Articles
Industry news, technical articles, and product introductions
📚 Claude Tutorials Hub
40+ step-by-step Claude guides — prompt engineering, Claude Code, API, agents. Browse by topic →
Loading...
Claude Code MCP Shows Connected but 0 Tools: "Invalid result for tools/list" (ttlMs / cacheScope), Reproduced and Fixed
An MCP server shows as connected but exposes 0 tools, and the log says Invalid result for tools/list with ttlMs and cacheScope failing validation. Reproduced with a stub server on Claude Code 2.1.280, 2.1.285 and 2.1.288: the cause is not extra fields being rejected. The server negotiated MCP 2026-07-28 and then left out fields that revision requires (resultType, ttlMs, cacheScope); adding unknown fields works fine. Whether stdio uses the new protocol is decided by a remote flag that is off by default, so the same version breaks for some users and not others, and 2.1.280 fails the same way once negotiation is on. MCP_PROTOCOL_NEGOTIATION=legacy (also works in settings.json env) restores the tools; servers fix it by adding the three fields.
mcpclaude-code+4
pitfallsOct 3, 20268 min
192
What People Built with the Fruit Fly Brain: Mario, Minecraft, DOOM and More — 9 Projects Taken Apart, 2 Retested
Since the fly connectome went public, GitHub has filled with fruit-fly-brain projects: DOOM, Mario, Flappy Bird, Minecraft, a phone app, a desktop pet, even trading signals. I read nine READMEs and asked how many neurons, who really decides the actions, and whether there are controls. I retested two: DesktopFly passes all its suites; Fly Mario falls in a pit 1.7 s after I cut its giant fiber, freezes at 0.8× weights and dies at 1.3×.
open-sourcegithub+7
fruit-flyOct 3, 202611 min
251
Claude Code install errors, reproduced: EACCES, a 600s mirror stall, Node 20 silently getting an old version, a region-block install.sh, and the native installer removing your npm copy
I reproduced every Claude Code install failure I could on macOS: 15 verbatim errors, each with wall time and exit code. npm -g into /usr/local fails with EACCES, exit 243. A cache dir that is merely 0555 gets blamed on root-owned files, with sudo chown advice. From Beijing, npmmirror took 147s and then >600s, npmjs 11-12s (2 samples each). On Node 20, an unpinned install silently lands on 2.1.197. Fetching claude.ai/install.sh from a blocked region gives curl exit 0 and a 447 KB HTML page. The native installer runs npm uninstall -g on your npm copy without saying so; it removed mine.
claude-codetroubleshooting+5
pitfallsSep 29, 202611 min
286
Was a Fruit Fly Brain Really Uploaded to a Computer? Eon's Demo, Taken Apart Layer by Layer
Eon Systems' 'uploaded fruit fly' is four layers stacked together: FlyWire's wiring diagram, the Shiu 2024 brain model, the NeuroMechFly body, and a hand-built brain–body interface. The widely shared '91% behavior accuracy' is really 91% of 164 circuit predictions in the Shiu paper, not a score for the virtual fly. Rebuilding it from the same open parts, I found the brain fires no spikes without input. What was copied is the structure, part of the function, and not the fly itself.
fruit-flyconnectome+6
fruit-flySep 28, 20269 min
330
Claude Code "bash denied by auto mode": Why It Blocks, "could not evaluate" and "unavailable for this model" Tested
In auto mode, a blocked Bash call usually shows one of three messages: denied by auto mode, Auto mode could not evaluate this action, or auto mode unavailable for this model. I ran 40-odd real sessions on Claude Code 2.1.280. denied means the classifier judged the action out of scope, most often [Code from External]: it would run external code you never named. Retrying won't help. Name the source in your prompt, or declare it trusted in autoMode.environment in user-level settings. could not evaluate means the classifier returned no usable verdict. unavailable for this model means the model is older than claude-opus-4-6; under claude -p it is silently downgraded, with only a WARN line in the debug log. In 2.1.280 the verdict is computed server-side and returned with the main response. Behind a relay gateway that only admits Claude Code clients, the local fallback classifier request gets a 503, which is a reliable cause of "temporarily unavailable (server error)".
claude-codepermissions+4
pitfallsSep 27, 202611 min
341
Claude Code "Invalid API key · Fix external API key": Not logged in, Credit balance is too low, API Error 401/429/529 — Exact Messages and Retry Behavior, Tested
28 cases, 61 claude -p runs on Claude Code 2.1.280 against a local Messages API stub. A 401 is retried 10 times, so Invalid API key · Fix external API key shows up after ~3 minutes; a key with non-ASCII chars or an embedded newline is rejected locally with 0 requests in 0.28 s. Every error goes to stdout, stderr is 0 bytes, exit 1, and JSON subtype still says success. CLAUDE_CODE_MAX_RETRIES=0 fails a 401 in 0.28 s. Set both KEY and TOKEN and both headers are sent.
claude-codetroubleshooting+4
pitfallsSep 27, 202611 min
288
Claude Code "Command timed out after 2m 0s": Two Timeout Paths, BASH_DEFAULT_TIMEOUT_MS and run_in_background Tested
Claude Code's Bash tool times out after 120 seconds by default. I ran 19 real sessions on 2.1.280 and found two timeout paths: only commands whose first word is sleep get killed with Exit code 143 / Command timed out after 2m 0s; everything else is moved to the background and killed 5 seconds after claude -p winds down. Either way claude exits 0, stderr is 0 bytes and the JSON top level says is_error=false. BASH_DEFAULT_TIMEOUT_MS=8000 killed at 8.17s; 0 or abc silently fall back to 120s; an explicit timeout above BASH_MAX_TIMEOUT_MS was silently clamped to 15s.
claude-codetroubleshooting+4
pitfallsSep 26, 20269 min
290
Claude Code MCP server Failed to connect: CONNECTION_CLOSED, connection timed out after 30000ms and ENOENT, reproduced one by one
Six causes behind Claude Code's MCP "Failed to connect", reproduced on 2.1.280: mcp list exits 0 on failure, CONNECTION_CLOSED hides two causes that only --debug-file reveals, and one server that never handshakes pushes claude -p wall time 4.63s → 36.21s, duration_ms only 4323.5 → 5930.
mcpclaude-code+4
pitfallsSep 24, 202610 min
337Service Up, Ports Open, Certs Valid, VPN Dead for 4 Hours: Tailscale Took Over DNS and Left the Proxy Box With No Upstream
A Los Angeles VPS running sing-box (VLESS-REALITY + Hysteria2) lost its VPN the day after Tailscale was installed. systemctl, ports and certificates were all fine. The root cause was in /etc/resolv.conf: Tailscale manages DNS by default, the tailnet had no global nameservers, and when dhclient renewed its lease tailscaled read an empty resolv.conf and dropped its upstream list. From then on every public domain got SERVFAIL, and the REALITY handshake could not even resolve www.apple.com. Full timeline, the evidence for each step, three fixes, and the rules we added to CLAUDE.md so an AI assistant (Claude Code) does not walk into this again.
claude-codetroubleshooting+8
pitfallsSep 17, 20266 min
280How to Fix Claude Code Error: temporarily unavailable, so auto mode cannot determine the safety of bash
Claude Code auto mode pops up 'temporarily unavailable, so auto mode cannot determine the safety of bash'? First, the conclusion: it's not your command that's dangerous; it's the safety classifier (an additional model call) that's temporarily unavailable. This article provides a four-step fix, a complete variant lookup for model name × tool name × reason, and a mechanism explanation for why read-only operations are unaffected.
pitfallsSep 4, 20265 min
656GitHub Native Stacked PR Tutorial: How to Use the gh stack Command, How to Merge, and How to Convert Old Branches
GitHub made Stacked PR a native feature and opened public preview on July 30, 2026: split a large change into a series of stacked small PRs, review layer by layer, and merge the entire stack with one click. This article is based on the official changelog and gh-stack documentation: five-minute quickstart (init/add/push/submit), review and merge rules (can you merge only one?), how to convert existing branches into a stack, daily maintenance with rebase/sync, and answers to frequent questions like pricing and Windows support.
developerSep 4, 20265 min
669How Large a Local LLM Can a 24GB Mac mini Run? A Summary of Memory Budgets, Measured Speeds, and Acceleration Methods
What models can a Mac mini with 24GB unified memory actually run? The answer: 27B with 4-bit quantization is the ceiling, and we successfully ran Qwen3.8-27B on the base M4 Mac mini—peak memory 19.4GB, 11.7-12.2 tok/s with speculative decoding. This article summarizes all measurements on this machine: memory budgets for various model sizes, speed expectations, real effects of three acceleration methods (DFlash 2 / native MTP / MLX vs llama.cpp), and how to choose quantization levels.
ai-tutorialsSep 4, 20266 min
421