Skip to main content
LearnGlossaryMCP server
GLOSSARY

What is an MCP server.

DEFINITION

An MCP server is a service that exposes tools, resources, or prompts to AI agents over the Model Context Protocol. Agents discover the server, read its tool descriptions, and call those tools as part of their plan. A paid MCP server adds one more behavior on top: it can return HTTP 402 with a payment URL, expecting the agent's wallet to settle before the tool actually runs.

WHY IT MATTERS

One contract, many agent runtimes.

Before MCP, every tool provider had to ship a different integration for every agent host - one for Claude Desktop, one for a Cursor extension, one for an internal agent runtime, one for OpenAI's function-calling format. Each integration drifted independently. MCP collapses that into a single server interface. Write the server once; any MCP-aware client can use it.

That uniform contract is what makes MCP-server monetization viable. If every agent runtime spoke its own dialect, charging per tool call would require a separate billing integration per dialect. With MCP, the server returns 402 once, in HTTP, and any runtime whose agent has a wallet can settle it. The protocol pins the contract; the payment layer plugs in beneath it.

HOW IT WORKS

Advertise, invoke, optionally charge.

  1. Advertise. The server publishes a list of tools, each with a name, JSON-schema input, and a natural-language description. The agent's planner reads these descriptions when deciding which tool to call.
  2. Invoke. The agent calls a tool with structured arguments. The MCP transport (stdio, SSE, or HTTP) delivers the call to the server.
  3. Authorize. Paid servers check whether this caller has already paid for this tool call (typically by API key, session, or payment receipt). If yes, run the tool. If no, return 402 with a payment URL.
  4. Settle (if paid). The agent's wallet pays at the URL. The wallet provider confirms the payment to the server (typically via a signed webhook); the server marks the caller paid, and the retried call runs the tool.
  5. Return. The result flows back to the agent through the MCP transport. The agent integrates the result into its next reasoning step. Free MCP servers skip steps 3 and 4 entirely.

The provider never has to know which agent runtime is calling, and the agent never has to know which payment provider the MCP server uses. Both sides talk through the protocol contract.

EXAMPLES

Three MCP-server shapes.

EXAMPLE 1

A documentation-search MCP server

A startup publishes an MCP server that exposes a single tool, search_docs(query). Any MCP-aware agent (Claude Desktop, a coding agent, an internal agent at a customer) can install the server, see the tool advertised, and call it. The startup never has to ship a separate SDK per agent runtime - the MCP server is the SDK. Free initially, then monetized later by returning 402 on heavy queries.

EXAMPLE 2

An internal MCP server bridging a private database

An engineering team runs an MCP server inside their own infrastructure that exposes read-only tools against their production analytics warehouse. Their internal Claude-based agents call those tools to answer business questions. No external API, no SDK; the MCP server is the contract. Because it is internal, no payment layer is needed - but the same server pattern works unchanged if they later expose a paid version to partners.

EXAMPLE 3

A paid MCP marketplace listing

An independent developer publishes an MCP server that calls a premium financial-data API and resells it per-query. Their server returns 402 with a hosted payment URL for any tool call. Agents that have a wallet pay automatically (within their spend policy); agents without a wallet see the 402 and stop. The developer captures revenue per call without onboarding each customer manually.

FAQ

Three common questions.

Is every MCP server a paid MCP server?

No. MCP servers are protocol-level constructs and most are free. The protocol does not mandate any payment flow. A paid MCP server is one that has chosen to gate some or all of its tool calls behind an HTTP 402 response with a payment URL, expecting an agent wallet to settle before the tool runs. Free MCP servers stay free; paid ones add the 402 layer on top of the same tool advertisement and invocation pattern.

Who runs the MCP server, the agent runtime or the tool provider?

The tool provider runs the MCP server. It is their service, their endpoint, their pricing. The agent runtime (Claude Desktop, a custom agent host) acts as the MCP client - it discovers the server, reads its tool descriptions, and calls those tools when its planner decides to. This separation is what makes monetization clean: the provider can charge per tool call without coordinating with every possible agent runtime, because the runtime simply forwards 402 responses to the paying wallet.

Does running a paid MCP server require running a blockchain node?

No. The MCP server only needs to do three things: advertise its tools, accept tool calls, and return either a 200 with the result or a 402 with a payment URL. Settlement happens off the MCP server - typically via the wallet provider's hosted checkout. Once the wallet provider confirms payment (via webhook), the server completes the call. The MCP server itself never holds crypto, never signs transactions, and never reads on-chain state.
Last reviewed: 2026-05-15. Published under CC BY 4.0.

Monetize your MCP server.

Return 402, accept USDC, settle in seconds. Free to start.