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.
Tool Poisoning Isn't Code, It's Text: How MCP Tool Descriptions Smuggle Prompt Injection

Tool Poisoning Isn't Code, It's Text: How MCP Tool Descriptions Smuggle Prompt Injection

Comments
4 min read
The Wildcard Scope Problem: Why MCP Configs Default to admin:* Instead of Least Privilege

The Wildcard Scope Problem: Why MCP Configs Default to admin:* Instead of Least Privilege

Comments
3 min read
Every Compute Marketplace Today Settles Against the Wrong Thing

Every Compute Marketplace Today Settles Against the Wrong Thing

2
Comments
5 min read
Give Your AI Agent Its Own Inbox: A 5-Minute Setup with MCP

Give Your AI Agent Its Own Inbox: A 5-Minute Setup with MCP

1
Comments
2 min read
One Iceberg MCP Server, Seven Catalogs: What It Takes to Reach Each One

One Iceberg MCP Server, Seven Catalogs: What It Takes to Reach Each One

11
Comments
7 min read
Context Over MCP, Part III: Horses for Courses

Context Over MCP, Part III: Horses for Courses

1
Comments 5
4 min read
MCP C# Per-Request Client Capabilities: Read the Request, Not the Server

MCP C# Per-Request Client Capabilities: Read the Request, Not the Server

6
Comments 2
4 min read
Live API specs for coding agents

Live API specs for coding agents

1
Comments
2 min read
Building a Full-Stack AI Creative Studio with Next.js, WebGPU, and Node.js: The Ultimate Capstone Blueprint

Building a Full-Stack AI Creative Studio with Next.js, WebGPU, and Node.js: The Ultimate Capstone Blueprint

1
Comments
10 min read
Give Claude Code a Knowledge Base It Can Actually Edit

Give Claude Code a Knowledge Base It Can Actually Edit

Comments
6 min read
Teaching an LLM to pull MCP Resources and Prompts on demand (instead of drowning it in context)

Teaching an LLM to pull MCP Resources and Prompts on demand (instead of drowning it in context)

Comments
7 min read
MCP security: what to log when an AI agent calls tools, and what the log can prove

MCP security: what to log when an AI agent calls tools, and what the log can prove

1
Comments 2
7 min read
How to Update MCP Tools When the Underlying API Changes

How to Update MCP Tools When the Underlying API Changes

Comments
6 min read
I Replaced grep-Based Code Review with a Knowledge Graph + MCP. Here Are 3 Bugs Vector Search Missed.

I Replaced grep-Based Code Review with a Knowledge Graph + MCP. Here Are 3 Bugs Vector Search Missed.

Comments 1
7 min read
Building TrueSRE: Autonomous Multi-Agent Incident Remediation with TrueForge, FastMCP, and Daytona

Building TrueSRE: Autonomous Multi-Agent Incident Remediation with TrueForge, FastMCP, and Daytona

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