Fleet 1.13:Teams are now shipping 5x more PRs with autonomous pipelines.See what's new →
FleetFleet
Glossary

Model Context Protocol

Model Context Protocol (MCP) is an open standard, introduced by Anthropic in 2024, that defines how AI models communicate with external tools and data sources through a structured JSON-RPC interface.

Before MCP, integrating an AI assistant with external systems — databases, APIs, file systems, version control — required bespoke code for each combination of model and tool. MCP standardizes the interface: a compliant tool (an MCP server) exposes a set of named operations; a compliant model client discovers and calls those operations using a defined protocol over stdio or HTTP.

MCP enables tool reuse across model providers. An MCP server built for Claude can, in principle, be used by any MCP-compatible client. This shifts the integration burden from N-times-M pairings to N plus M: each tool implements MCP once, and each model client implements MCP once.

The protocol handles tool discovery (listing available tools and their schemas), tool invocation (calling a tool with typed arguments), and result streaming (returning results incrementally for long-running operations). It also defines resource references (pointers to external data the model can read) and prompt templates.

How this relates to Fleet

Fleet exposes 32 tools through an MCP server (fleet mcp serve). Claude Code auto-discovers these tools via the .mcp.json configuration file in the repository. This means Claude Code agents running inside a Fleet-managed fleet can call Fleet operations — querying agent status, publishing fabric events, reading audit logs — directly from within their task execution loop.

Frequently asked questions

Is MCP specific to Claude?

MCP was introduced by Anthropic and is natively supported by Claude. Other model providers and open-source projects have begun implementing MCP compatibility, but Claude and Claude Code remain the most mature MCP-native clients as of 2025.

What is the difference between an MCP tool and a function call?

Function calling (as defined by OpenAI and supported by most major models) is a model-to-application interface for a single application. MCP is a model-to-ecosystem interface — a server implementing MCP can serve any compatible model client without per-client code. MCP also defines resources and prompt templates beyond simple function invocation.

Run your first agent fleet

One binary. Five minutes. See every agent, coordinate every handoff, and keep a full audit trail of what your fleet did.