Unclear It is not stated what decides whether Claude Code skips waiting for the resource listing.
MCP (Model Context Protocol) servers are external programs or services that give Claude Code extra tools and data. After connecting to one, Claude Code asks what it offers. It now does this in two separate groups instead of one:
- tools, commands and skills
- resources and resource templates
For servers connected over HTTP or SSE (ways of reaching a server over the network) that offer resources, Claude Code can now skip waiting for the resource group under some conditions and ignore any errors from it. Tools can then be registered without waiting on a slow resource listing. Before, everything was fetched together and Claude Code waited for all of it.
The switch for protocol version negotiation on stdio MCP servers (servers that run as a local process) was read as on for this site's account and for an anonymous baseline, having switched on since the previous reading.
MCP servers with slow resource listings should make their tools available sooner after startup.
tengu_mcp_protocol_negotiation_stdio On for this account, and not off by defaultThe flag server returned on for the one account this site reads, and nothing in this release compiles it off by default. The compiled default is shown below, and says which it is when we cannot read one: a fifth of gates compile in a string or a number rather than on or off, and most published releases have no gate table behind them at all. No client can see what the server returns for your account.
This account: on · anonymous baseline: on · compiled default in v2.1.292: on
These values were read against a different version of Claude Code, so treat them as the nearest reading available instead of one taken on this release.
Read once, for one account on one subscription tier, against v2.1.292. It isn't a statement about your account. What a flag value here can and cannot tell you
A reading is one sample. Claude Code evaluates its flags remotely, so no client sees the targeting rule behind a value and this says nothing about your account.
A reading is one sample. Claude Code evaluates its flags remotely, so no client sees the targeting rule behind a value and this says nothing about your account.
It is not stated what decides whether Claude Code skips waiting for the resource listing.