DEV Community

Model Context Protocol

MCP is an open protocol that standardizes how applications provide context to LLMs.

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
MCP server

MCP server

Comments
7 min read
Agentic AI patterns beyond the demo: tool-use, ReAct loops, multi-agent orchestration, and where MCP fits

Agentic AI patterns beyond the demo: tool-use, ReAct loops, multi-agent orchestration, and where MCP fits

Comments
9 min read
We asked Claude and Gemini to get around our AI agent's spending rules. Here's what happened in 80 runs.

We asked Claude and Gemini to get around our AI agent's spending rules. Here's what happened in 80 runs.

Comments
4 min read
We gave an AI assistant one paragraph and our backend. It built a working app in 16 minutes, on the second try

We gave an AI assistant one paragraph and our backend. It built a working app in 16 minutes, on the second try

Comments
4 min read
Triglav: orchestrating Claude Code and Codex agents for long-running work and layered review

Triglav: orchestrating Claude Code and Codex agents for long-running work and layered review

2
Comments 5
8 min read
I built a recipe board for AI agents with Bayesian scores and auto-rollback (stdlib Python + SQLite)

I built a recipe board for AI agents with Bayesian scores and auto-rollback (stdlib Python + SQLite)

1
Comments 2
6 min read
Query App Store and Google Play data from Claude with MCP

Query App Store and Google Play data from Claude with MCP

Comments
3 min read
A Private MCP Registry in 10 Minutes with agentregistry

A Private MCP Registry in 10 Minutes with agentregistry

Comments
10 min read
How We Built a Shared Markdown Board for AI Agents (and Made Checklists Tick Themselves)

How We Built a Shared Markdown Board for AI Agents (and Made Checklists Tick Themselves)

Comments
12 min read
Giving Hermes Agent or OpenClaw access to your Mac, without handing it the keys

Giving Hermes Agent or OpenClaw access to your Mac, without handing it the keys

Comments
3 min read
How to connect Apify to Claude (MCP) and give it YouTube transcripts in 5 minutes

How to connect Apify to Claude (MCP) and give it YouTube transcripts in 5 minutes

Comments
3 min read
DIY agent memory works until you have to maintain it

DIY agent memory works until you have to maintain it

Comments
3 min read
LLM testing of Anthropic’s Hacker-Opus test

LLM testing of Anthropic’s Hacker-Opus test

Comments
9 min read
What breaks when agents call your API: five lessons from serving 300 clients

What breaks when agents call your API: five lessons from serving 300 clients

Comments
2 min read
I built a self-hosted MCP control layer for enterprise systems — permissions, audit, human-in-the-loop

I built a self-hosted MCP control layer for enterprise systems — permissions, audit, human-in-the-loop

Comments
1 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.