--- title: "What is the Model Context Protocol (MCP)? - actionlake" description: "The Model Context Protocol (MCP) is an open standard that lets AI apps discover and call tools on other systems. How it works, its versions and its limits." canonical: https://actionlake.com/glossary/mcp updated: 2026-10-24 --- Model Context Protocol # Model Context Protocol (MCP) The Model Context Protocol (MCP) is an open standard that lets an AI application connect to external systems and discover and call their tools, read their resources and use their prompts through one JSON-RPC message format. Updated 24 October 2026 Also called MCP, Model Context Protocol 4 sources checked **On this page** Connect an agent to every system you run. 100,000 calls free a month. No card. [Start free](https://actionlake.com/console?start=sandbox) ## What it is MCP defines how an AI application talks to the systems around it. The specification names three roles. The **host** is the AI application, such as Claude Code. The host creates one **client** per connection. Each client talks to one **server**, a program that offers capabilities. A server can offer three kinds of thing: **tools** (functions the model can call), **resources** (data the model or the person can read) and **prompts** (reusable templates). Messages are JSON-RPC 2.0. Two standard transports carry them: stdio, for a server running as a local process, and [Streamable HTTP](https://actionlake.com/glossary/streamable-http), for a [remote MCP server](https://actionlake.com/glossary/remote-mcp-server). The project describes MCP as a USB-C port for AI applications: one plug shape instead of a custom cable for every device. ## Why it matters Before MCP, every agent framework described tools its own way, so every integration was written again for every framework. With MCP, a system that publishes an [MCP server](https://actionlake.com/glossary/mcp-server) works with any [MCP client](https://actionlake.com/glossary/mcp-client) that speaks a compatible revision. The integration work moves from once per framework to once per system. ## How it works 1. The client connects and learns the server's capabilities and protocol version. 2. It asks for the list of tools (`tools/list`). Each [MCP tool](https://actionlake.com/glossary/mcp-tool) has a name, a description and a JSON Schema for its input. 3. The model picks a tool, and the client sends `tools/call` with arguments. 4. The server runs it and returns content, or a result marked `isError` that the model can read and correct. The protocol is versioned by date. The current revision is 2026-07-28, which made each request self-describing and removed protocol-level sessions. Servers and clients built on earlier revisions, such as 2025-11-25 and 2025-06-18, remain in use, and the specification describes how the two eras detect each other and fall back. ## Example A support agent connected to a ticket desk's MCP server lists that server's tools, finds one that creates a ticket, reads its schema, and calls it with a title and a priority. Nobody wrote code for that vendor inside the agent. ## Common pitfalls - **Assuming MCP adds security.** The specification says the protocol cannot enforce its own security principles; consent, access control and logging are left to implementers. - **Trusting tool descriptions.** The specification tells clients to treat tool annotations as untrusted unless they come from a trusted server. - **Connecting many servers at once.** Every server adds tool definitions to the model's context. See [tool overload](https://actionlake.com/glossary/tool-overload). ## How actionlake handles it The actionlake endpoint is one remote MCP server at `https://connect.actionlake.com/mcp`. It speaks Streamable HTTP on every current revision: 2026-07-28, with per-request metadata and `server/discover`, and the handshake revisions 2025-11-25, 2025-06-18 and 2025-03-26. Behind it sit 1,000+ connectors and 289,000+ actions (counted from our service files, 24 October 2026), reached through eight fixed tools. MCP is the road; actionlake adds what the protocol leaves to implementers: a [credential vault](https://actionlake.com/glossary/credential-vault), [per-key permissions](https://actionlake.com/glossary/ai-agent-permissions), [spending caps](https://actionlake.com/glossary/agent-spending-cap), [human approvals](https://actionlake.com/glossary/human-in-the-loop-approval) and a [hash-chained ledger](https://actionlake.com/glossary/tamper-evident-ledger). Read how the pieces fit on the [platform page](https://actionlake.com/platform), or connect a client with the [quickstart](https://actionlake.com/docs/quickstart). ## Questions **Is MCP only for Claude?** No. MCP is an open protocol, and the project's own introduction lists AI assistants and developer tools from several vendors that support it. Any client that speaks a compatible revision can use any MCP server. **Is MCP an API?** MCP is a protocol for describing and calling capabilities, not a vendor API. An MCP server usually wraps an existing API and presents its operations as tools a model can discover and call. **What is the difference between MCP and tool calling?** Tool calling is the model's ability to ask for a named function with arguments. MCP is the standard way an application finds those functions on other systems and invokes them, so tools written once work across clients. ## Related terms - [MCP server An MCP server is a program that offers tools, resources and prompts to AI applications over the Model Context Protocol, usually by wrapping one system's API, such as a ticket desk or an accounting ledger.](https://actionlake.com/glossary/mcp-server) - [MCP client An MCP client is the component inside an AI application that holds one connection to one MCP server, fetches that server's tool list and passes the model's tool calls to it.](https://actionlake.com/glossary/mcp-client) - [MCP tool An MCP tool is a named function that an MCP server offers to AI models, described by a name, a plain-language description and a JSON Schema for its input, and invoked with a tools/call request.](https://actionlake.com/glossary/mcp-tool) - [Streamable HTTP Streamable HTTP is the standard MCP transport for remote servers: the client sends each JSON-RPC message as an HTTP POST to one endpoint, and the server answers with a JSON object or a Server-Sent Events stream.](https://actionlake.com/glossary/streamable-http) - [MCP gateway An MCP gateway is a single MCP endpoint that sits between AI agents and many systems, holding the credentials and enforcing permissions, limits and logging on every tool call that passes through it.](https://actionlake.com/glossary/mcp-gateway) - [Tool calling Tool calling, also called function calling, is a language model's ability to answer with a structured request to run a named function with arguments, which the application executes before handing the result back to the model.](https://actionlake.com/glossary/tool-calling) ## Sources 1. [What is the Model Context Protocol (MCP)?](https://modelcontextprotocol.io/docs/getting-started/intro) Model Context Protocol · checked 22 October 2026 2. [Specification, revision 2025-11-25](https://modelcontextprotocol.io/specification/2025-11-25) Model Context Protocol · checked 22 October 2026 3. [Versioning](https://modelcontextprotocol.io/specification/versioning) Model Context Protocol · checked 22 October 2026 4. [Architecture overview](https://modelcontextprotocol.io/docs/learn/architecture) Model Context Protocol · checked 22 October 2026 [All 30 glossary terms](https://actionlake.com/glossary) ## Connect an agent. Start free. [Start free](https://actionlake.com/console?start=sandbox) [Read the quickstart](https://actionlake.com/docs/quickstart) 100,000 calls free every month. No card. Hard caps on every key. --- Source: https://actionlake.com/glossary/mcp More: https://actionlake.com/llms.txt