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.
You Shall Not Pass — Allow/Deny Policies for MCP Tools Are Now in Heimdall

You Shall Not Pass — Allow/Deny Policies for MCP Tools Are Now in Heimdall

2
Comments 1
3 min read
Two Tiny MCP Servers That Reduced Prompt Waste This Week

Two Tiny MCP Servers That Reduced Prompt Waste This Week

Comments
3 min read
Compass v1.1.0 · we shipped a memory plugin that catches its own consumption drift

Compass v1.1.0 · we shipped a memory plugin that catches its own consumption drift

1
Comments
5 min read
Treenix. Typed runtime for humans and agents

Treenix. Typed runtime for humans and agents

1
Comments
1 min read
Determinism as a feature: when to let your agent call a math API instead of reasoning

Determinism as a feature: when to let your agent call a math API instead of reasoning

1
Comments 6
2 min read
Rails are not settlement: what the 92% x402 crater tells us about the agent economy

Rails are not settlement: what the 92% x402 crater tells us about the agent economy

3
Comments
5 min read
Anthropic described the right way to build MCP servers. Gut feeling confirmed.

Anthropic described the right way to build MCP servers. Gut feeling confirmed.

2
Comments 2
2 min read
We Built Deterministic JSON Ops for AI Agents — The Problem It Solves

We Built Deterministic JSON Ops for AI Agents — The Problem It Solves

2
Comments
2 min read
I built a tool that gives Claude Code eyes on videos — extract code from any tutorial

I built a tool that gives Claude Code eyes on videos — extract code from any tutorial

Comments
1 min read
Chivox MCP — Speech assessment for AI language agents

Chivox MCP — Speech assessment for AI language agents

4
Comments 3
2 min read
I'm a marketer, not an engineer. I shipped open-source AI infrastructure in 3 months by directing AI coding agents.

I'm a marketer, not an engineer. I shipped open-source AI infrastructure in 3 months by directing AI coding agents.

1
Comments
3 min read
How to Audit Your AI Agent Skills for Credential Exposure and Malicious Instructions

How to Audit Your AI Agent Skills for Credential Exposure and Malicious Instructions

1
Comments 1
3 min read
How I let AI agents pay for APIs per call (the HTTP 402 path)

How I let AI agents pay for APIs per call (the HTTP 402 path)

1
Comments 1
4 min read
MCP Gives AI Agents Hands. Safety Teaches Them Where Not to Touch

MCP Gives AI Agents Hands. Safety Teaches Them Where Not to Touch

1
Comments 1
8 min read
The Agentic Trust Gap: We're Building the Engine Without the Brakes

The Agentic Trust Gap: We're Building the Engine Without the Brakes

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