ceos/fastmcp
1
0
Fork 0
mirror of https://github.com/PrefectHQ/fastmcp.git synced 2026-08-09 07:09:11 +02:00
Code Issues Projects Releases Packages Wiki Activity

Flag the sampling removal at the top of the page

Browse source
This commit is contained in:
Jeremiah Lowin 2026-07-26 20:42:12 -04:00
commit 4a616d6e39
No known key found for this signature in database
1 changed files with 4 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

6
docs/servers/sampling.mdx
View file

@ -5,12 +5,14 @@ description: Generate text from a FastMCP server — by calling an LLM directly,
icon: robot
---
<Warning>
**`ctx.sample()` and `ctx.sample_step()` were removed in FastMCP 4.** The modern MCP protocol gives a server no channel to push a request to its client, so there is nothing left for those methods to do. Generate by [calling an LLM directly](#calling-an-llm-directly), or [ask the caller's model](#asking-the-callers-model) when borrowing their model is the point.
</Warning>
A tool that needs text generated calls a model to get it, and in FastMCP 4 that call is ordinary Python: your server holds an API key, creates a provider client, and awaits a completion inside the tool. No protocol is involved, so the tool behaves the same for every client — including the many that never implemented sampling at all.
The alternative is to ask the caller. Sampling borrows *the caller's* model — their provider, their credentials, their bill — by returning a request for a completion that the client fulfils and hands back. Every ask costs a full round trip, so it earns its keep when using the caller's model is the point, and rarely otherwise.
`Context` carries no sampling methods in FastMCP 4. If you came here looking for `ctx.sample()`, [the removed methods](#the-removed-methods) covers what happened and where the capability went.
## Calling an LLM directly
Hold a provider API key in your server's environment, create the client once at module scope so connections are reused across calls, and generate inside the tool. You choose the model, control the prompt, see the token usage, and can test the tool with no client attached.