Follow Discord
Sweep 22 Oct 2026 · 04:32Z Build v2.1.308 527 read Stable v2.1.308 Latest v2.1.308 Next v2.1.308 Feeds RSS JSON llms.txt llms-full.txt Unofficial
HomeReleasesv2.1.251entry #339

Claude Code v2.1.251 ·

Eval sandboxes run with claude.ai MCP servers off

Eval sandboxes force claude.ai MCP servers off so they can't reach real servers.

Under the hood Internal Changes
JSON All of v2.1.251
Under the hoodTier: how much it should matter to you
1Useful: my rating, 1 to 5
3Signal: worth watching, 1 to 5
Plugin EvalArea: what it touches
Internal ChangesKind: in v2.1.251,
Internal ChangesSection of the release
What

The internal evaluation harness now forces ENABLE_CLAUDEAI_MCP_SERVERS to false and pins its own temp directories, so evals cannot reach real MCP servers or share scratch space with the host.

Details
Evidence

ENABLE_CLAUDEAI_MCP_SERVERS: "false"

Strings lifted out of the shipped bundle, so the claim above can be checked against them.

Read from
Names in the bundleENABLE_CLAUDEAI_MCP_SERVERS
How sure we are
One source agreesOne thing we can check says the same as this entry.
Anthropic's release notes agreeChanged project-level .claude/settings.json env to no longer set CLAUDE_CONFIG_DIR, CLAUDE_CODE_TMPDIR, or TMPDIR/TMP/TEMP; set them in your…

See this entry in the whole of v2.1.251 →

Feedback