Windows GUI check — published sentinel-ir-mcp 0.5.9

Verdict

Source (GitLab, Apache-2.0): https://gitlab.com/jakubrojicek11/sentinel-ir
npm: https://www.npmjs.com/package/sentinel-ir
Playground (runs in your browser): https://sentinel-ir-playground-dc30c8.gitlab.io/

Desktop startup is verified; desktop-originated tool calls remain untested. Normally installed VS Code and its Cline extension both started the published server without signing in. Actual analysis calls passed through the MCP Inspector browser fallback, not a desktop client.

VS Code also reproduced the reported Error/empty-output symptom, but on its session-bound server entry. The separate locally configured / Global in Code entry started successfully with the same configuration. Evidence points to VS Code's session/policy surface, not a broken Sentinel executable. The exact underlying VS Code policy requirement is not established.

Environment and configuration

• Windows Server 2022; VS Code 1.146.0, official user installer, not portable.
• Onboarding bypassed with Continue without Signing In. No Microsoft/GitHub/Cline login.
• Primary runtime Node 22.23.5, secondary Node 24.22.2; spawned server ExecutablePath checked using Win32_Process, not inferred from shell PATH.
• Project: C:\t\Projekt Žluťoučký kůň\app; files src\index.js, src\util.js, src\main.rs, tool.py.
• Setup invoked as npx -y sentinel-ir-mcp@0.5 setup --client vscode. It printed a command; it did not write configuration.
• Registered using the printed code --add-mcp form; resulting user configuration: %APPDATA%\Code\User\mcp.json.
• Actual running package: %LOCALAPPDATA%\npm-cache\_npx\3ec5bc0582433d0b\node_modules\sentinel-ir-mcp\package.json → 0.5.9. Both Node versions used this published npm cache installation.

VS Code's generated entry:

{"type":"stdio","command":"npx","args":["-y","sentinel-ir-mcp@stable-0.5","C:\\t\\Projekt Žluťoučký kůň\\app"]} 

For Cline and Inspector, copied the Windows JSON-client form confirmed by setup --client claude-desktop --project "<project>" --config <temporary-file> --dry-run:

{"command":"cmd","args":["/c","npx","-y","sentinel-ir-mcp@stable-0.5","C:\\t\\Projekt Žluťoučký kůň\\app"]} 

Verified results

Inspector calls: entered absolute Czech/spaced paths through visible tool forms and clicked Execute Tool.

• analyze_file on ...\src\index.js: OK, 75 ms in result pane; analysisStatus: complete, language: javascript, risk: medium, filesystem and network recognized (fs.readFileSync, https.get).
• analyze_directory on project root: OK, 39 ms; 4 analyzed, 4 complete, 0 incomplete, no timeout/truncation; Rust/Python critical (process spawning), index.js medium, util.js low.

Protocol monitoring panel separately displayed approximately 73 ms / 34 ms for those calls. No CLI/SDK call is being presented as GUI coverage.

Visual evidence

VS Code Node 22 — running	Cline — connected and tools

Inspector fallback — file result	Inspector fallback — directory result

🔴 VS Code session entry — Error	🟢 Same runtime, local entry — Running / 3 tools

Failure evidence and limitations

• Exact working route after relaunch: MCP: List Servers → Show locally configured servers… → sentinel-ir (Global in Code) → Start Server.
• Session-bound failure output file was empty. Full failure-time logs are preserved in vscode-node24-failure-logs; focused renderer.log, exthost.log and full subsequent local MCP log are also supplied in windows-mcp-logs.zip.
• Generated npx and alternate npx.cmd both work locally; cmd /c npx works in Cline and Inspector. The session-bound entry was not fully retested with every command variant. Switching to the local surface resolved startup without any command change.
• Desktop analysis calls, account-policy root cause, and Node 24 analysis calls: untested. Inspector demonstrates server tools, not desktop model orchestration. No claim that Copilot model usage works without sign-in.
• No source-code, repository, or MR changes. No unit-test results substituted for runtime coverage.
• Recording required recovery after an unfinalized MP4 stop. The supplied condensed video is reconstructed from the original desktop H.264 frames, with idle sections removed, two labeled portions at 2× speed, and explanatory overlays; it is not a second test run. Screenshots/logs are the primary evidence.

Facts vs interpretation: successful local launches and Inspector tool responses are observed facts. Session/policy routing is the best-supported explanation for the failed entry; these tests do not establish which VS Code setting or sign-in would repair that session-bound route. No Sentinel launch failure was observed on the functioning local/client routes.

Independent Engineering Projects

Built as independent engineering experiments across AI, software analysis, security, and autonomous systems.

Evaluated by reproducible evidence, not by the number of layers.

Explore the projects:

Sentinel Ecosystem: AutoDoc-Sentinel, Sentinel-IR, Sentinel-IR-MCP and related tools.
Agentix Lite: Independent security and system-observation project.
Find the projects: GitLab repositories | NPM packages

Support the work: ⭐ Star the repositories on GitLab.

Connect: Follow me here on DEV Community or explore the Playground.

Each project is distributed under its own license. Check the corresponding repository or NPM package for licensing terms.

Copyright © 2026 jackymenCZ. All rights reserved. Written for the community.