liveBook · Manning

MCP server

As explained in Designing AI Systems

An MCP server is a server that exposes tools through the Model Context Protocol for discovery and invocation by compatible clients.

An MCP server is a lightweight program that wraps an external system—such as a database, API, or file system—and exposes its capabilities through the Model Context Protocol. “Server” describes the role of serving capabilities to AI applications, not a required deployment location: it may run locally as a subprocess or remotely as a service. section 6.4.2

Understand an MCP server through its protocol boundaries and platform responsibilities:

  • Exposes tools as executable functions with JSON Schema inputs and outputs; clients discover them with tools/list and invoke them with tools/call. section 6.4.3
  • May also expose read-only resources, such as files or database records, and reusable prompts for structured model interactions. section 6.4.3
  • Connects to an MCP client inside an AI host; each connected server has a dedicated client connection. section 6.4.2
  • Lets a platform Tool Service register external tools, centralize credentials, enforce policies, track invocations, and share one connection across applications. section 6.4.5

Registering a GitHub MCP server

A platform can register an external server at an internal URL under the namespace devtools.github, resolve credentials through a credential reference, require confirmation, and enforce a rate limit. Discovery then returns names such as devtools.github.create_issue and devtools.github.list_repos.

Figure 6.8 The integration cost progression. Without a standard protocol (left), each AI application needs custom code for each external tool, creating a multiplicative and unscalable N × M cost. With the Model Context Protocol (center), the ecosystem standardizes, reducing the integration burden to an additive N + M requirement. By introducing a platform architecture (right), the Tool Service acts as the single, universal MCP client for all applications. This abstracts the complexity away from application developers entirely, reducing the organization's integration cost to just M: one connection per tool, securely shared across every application.

Compare direct application integrations with MCP standardization and centralized platform multiplexing: integration cost progresses from N×M to N+M to M. section 6.4.1

How Designing AI Systems covers it

How deep it goes
Explains roles, primitives, transport integration, credentials, policies, tracking, and deployment, but not server implementation code.
Examples
Uses GitHub, Postgres, databases, APIs, file systems, codebases, issue creation, repository listing, and platform registration.
What it assumes
Assumes familiarity with AI hosts, clients, external tools, and platform services while defining MCP roles and primitives explicitly.
What you can do after
Operate/configure external MCP integrations through namespaces, credential references, policies, rate limits, discovery, and routed execution.
How it connects
Connects hosts, MCP clients, tools, resources, prompts, Tool Service, credential stores, policies, and platform registries.

Also explained in

Compare how 18 books explain MCP server →

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Designing AI Systems. The section links point to the parts of the book it draws on.