Download Latest Version v3.2.0_ Show Don_t Tool source code.tar.gz (26.4 MB)
Email in envelope

Get an email when there's a new version of FastMCP

Home / v3.1.0
Name Modified Size InfoDownloads / Week
Parent folder
README.md 2026-03-03 9.4 kB
0
v3.1.0_ Code to Joy source code.tar.gz 2026-03-03 17.4 MB
0
v3.1.0_ Code to Joy source code.zip 2026-03-03 18.1 MB
0
Totals: 3 Items   35.5 MB 0

FastMCP 3.1 is the Code Mode release. The 3.0 architecture introduced providers and transforms as the extensibility layer — 3.1 puts that architecture to work, shipping the most requested capability since launch: servers that can find and execute code on behalf of agents, without requiring clients to know what tools exist.

Code Mode

Standard MCP has two scaling problems. The entire tool catalog loads into context upfront — with a large server, that's tens of thousands of tokens before the LLM reads a single word of the user's request. And every tool call is a round-trip: the LLM calls a tool, the result flows back through the context window, the LLM reasons about it, calls another tool, and so on. Intermediate results that only exist to feed the next step still burn tokens every time.

CodeMode is an experimental transform that solves both. Instead of seeing your tool catalog directly, the LLM gets meta-tools: it searches for relevant tools on demand (using BM25), inspects their schemas, then writes Python that chains call_tool() calls in a sandbox and returns a final answer. Discovery is staged and targeted; intermediate results never touch the model's context window.

:::python
from fastmcp import FastMCP
from fastmcp.experimental.transforms.code_mode import CodeMode

mcp = FastMCP("Server", transforms=[CodeMode()])

Your existing tools don't change — CodeMode wraps them. The default three-stage flow (search → get schemas → execute) is configurable: collapse it to two stages for smaller catalogs, skip discovery entirely for tiny ones. The sandbox supports resource limits on time, memory, and recursion depth.

Read the docs here.

Search Transforms

Code Mode's discovery layer is also available as a standalone transform. SearchTools adds BM25 text search to any server — clients can query against tool names and descriptions and receive ranked results, without needing to know tool names upfront. This is useful anywhere the tool catalog is large, dynamic, or not known in advance.

Prefab Apps

3.1 adds early integration with Prefab, a frontend framework with a Python DSL that compiles to React. The vision: Python developers building MCP servers shouldn't have to leave Python to ship a proper UI. Prefab is still under very active development (their words: "probably shouldn't use it yet"), but the integration is here, the pieces are aligning, and 3.2 is where this gets interesting.

Auth Additions

MultiAuth lets you compose multiple token verification sources into a single auth layer — useful when you need to accept tokens from more than one provider (e.g., internal JWTs alongside a third-party OAuth provider). This release also adds out-of-the-box support for PropelAuth and a Google GenAI sampling handler.

Under the Hood

Heavy imports are now lazy-loaded, meaningfully reducing startup time for servers that don't use every feature. fastmcp run and dev inspector gain a -m/--module flag for module-style invocation, MCPConfigTransport now correctly persists sessions across tool calls, and search_result_serializer gives you a hook to customize how search results are serialized for markdown output. Eight new contributors, and the usual round of fixes.

What's Changed

New Features 🎉

Enhancements 🔧

Fixes 🐞

Docs 📚

Other Changes 🦾

New Contributors

Full Changelog: https://github.com/PrefectHQ/fastmcp/compare/v3.0.2...v3.1.0

Source: README.md, updated 2026-03-03