Skip to content
AI & Automation9 min read

Model Context Protocol (MCP): A Complete Guide for Developers and Businesses

What the Model Context Protocol is and how it works in 2026: hosts, clients and servers, tools, resources and prompts, transports, the stateless 2026-07-28 specification, authorization and practical use cases.

01

Quick answer

The Model Context Protocol (MCP) is an open standard for connecting AI applications to tools and data. An MCP server exposes tools (functions the model can call), resources (readable data) and prompts (templates) from a system such as a CRM or database. AI applications (hosts) connect through MCP clients over stdio for local servers or Streamable HTTP for remote ones, discover what a server offers and call it. The 2026-07-28 specification made MCP stateless, and remote servers use OAuth 2.1-based authorization. MCP complements APIs rather than replacing them.

02

Where This Fits

Building a server is covered in how to build an MCP server, positioning against APIs in MCP vs API and security in MCP security. For agents talking to other agents, see agent-to-agent communication. Agent design generally is in AI agent development.

03

Why MCP Exists

Before MCP, every AI application integrated every tool its own way: one connector for each pair of app and system. MCP turns that many-to-many problem into a standard interface. A company can expose its order system once as an MCP server, and any compatible assistant, IDE or agent framework can use it, with consistent discovery, schemas and authorization.

Anthropic introduced MCP in November 2024; in December 2025 it was contributed to the Agentic AI Foundation under the Linux Foundation, with support from several major AI and cloud companies.

04

MCP Architecture: Hosts, Clients and Servers

RoleWhat it isExample
HostThe AI application the user works inA chat assistant, IDE or agent platform
ClientThe connector inside the host, one per serverHandles protocol messages and auth
ServerA program exposing capabilities from a systemAn MCP server for your CRM or file store
05

Server Capabilities: Tools, Resources and Prompts

Tools are functions with a name, description and JSON Schema for inputs (and optionally outputs). The model decides when to call them; the host typically asks the user to approve. Resources are data identified by URIs, such as files or records, which the application can read and include as context. Prompts are templates a user can choose, such as 'summarize this ticket'. Servers can also declare optional extensions, a formal mechanism added in the 2026-07-28 revision; long-running work uses the official tasks extension.

06

What Changed in the 2026-07-28 Specification

The 2026-07-28 revision is the largest change since launch, so older tutorials may be out of date:

  • Stateless core: the initialize handshake and protocol-level sessions (the Mcp-Session-Id header) are removed; each request carries its protocol version and client capabilities in metadata
  • server/discover: servers must implement it to advertise versions, capabilities and identity
  • Multi Round-Trip Requests: servers that need more input return an input_required result instead of sending requests to the client
  • subscriptions/listen: one opt-in stream for change notifications replaces older subscription mechanisms
  • Deprecations: Roots, Sampling and Logging features, the HTTP+SSE transport, and Dynamic Client Registration in favour of Client ID Metadata Documents
  • Caching hints: list and read results carry ttlMs and cacheScope fields
07

Transports

stdio: the host launches the server as a local process and exchanges messages over standard input and output. Simple and private, suited to developer tools and desktop assistants. Servers must not write logs to stdout, which would corrupt messages.

Streamable HTTP: the server runs as a web service and clients send requests over HTTP, with streamed responses where needed. Suited to remote, shared and SaaS-hosted servers, and the transport where authorization applies.

Want your product or internal systems available to AI assistants?

ZSpace Labs designs and builds MCP servers with narrow tools, proper authorization and the testing needed for production use.

Start a Project
08

Authorization and Security

Remote MCP servers use OAuth 2.1-based authorization. The server publishes protected resource metadata so clients can discover its authorization server; clients use the authorization code flow with PKCE and request audience-bound tokens; the server must validate that tokens were issued for it and must not pass the client's token through to upstream APIs. Beyond authorization, the main risks are over-broad tools, untrusted servers and prompt injection through tool results. See MCP security.

09

Practical Use Cases

MCP Apps, the official UI extension, lets tools return interactive interfaces inside supporting assistants; see AI assistant app UX. In commerce, MCP is a transport for protocols such as UCP; see ACP vs UCP vs MCP.

Use caseWhat the MCP server exposes
Internal assistant over company systemsRead tools for CRM, tickets and documents
Developer toolingRepository, CI, issue tracker and database access
SaaS product integrationYour product's actions for customers' AI assistants
Operations agentsNarrow write tools such as creating tickets or updating orders
Data analysisQuery tools over a warehouse with row limits and read-only roles
10

MCP vs Other Standards

MCP connects an AI application to tools and data. It is complementary to A2A, which connects agents to other agents, and to ordinary APIs, which MCP servers usually call underneath. Model providers' function-calling features define how a model requests a tool call; MCP standardizes how those tools are discovered and reached across applications.

11

Advantages and Limitations

AdvantagesLimitations
Build once, use from many AI applicationsSpecification is evolving quickly; implementations lag
Standard discovery and schemasClient support for features varies
Defined authorization model for remote serversSecurity depends on careful implementation
Open governance under the Linux FoundationNot a substitute for well-designed APIs
12

How to Adopt MCP Step by Step

  • 1. Pick one system and a handful of high-value tools
  • 2. Decide local (stdio) or remote (Streamable HTTP) based on who will use it
  • 3. Design narrow tools over your existing APIs, read-only first
  • 4. Implement with an official SDK targeting the current specification
  • 5. Add authorization for remote servers and least-privilege access
  • 6. Test with the MCP Inspector and real clients
  • 7. Monitor usage and extend tools based on evidence
13

MCP in the Enterprise: Governance

As MCP use spreads, organizations need the same governance they apply to other integrations. Maintain a catalogue of approved MCP servers (internal and third-party) with owners, data access and permitted clients; block unapproved servers on managed devices; require security review for servers that touch sensitive data or perform writes; and route remote server access through identity providers with audit logs. Treat MCP servers as production services with versioning, monitoring and incident response.

14

Common MCP Server Patterns

PatternDescriptionWatch for
API adapterWraps an existing REST or GraphQL API in task-level toolsKeep business rules in the API
Data accessRead-only queries over a database or warehouseRow limits, read-only roles, no free-form SQL for untrusted users
Document sourceExposes files or knowledge as resourcesPermissions per document
Workflow triggerStarts approved automationsApprovals and idempotency
Developer toolingRepositories, CI, issue trackersLocal execution risk, token scopes
15

How MCP Fits With Function Calling

Model providers' function calling and MCP operate at different levels. Function calling is the model-side mechanism: the model returns a structured request to call a tool, and the application executes it. MCP is the integration-side standard: how the application discovers available tools from servers, how it calls them and how authorization works for remote servers. An AI host typically lists MCP tools to the model through function calling, receives the model's tool call and routes it to the right MCP server. Several model platforms can also connect to remote MCP servers directly from their APIs.

16

Planning an MCP Rollout

  • Inventory: which systems should AI clients reach, and for whom
  • Prioritize: start with read-only, high-value tools
  • Design: task-level tools over existing APIs, with clear descriptions
  • Secure: OAuth-based authorization for remote servers, least-privilege scopes, approvals for writes
  • Govern: catalogue approved servers, owners and data classes
  • Operate: logging, tracing, versioning and support
  • Track the specification: plan upgrades when new revisions ship
17

Worked Example

An illustrative scenario, not a client case: a B2B software company wants customers' AI assistants to check account status and open support tickets. It builds a remote MCP server over its existing public API with three tools (get account summary, list open tickets, create ticket), OAuth-based authorization tied to customer accounts and per-tool scopes, and logs every call. Customers connect from their preferred assistant without a custom integration for each.

18

Common Mistakes

  • Following pre-2026 tutorials that rely on the removed initialize handshake or sessions
  • Exposing a generic 'run any query' tool
  • Passing user tokens through to upstream APIs
  • Connecting unvetted third-party servers to sensitive data
  • Writing logs to stdout in stdio servers

Planning an MCP integration?

Talk to ZSpace Labs about MCP server development and API and backend integration.

Start a Project
19

Conclusion

MCP is becoming the standard way to give AI applications access to tools and data. Build narrow, well-authorized servers on top of your APIs, target the current specification and treat security as a first-class concern. Next: build an MCP server, MCP vs API and MCP security.

FAQ

Common questions.

An open protocol that standardizes how AI applications connect to external tools, data and prompts. An MCP server exposes capabilities once, and any MCP-compatible AI application can discover and use them.

MCP was introduced by Anthropic in November 2024 and was contributed to the Agentic AI Foundation, a directed fund under the Linux Foundation, in December 2025. The specification is developed openly with versioned releases.

As of October 2026, the latest revision is dated 2026-07-28. It made the protocol stateless, removing the initialize handshake and protocol-level sessions, and added server/discover. Check modelcontextprotocol.io for newer revisions.

The host is the AI application the user interacts with. Inside it, an MCP client connects to each MCP server. Servers expose tools, resources and prompts from a system such as a database, SaaS product or file store.

Tools are functions the model can call to take actions or fetch data. Resources are data the application can read, identified by URIs. Prompts are reusable templates users can invoke.

stdio for local servers launched by the host, and Streamable HTTP for remote servers. The older HTTP+SSE transport is deprecated.

For remote HTTP servers, MCP uses OAuth 2.1-based authorization: servers publish protected resource metadata, clients obtain audience-bound tokens with PKCE, and servers must validate that tokens were issued for them and must not pass them through to other APIs.

No. MCP servers usually wrap existing APIs to make them usable by AI applications. Your APIs remain the source of business logic and permissions.

Many AI assistants, IDEs, agent frameworks and model platforms support MCP clients, and many software vendors publish MCP servers. Support for specific features varies, so check each client's documentation.

The protocol defines authorization and security requirements, but safety depends on implementation: trusted servers only, least-privilege tools, user consent, audience-bound tokens, input validation and protection against prompt injection through tool results.

Get in touch

Have a project in mind?

Whether you're building a new digital product, improving an existing website, or looking to automate part of your business — let's talk.