---
title: "FastMCP: The Framework Behind My MCP Servers"
description: "Aleksandr Filippov builds Model Context Protocol servers on FastMCP — an async tool layer for a PyPI-published agent-memory server, a production system-of-record server with a curated Deep Research endpoint, and an HR server designed fail-closed around sensitive data."
date: "2026-08-27T07:00:00Z"
last_updated: "2026-08-28"
build_time: "2026-08-28T03:11:43Z"
skill_name: "FastMCP"
skill_description: "MCP servers built on FastMCP — an async tool layer behind a PyPI-published memory server, a production system-of-record server, and an HR server designed fail-closed — with tool surfaces curated for agents rather than generated from an API."
skill_category: ["mcp-tooling","ai-engineering"]
since: "2025-06-02"
last_used: "2026-08-28"
related_skills: ["mcp","python","llm-engineering","fastapi","oauth"]
related_projects: ["youtrack-mcp-server","mcp-context-server","peopleforce-mcp-server"]
related_experience: ["ai-product-manager-at-spotware"]
keywords: ["FastMCP","Model Context Protocol","MCP Server","Tool Design","Async Python","Streamable HTTP","stdio Transport","Agent Tooling","Python"]
license: "https://creativecommons.org/licenses/by/4.0/"
canonical: "https://www.alexfeel.info/skills/fastmcp/"
---

FastMCP is the framework under every MCP server I build, and the skill is knowing **which decisions the framework leaves to you**. The framework handles the protocol; the server's worth is decided in what its tools say and refuse. Three servers exercise that: a durable **agent-memory server** published to PyPI and listed in the official MCP Registry, whose async tool layer fronts thread-scoped storage with full-text, semantic, and hybrid retrieval; a **production system-of-record server** that turns a project-tracking platform into agent-callable tools, plus a second, deliberately narrow endpoint exposing only the `search` and `fetch` pair ChatGPT's Deep Research connector accepts; and an **HR-platform server in development**, designed fail-closed around a two-tier sensitivity model before the first tool shipped.

The recurring craft across them: tool surfaces **curated for an agent's context budget** rather than generated one-to-one from an upstream API — responses trimmed to what the caller needs with raw payloads one parameter away, errors written as corrections an agent can act on rather than status codes, per-user credentials whose responses are never cached, and partial degradation that marks the inaccessible corner instead of failing the whole call. Servers run across stdio and streamable HTTP transports, into Claude Code, agent runtimes, and gateway deployments alike. The three servers are in the **Related Projects** panel above.


## Site index

- [llms.txt](https://www.alexfeel.info/llms.txt)
- [Complete index](https://www.alexfeel.info/llms-index.txt)