Gram by Speakeasy

Introducing Gram by Speakeasy. Gram is everything you need to power integrations for Agents and LLMs. Easily create, curate and host MCP servers for internal and external use. Build custom tools and remix toolsets across 1p and 3p APIs. Try building a MCP server now!

Model Context Protocol (MCP) Hub

Welcome to the Model Context Protocol Hub. MCP is an open standard that enables AI agents to securely connect to external tools, data sources, and services. Whether you’re using MCP servers or building your own, this hub will help you get the most out of the protocol.

Core concepts

Understanding MCP’s building blocks is essential for making informed decisions about how to use it effectively.

Tools

Functions that AI agents can call to perform actions

Resources

Data and context that agents can access

Prompts

Pre-built workflows that guide agent behavior

Transports

Sending and receiving data

Tool design

Building effective MCP servers requires thoughtful design. Learn how to create tools that agents can use efficiently.

Less is more

Why tool count matters and how to design focused servers

Dynamic tool discovery

Enable runtime tool registration for more efficient servers

Optimize OpenAPI for MCP

Prepare your API for MCP generation

Use cases

See how companies are using MCP in production and explore practical implementation patterns.

Real-world MCP usage

From Block's internal tooling to Solana blockchain analysis

Account management

Building account operations with MCP

E-commerce

Implementing shopping workflows

Task management

Creating project management tools

Getting started

New to MCP? Start with these resources to understand what it is and how to use it.

What is MCP?

A five-minute introduction to the Model Context Protocol

Quickstart Guide

Install your first MCP server and connect it to an AI agent

MCP for skeptics

A balanced view of MCP's trade-offs and limitations

Last updated on October 10, 2025