fastmcp-extensions
Unofficial extension library for FastMCP 3.x with patterns, practices, and utilities
Decision gist · record as of 2026-08-14
Yes, with conditions. Install if you are building multiple MCP servers or a production MCP deployment where auth, filtering, telemetry, and documentation consistency matter. The library is actively maintained, has low install friction, and is permissively licensed. However, it is still in Beta (Development Status 4), the auth factory's production readiness is not explicitly confirmed, and the ecosystem around FastMCP itself is young. Suitable for teams standardizing on MCP; less critical for a single throwaway server.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python 3.10 or later; fastmcp must be installed as a runtime dependency.
- Low friction; pure Python wheel with no compiled dependencies.
- Active maintenance as of 2026-08-14 with recent release.
License · maintenance · safety
permissive license (permissive) — Apache License 2.0 is permissive; you may use, modify, and distribute this package and derivative works freely, provided you include the license and attribution notices. No restrictions on commercial use.
last release 2026-08-14 (0 days) · last repo commit 2026-08-14 · 1 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 152,514 downloads/mo, #10,899 on PyPI
Alternatives
Verify before relying
pip install fastmcp-extensions
from fastmcp_extensions import mcp_server, mcp_tool, register_mcp_tools
app = mcp_server(name="my-server", package_name="my-package")
@mcp_tool(read_only=True)
def list_items() -> list[str]:
return ["item1", "item2"]
register_mcp_tools(app)- Whether the auth factory's OIDC and JWT modes are production-ready or still in beta.
- Performance characteristics when filtering large tool lists or handling high request volume.
- Compatibility guarantees across FastMCP 3.x minor versions and upgrade path to 4.x.
- Whether Sentry and Segment telemetry truly remain no-ops when keys are not supplied.
What it is and what it does
FastMCP Extensions is a library that sits on top of FastMCP 3.x and encodes common patterns for shipping production MCP servers. Instead of reinventing auth, filtering, telemetry, and documentation scaffolding for each new server, you inherit them from a single opinionated base. The library provides factories for assembling auth verifiers (OIDC for browsers, JWT for machines, token introspection), tool filtering based on MCP annotations (read-only mode, destructive-operation gating, modality checks), and integration with Sentry and Segment for structured telemetry. It also includes a server factory that wires up server-info resources, credential resolution from HTTP headers or environment variables, and optional asset discovery.
The library is designed around a philosophy that a CLI and an MCP server should share the same tool implementations, not drift into separate code paths. It provides decorators for deferred tool and resource registration, test utilities to measure tool-list size and call tools programmatically, and auto-generated Markdown documentation. Telemetry and auth are wired once and inherited by every server built on the library, reducing the surface for misconfiguration and making it easier to apply security hardening uniformly across a fleet of servers.
Use it for
- Build an MCP server with OIDC and JWT auth already wired, so each new server inherits the same verifier logic without hand-rolling auth middleware.
- Implement tool filtering (read-only mode, no-destructive mode) by annotating tools and letting the library enforce the filters across all clients automatically.
- Measure tool-list size before deployment to catch context-window truncation that would break agent interactions.
- Share tool implementations between a CLI and an MCP HTTP server using the same decorators and registration functions, eliminating code duplication.
- Integrate Sentry and Segment telemetry across both CLI and MCP paths without per-tool wiring; telemetry becomes a no-op if keys are not supplied.
- Generate Markdown documentation for your tool surface automatically, with per-tool URLs for sharing with stakeholders.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, with conditions.
Install if you are building multiple MCP servers or a production MCP deployment where auth, filtering, telemetry, and documentation consistency matter. The library is actively maintained, has low install friction, and is permissively licensed. However, it is still in Beta (Development Status 4), the auth factory's production readiness is not explicitly confirmed, and the ecosystem around FastMCP itself is young. Suitable for teams standardizing on MCP; less critical for a single throwaway server.
Install
fastmcp-extensions on PyPI
Before you install
Low friction; pure Python wheel with no compiled dependencies. Active maintenance as of 2026-08-14 with recent release. Depends on 10 runtime packages including fastmcp, httpx, pydantic, and telemetry sinks (Sentry, Segment), all standard ecosystem choices.
Requires Python 3.10 or later; fastmcp must be installed as a runtime dependency.
License in practice
Apache License 2.0 is permissive; you may use, modify, and distribute this package and derivative works freely, provided you include the license and attribution notices. No restrictions on commercial use.
Quickstart
pip install fastmcp-extensions
from fastmcp_extensions import mcp_server, mcp_tool, register_mcp_tools
app = mcp_server(name="my-server", package_name="my-package")
@mcp_tool(read_only=True)
def list_items() -> list[str]:
return ["item1", "item2"]
register_mcp_tools(app)Verify before relying
- Whether the auth factory's OIDC and JWT modes are production-ready or still in beta.
- Performance characteristics when filtering large tool lists or handling high request volume.
- Compatibility guarantees across FastMCP 3.x minor versions and upgrade path to 4.x.
- Whether Sentry and Segment telemetry truly remain no-ops when keys are not supplied.
Package facts
| License | permissive license permissive |
| Python support | Supports the current Python release >=3.10 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 10 packagesfastmcphttpxmcpmsgspecpy-key-value-aiopydanticsegment-analytics-pythonsentry-sdkstarletteuvicorn |
| Maintenance | Actively maintained 0 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 152,514 / month, #10,899 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Development Status :: 4 - BetaIntended Audience :: DevelopersLicense :: OSI Approved :: MIT LicenseProgramming Language :: Python :: 3Programming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13 |
Evidence: fastmcp_extensions-0.21.0-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “fastmcp extensions utilities”
- fastmcp-extensionsProvides hardened patterns and utilities for building Model Context…
- fastmcp-slimFastMCP exposes Python functions as Model Context Protocol (MCP)…
- fastmcpFastMCP is a Python framework for building Model Context Protocol…
Give your agent the search over MCP, or paste the wish link into any chat.
More Application Frameworks packages
FastAPI is a Python web framework for building REST APIs using type hints, with automatic request validation, serialization, and interactive API documentation.
Provides a way to document function parameters, class attributes, return types, and variables inline using Python's `Annotated` type hint syntax instead of traditional docstrings.
Textual is a Python framework for building cross-platform user interfaces that run in the terminal or web browser using a modern, component-based API.
Install it if you're developing CLI tools, dashboards, or interactive terminal applications.
Typer builds command-line applications from Python functions using type hints, automatically generating help text, argument parsing, and shell completion.
Install it if you are building CLIs in Python.
Build and connect to Model Context Protocol servers that expose tools, resources, and prompts to LLM applications over stdio, HTTP, or SSE transports.
Install it if you need to build or connect to servers.
Werkzeug is a WSGI utility library providing request/response objects, URL routing, an interactive debugger, HTTP utilities, and a development server for building web applications.
See also fastmcp · django-mcp-server · fastmcp-slim · jupyter-server-mcp · mcpadapt · tilt-mcp · astro-airflow-mcp · mcp-types · mcp-server-appwrite