Login Get a Demo
01 Glossary · AI security

What Is the Model Context Protocol (MCP)?

The open standard that connects AI applications to tools and data: hosts, clients, servers, the current specification and its security implications.

The short answer

What is the Model Context Protocol (MCP)?

Last updated
Read time
5 min read
From
Cranium AI
Also called
MCP
Share on LinkedIn

The Model Context Protocol (MCP) is an open-source standard for connecting AI applications to external systems such as data sources, tools and workflows.

An AI application, the host, runs one client per MCP server, and the server offers tools, resources and prompts over JSON‑RPC 2.0. MCP standardizes the connection and leaves enforcement of consent and safety to implementers.

Key takeaways
  • The current specification revision is 2026‑07‑28. The previous revision was 2025‑11‑25.
  • Servers expose three primitives: tools the model can execute, resources for context, and prompts as templates.
  • The specification says tools represent arbitrary code execution and must be treated with appropriate caution.
  • MCP is governed as Model Context Protocol a Series of LF Projects, LLC, with changes proposed through SEPs.
02 Architecture

How does MCP work?

01

Host

The AI application that coordinates and manages one or more MCP clients, for example a coding assistant or a chat application.

MCP architecture overview
02

Client

A component inside the host that maintains a connection to one MCP server and obtains context from it for the host to use.

03

Server

A program that provides context to clients. It can run locally over the stdio transport, or remotely over Streamable HTTP, where it typically serves many clients.

04

Primitives

Servers expose tools (executable functions), resources (data for context) and prompts (reusable templates). Clients can offer elicitation, which lets a server request input from the user.

03 What changed

What changed in the 2026 revision?

Revision 2026‑07‑28 changed how every request works, which matters to anyone logging or filtering MCP traffic.

01

Stateless requests

The initialize handshake and protocol-level sessions are gone. Every request now carries its protocol version and the client’s capabilities.

Key changes in this revision
02

Mandatory discovery

Servers must implement server/discover to advertise their supported protocol versions, capabilities and identity.

03

Deprecations

Roots, Sampling and Logging are deprecated. So is OAuth Dynamic Client Registration, in favor of Client ID Metadata Documents.

04 Security

What are the security implications of MCP?

01

Tool descriptions are untrusted

The specification says descriptions of tool behavior should be considered untrusted unless they come from a trusted server. The model reads those descriptions when choosing what to call.

MCP specification
02

Consent is up to implementers

Hosts must obtain explicit user consent before invoking any tool, and the specification acknowledges that MCP itself cannot enforce its security principles at the protocol level.

03

Local servers run code

A local MCP server is a program executed on the user’s machine. MCP’s security guidance warns of malicious startup commands and recommends sandboxing and showing the exact command before it runs.

MCP security best practices
04

Tokens and scopes

The guidance forbids token passthrough, where a server accepts tokens that were not issued for it, and recommends minimal scopes that are elevated only when needed.

05 Keep going

Related reading.

06 Questions

Frequently asked questions.

Straight answers, kept current. Last updated .

Ask us anything →
Who maintains the Model Context Protocol?

An open-source project with its own governance. Its governance page states that the project is established as Model Context Protocol a Series of LF Projects, LLC. Anthropic donated MCP in December 2025 to the Agentic AI Foundation, a directed fund under the Linux Foundation. Lead Maintainers and Core Maintainers steer the specification, and changes are proposed as Specification Enhancement Proposals (SEPs).

Is MCP secure by default?

No, and the specification says as much. It states that MCP enables arbitrary data access and code execution paths, and that the protocol cannot enforce its security principles itself. User consent, access control, authorization and data protection are the job of the hosts, clients and servers that implement it. That is why an inventory of the MCP servers in use is the first control to put in place.

What is the difference between an MCP server and an API?

An API is an interface a developer codes against. An MCP server wraps capabilities, often existing APIs, in a standard form an AI application can discover: it lists its tools, resources and prompts, describes them in text and schemas, and executes the tool calls the model requests. The security-relevant difference is the caller: a model choosing actions from descriptions, not a developer writing fixed calls.

Does Cranium AI secure MCP?

In part, and it is worth being exact. Cranium AgentSensor inventories agent frameworks, MCP servers and tools from source code into the AI‑BOM, so you know which servers your applications reference. The Tool Inspector shows the tool calls an agent made. Cranium AI does not run an MCP gateway or proxy and does not authorize or block tool calls at runtime. That control belongs at the host or the tool layer.

07 See it for yourself

From the definition
to the evidence.

See how Cranium AI discovers, observes, governs, secures and proves every AI model, agent and vendor in your enterprise.