MCP Glossary Search. Find any MCP term fast.
Instant search over the 60 terms in our MCP glossary, grouped by topic, with plain-English definitions written against the 2026-07-28 specification.
Search the glossary
Type part of a word, or pick a topic to browse.
60 terms
- Model Context Protocol (MCP) Basics
- An open standard for connecting AI applications to external systems such as files, databases and business tools. The official docs compare it to a USB-C port for AI apps.
- Specification Basics
- The document that defines MCP's rules for clients and servers. The spec is based on a TypeScript schema file, which is the source of truth for every message.
- Protocol version Basics
- A date string that names a spec release, such as
2026-07-28. Every request now declares the version it uses, and a server that does not support it replies with an "unsupported protocol version" error listing the versions it does support. - Host Basics
- The AI application a person uses, such as Claude Desktop or Visual Studio Code. The architecture docs define it as the app that "coordinates and manages one or multiple MCP clients."
- Client Basics
- A component inside the host that keeps a connection to one MCP server. The host creates one client per server, so three connected servers means three clients.
- Server Basics
- A program that provides tools, data or prompts to MCP clients. It can run on your computer or on a vendor's infrastructure. See what is an MCP server.
- Local server Basics
- An MCP server that runs on the same machine as the host, usually launched by the host over stdio. It can reach local files and programs, so the security guide recommends sandboxing.
- Remote server Basics
- An MCP server hosted elsewhere and reached over Streamable HTTP. Remote servers typically serve many clients and use OAuth for sign-in.
- Connector Basics
- A common product name for an MCP connection inside an AI app. Claude and ChatGPT, for example, let users add "custom connectors" by entering a remote MCP server URL, per Vercel's setup guide.
- SDK (software development kit) Basics
- A code library for building MCP servers or clients in a given language. Official SDKs exist for TypeScript, Python, C#, Go, Rust, Ruby, Java, Swift, PHP and Kotlin, ranked in tiers on the SDK page.
- JSON-RPC 2.0 Messages and transport
- The lightweight message format MCP uses for every exchange. It defines requests, responses and notifications, and MCP adds a few rules, such as request IDs never being null.
- Request and result Messages and transport
- A request is a message from client to server that starts an operation and carries a unique ID. The server answers with a result (or an error) that carries the same ID; in the 2026-07-28 spec every result includes a
resultTypesuch as"complete". - Notification Messages and transport
- A one-way message that expects no reply and carries no ID. Servers use notifications for things like progress updates and change alerts.
_metaMessages and transport- A metadata field attached to MCP messages. Under the base protocol, every request uses it to carry the protocol version and client capabilities, and usually the client's name and version.
- Stateless Messages and transport
- The property that every request contains all the information needed to process it. The 2026-07-28 spec made MCP stateless and removed the old
initializehandshake and protocol-level sessions, per the changelog. server/discoverMessages and transport- A request every server must support that returns its supported versions, capabilities and identity. Clients may call it first, but they are not required to.
- Capabilities Messages and transport
- Declarations of which features a client or server supports, such as tools or elicitation. Clients send theirs on every request; servers return theirs from
server/discover. - Transport Messages and transport
- The channel that carries MCP messages, such as stdio or HTTP. The transport overview says message meaning is identical on every transport; only framing and delivery differ.
- stdio Messages and transport
- A transport where the client launches the server as a subprocess and they exchange newline-delimited messages over standard input and output. The server must not write anything to stdout that is not a valid MCP message.
- Streamable HTTP Messages and transport
- The transport for remote servers. Each message is an HTTP POST to a single MCP endpoint, and the server replies with JSON or a short Server-Sent Events stream; it replaced the older HTTP+SSE transport, which is now deprecated.
- Primitive Server features
- One of the core building blocks a server or client can offer. Servers offer tools, resources and prompts; clients offer elicitation.
- Tool Server features
- A function the AI model can call to take an action, such as querying a database or sending a message. Clients find tools with
tools/listand run them withtools/call, per the tools spec. - Input schema Server features
- A JSON Schema that describes the inputs a tool expects, including which are required. It lets the AI build valid calls and lets software check them.
- Structured content Server features
- Machine-readable data a tool returns in a
structuredContentfield. If the tool declares an output schema, the server must return data that matches it. - Tool annotations Server features
- Optional hints about a tool's behavior, such as
readOnlyHint,destructiveHint,idempotentHintandopenWorldHint. The schema says they are only hints and clients should never rely on them from untrusted servers. - Tool execution error Server features
- A failure reported inside a normal tool result with
isError: true, such as a bad date or an API failure. It differs from a protocol error (like an unknown tool) and gives the AI a chance to correct itself and retry. - Resource Server features
- Read-only data a server shares as context, such as a file, a database schema or a report. Each resource has a unique URI and an optional MIME type, per the resources spec.
- Resource template Server features
- A parameterized resource address, such as
weather://forecast/{city}/{date}. Templates follow the URI template standard (RFC 6570) and let clients request many related resources. - Prompt Server features
- A reusable instruction template a server offers for users to pick, often as a slash command. Prompts are user-controlled, which means they run only when someone chooses them.
- Elicitation Interaction patterns
- A way for a server to ask the user for more information during a task, such as a seat preference or a confirmation. The client concepts page describes two modes: form and URL.
- URL mode elicitation Interaction patterns
- An elicitation that sends the user to a web page instead of a form in the app. The data never passes through the client, so it suits sensitive steps like credential entry; servers must not use form mode for passwords, API keys or payment details.
- Multi Round-Trip Requests (MRTR) Interaction patterns
- The 2026-07-28 pattern for when a server needs input to finish a request. The server returns an "input required" result listing what it needs, and the client retries the original request with the answers, per the message patterns page.
- Subscriptions (
subscriptions/listen) Interaction patterns - A long-lived request a client opens to receive chosen change notices, such as "tool list changed" or "resource updated." It replaced the older HTTP GET stream and
resources/subscribemethods in the 2026-07-28 spec. - Progress notification Interaction patterns
- A message a server sends while a request is still running to report how far along it is. The client opts in by attaching a
progressTokento its request. - Cancellation Interaction patterns
- Abandoning a request that is still running. On stdio the client sends a cancel notification; on Streamable HTTP, closing the response stream counts as cancellation.
- Pagination Interaction patterns
- Splitting long lists, such as tool or resource lists, into pages. The server returns a
nextCursor, and the client sends it back ascursorto get the next page. - Caching hints Interaction patterns
- The
ttlMsandcacheScopefields on list and read results.ttlMssays how many milliseconds a result stays fresh, andcacheScopesays whether shared caches may reuse it (public) or only the same authorization context (private). - Completion Interaction patterns
- A feature that suggests valid values for prompt or resource template arguments as a user types. For example, typing "Par" for a city could suggest "Paris."
- Sampling Deprecated features
- A client feature that let servers ask the host's AI model for a completion. It is deprecated as of 2026-07-28; new builds should call an LLM provider's API directly.
- Roots Deprecated features
- A client feature that told servers which folders they should focus on, using
file://URIs. It is deprecated as of 2026-07-28; the docs suggest passing paths through tool parameters, resource URIs or server configuration instead. - Logging Deprecated features
- A feature that let servers send log messages to the client. It is deprecated as of 2026-07-28; servers should log to stderr on stdio or use OpenTelemetry. Deprecated features stay usable until at least the first revision released on or after 28 July 2027.
- Extension Extensions
- An optional, opt-in addition to the core protocol that both client and server must support. Extensions use identifiers like
io.modelcontextprotocol/tasksand are listed in the extensions overview. - Tasks Extensions
- An official extension for long-running operations. The server returns a durable task ID, and the client polls with
tasks/getuntil the status reaches completed, failed or cancelled, per the Tasks docs. - MCP Apps Extensions
- An official extension that lets a server show interactive UI, such as charts, forms or dashboards, inside the chat. The UI runs in a sandboxed iframe controlled by the host, per the MCP Apps docs.
- Skills over MCP Extensions
- An official extension that lets servers share Agent Skills, which are folders with a
SKILL.mdinstruction file and supporting files. Hosts discover them withskills/listand must verify file digests before use, per the Skills docs. See MCP Apps, Tasks and Skills explained for more on all three. - Protected Resource Metadata Security and authorization
- A document (defined in RFC 9728) that a protected MCP server must publish to point clients to its authorization server. Clients must use it to find where to sign in.
- Client ID Metadata Document Security and authorization
- A way for an MCP client to identify itself to an authorization server using an HTTPS URL as its client ID. It is the preferred registration method; Dynamic Client Registration is deprecated as of 2026-07-28.
- PKCE Security and authorization
- Short for Proof Key for Code Exchange, an OAuth safeguard against stolen authorization codes. The client creates a secret code verifier and proves it holds that secret when it trades the code for a token.
- Resource indicator (token audience) Security and authorization
- A parameter (RFC 8707) that names the exact MCP server a token is for. Clients must send it, and servers must reject tokens issued for any other audience.
- Scope Security and authorization
- A named permission an access token carries, such as
files:read. The spec encourages least privilege, with extra scopes requested later through a "step-up" flow when an action needs them. - Token passthrough Security and authorization
- An anti-pattern where a server accepts a token meant for another service and forwards it downstream. The security guide says it is explicitly forbidden.
- Confused deputy Security and authorization
- An attack where a trusted program is tricked into using its authority for an attacker. In MCP it can affect proxy servers that use one static OAuth client ID, so the spec requires per-client user consent.
- Prompt injection Security and authorization
- Hidden instructions in data or tool output that try to make the AI do something the user did not ask for. Stripe and Supabase both warn about it in their MCP docs and advise keeping tool approvals on.
- Human in the loop Security and authorization
- Keeping a person able to review and deny AI actions. The tools spec says there should always be a human in the loop with the ability to deny tool invocations.
- Reference servers Ecosystem
- Example MCP servers maintained by the MCP project, such as Filesystem, Git, Fetch and Time. The servers README calls them educational, not production-ready.
- MCP Inspector Ecosystem
- The official developer tool for testing MCP servers, described in its repository as "deterministic testing tools for MCP servers." It runs with
npx @modelcontextprotocol/inspector. - MCP Registry Ecosystem
- The official metadata catalog for publicly available MCP servers, in preview as of October 2026. It stores metadata, not code, and verifies namespaces through GitHub or DNS, per its about page. See the MCP registry explained.
- Agentic AI Foundation (AAIF) Ecosystem
- The Linux Foundation directed fund that hosts MCP. Anthropic donated MCP to it in December 2025, and Anthropic, Block and OpenAI co-founded it, per Anthropic's announcement. See who owns MCP.
- MCPA (Model Context Protocol Associate) Ecosystem
- A certification launched on 14 September 2026 by the AAIF and Linux Foundation Education. It is an online proctored multiple-choice exam aligned to the 2026-07-28 spec, per the Linux Foundation. The exam page lists it at 90 minutes.
From our MCP glossary, checked against the 2026-07-28 specification on 28 October 2026.
How to use it
How to use the MCP Glossary Search
Type part of a word, such as elic or OAuth. Terms whose name matches come first, then terms that mention it in their definition. Pick a topic to browse a group, such as security or deprecated features.
Links inside a definition open the official source or our deeper guide on that topic.
Limits
What it can't tell you
Definitions are short by design. For exact rules, use the linked specification pages; for context and examples, read the full guides.
The glossary follows the 2026-07-28 specification. Older articles, SDKs and apps may still use earlier terms, such as sessions or the initialize handshake.
FAQ
Common questions
What is the difference between a tool, a resource and a prompt?
A tool is an action the AI model can call, such as creating a record. A resource is read-only data the server shares as context. A prompt is a reusable template that a person chooses to run.
What is a host in MCP?
The AI application a person uses, such as Claude Desktop or Visual Studio Code. Inside it, one client connects to each server.
Is MCP still using sessions?
No. The 2026-07-28 specification removed protocol-level sessions and the initialize handshake. Every request now carries its own protocol version and capabilities.
What does deprecated mean in MCP?
A deprecated feature still works but is scheduled for removal, with a minimum twelve-month window under the feature lifecycle policy. Roots, sampling and logging are deprecated as of 2026-07-28.
Project Managers who will work with you on your project!
Irina S.
Benjamin G.
David G.
Jeanette M.
Mark S.
Maryna P.
Wondering what this costs? Every service has published pricing, and you don't need a discovery call to see it.
View pricingWant a second opinion on your MCP setup?
Request a free MCP readiness review. We'll look at the tools and AI apps you use and tell you where MCP could help, which servers exist and what to lock down first.
Request a Free Review →
