-world team replaced per-agent tool definitions with an MCP server to standardize discovery, versioning,...
-
Claude Code grows up: plugins + marketplaces make it team-ready2026-06-15Claude Code’s plugin and marketplace model is solidifying into a team-ready platform for standardized skills, ...
-
MCP is making databases first-class tools for LLM agents2026-06-09Vendors are shipping official MCP servers for major databases, making agentic, schema-aware DB access viable w...
-
Expose your catalog as an MCP tool or assistants won’t see your products2026-06-08ChatGPT and other assistants increasingly shop via tools that query real product catalogs, not by scraping you...
-
Retrieval moves under the agent: MCP and Gemini shift RAG into a shared service2026-06-04Google and Anthropic are turning RAG retrieval into a shared agent-callable service, not an app-local pipeline...
-
MCP is moving into production fast — and Flowise’s 9.9 RCE shows the security co...2026-06-02A 9.9‑severity RCE in Flowise’s MCP stdio path spotlights how agent tooling can become an OS‑level attack surf...
-
Snowflake is buying Natoma to put guardrails on MCP-connected AI agents2026-05-29Snowflake is acquiring Natoma to bring identity, policy, and audit controls to MCP-connected AI agents across ...