framework
FastMCP is a framework for building Model Context Protocol (MCP) servers and clients, letting developers expose tools, data, and prompts to AI agents.
No evidence-backed relationships are recorded.
A developer's GraphRAG build turns Thailand's 96-section PDPA into a 190-node graph so an agent can walk from Section 26 to the fines that cite it. The published part argues the vector-search gap from vocabulary and reports no measured recall figures.
Reality
A builder audited the human-in-the-loop gate on his own MCP write tool and found a keyword argument the caller sets. Optional evidence makes an optional check.
Reality
S&P Global Energy says per-dataset Genie agents, bundled by a FastMCP proxy, cut launch time for conversational data products from months to days. Its governance claim rests on Unity Catalog, though part of the estate sits in sources outside Databricks.
Reality
A dev.to harness guide puts numbers on two ways MCP breaks at scale, 8,000 to 15,000 tokens of tool schema on every prompt and a SQLite session lock duplicate stdio processes cannot share. Its fix moves stateful tools onto a supervised loopback daemon.
Reality
His case rests on a refund workflow where anything over $100 needs human confirmation, a rule that stays an instruction while it lives in the prompt and becomes enforceable only when something inspects the tool call first.
Reality
The Python SDK's v2.0.0 moved mcp.server.fastmcp wholesale on July 28 and shipped no shim, so any project that wrote mcp>=1.0 pulls 2.x on the next fresh install. A second default quietly changed the name clients see.
Reality
The official mcp package hit 2.0.0 on 28 July with renamed imports and a shorter context-manager yield, so wrappers that declared no upper bound now fail at runtime on a fresh install of code nobody touched.
Reality
A fault-injection scan of 31 popular MCP servers found only 3% of their 265 tools declare an output contract that would reject a well-typed but wrong response. The failing 97% split into two different problems.
Reality
An AWS EC2 rig with mcp unbounded in requirements.txt picked up mcp 2.2.0 and stopped importing. The server edit is two lines; the pip resolver and the test suite's camelCase attribute reads are where the work sits.
Reality
The code moved into fastmcp-slim behind client and server extras, and pip -U over 3.2.x does not always re-resolve them. The httpx2 swap breaks a second class of code that still compiles.
Reality
The cheap fractional-GPU tiers top out at 3 GB of device memory, so the weights pick the instance and hand you a Graviton2 host with a 2018 Turing card. The interesting cost is the toolchain, not the hourly rate.
Reality
A dev.to walkthrough wires chokidar, tree-sitter, Qdrant and an MCP server into a code search stack. Every part is off the shelf; the unresolved work is reindexing and retrieval quality.
Reality