Open sourcePython · ≈29k stars · Apache-2.0
FastMCP
The fast, Pythonic way to build MCP servers and clients.
FastMCP (created by Jeremiah Lowin, now stewarded by Prefect) became the de-facto standard for authoring MCP servers in Python — decorators, auth, proxying and deployment in a few lines. Now among the most-starred tools in the protocol layer.
Activity
- Last push
- · yesterday
- Latest release
- v4.2.3
· yesterday - Last 90 days
- 20+ releases
v4.2.3v4.2.3: Trace Elements
· yesterdayFastMCP 4.2.3 adds an opt-in parent_task_spans setting for background tasks: turn it on and each task's worker span nests inside the tools/call request that submitted it, so the whole job reads as one trace (off by default, where the worker still starts its own trace linked…
v4.2.2v4.2.2: Tea for Two (Too)
· 3d agoFastMCP 4.2.2 fixes skills discovery for tool-only clients. Adding a server transform such as ResourcesAsTools made skills/list come back empty even though the skill:// files stayed readable; skills are now listed whenever their files are actually served. Thanks to our 2…
v4.2.1v4.2.1: 4, 2, 1... Liftoff
· 4d agoFastMCP 4.2.1 is a security and correctness patch on top of 4.2.0. It tightens OAuth and token handling: JWTs aren't accepted before their nbf, provider required_scopes survive a custom verifier, pre-registered OAuth clients can be pinned to their issuer, and consent, metadata…
v4.2.0v4.2.0: Mad Skills
· 8d agoFastMCP 4.2 serves agent skills from the server. A skill used to live in a folder on each machine, so every agent kept its own copy and an update meant asking everyone to reinstall. Now the server holds one copy next to the tools the skill describes, and a deploy updates every…
v4.2.0a5v4.2.0a5: Skillium FancysonPre-release
· 8d agoFastMCP 4.2.0a5 adds SkillManifestProvider, which serves skills from their manifests (frontmatter plus each file's digest and size) and reads a file only when a client reads it, so skills kept in a bucket or database don't have to be loaded to answer skills/list.…
Checked against GitHub on Nov 21, 2026. Release notes are shortened to plain text.
The team behind it
Washington, DC
Workflow orchestration, now stewarding FastMCP.
Prefect builds dataflow and workflow orchestration infrastructure, and in 2025 took stewardship of FastMCP — the most popular way to author MCP servers. A data-platform company moving squarely into the agent harness layer.
In research (1)
- Agentic AI Defense: Decode-Time Provenance Binding for MCPVerdict: Incremental
Oct 22, 2026 · The testbed's MCP server is a FastMCP process running over stdio.
Neighbours on the workbench
TypeScript · ≈395k stars · MIT
openclaw/openclaw
The viral open-source personal AI assistant that really does things.
Maintained by OpenClaw Foundation
v2026.11.6releasedShell · ≈329k stars · MIT
mattpocock/skills
Small, composable agent skills for real engineering work.
Maintained by Matt Pocock (AI Hero)
MDX · ≈323k stars · MIT
obra/superpowers
An agentic skills framework and software methodology that works.
Maintained by Jesse Vincent (obra)
Connections
Relations from the Harness Hub knowledge graph, as charted in the State of Harness reports.
Maintained by · 1
- PrefectStartup
Built on · 1
- Model Context ProtocolProject
Similar entries · 3
- ComposioProject
- gemini-notebook-mcp-cliProject
- python-sdkProject
