Anti-Vibe MCP server
io.github.Hellstellar/anti-vibe·v0.4.7Read coding-agent output one sentence at a time, skim it by heading, or speed-read it.
0 stars417 downloads/wk
Reviews
Write oneNobody has reviewed Anti-Vibe yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Anti-Vibe tools (3)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
review_flowreview_markdownrsvpify_markdown
Public scan report
scanner v0.1.10 · 2026-10-13 · same rubric, same numbers if you re-run it
- Code scan69 source files scanned25/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitylocal package, no credentials required12/15
- Maintenancelast push 6 days ago15/15
- Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
How Anti-Vibe compares
Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 92/100
- higher than 90% of 4,460 AI and agents servers
- Tools
- 3
- the typical AI and agents server has 6
- Tools that change things
- 0%
- typical: 0%. Fewer write tools means less an agent can break
- Downloads a week
- 417
- more than 84% of 1,538 AI and agents servers with a package
What its tools let an agent do: 3 read
Install Anti-Vibe in Claude Code, Cursor or VS Code
Runs npx -y anti-vibe-mcp on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add anti-vibe -- npx -y anti-vibe-mcp
What the publisher says
From the Anti-Vibe repository's README, as published. We do not edit it. Read it on GitHub
Anti-Vibe
Your agent wrote 800 lines in 4 seconds. You read 6 of them and hit "Approve." Be honest.
▸ Live at anti-vibe.pages.dev (paste any markdown, no install)
Add it to Claude Code:
claude mcp add anti-vibe -- npx -y anti-vibe-mcpThen ask your agent to "send this to Anti-Vibe". For other MCP clients, see MCP server.
"Vibe coding" is letting the AI cook and merging whatever it hands back on faith. Fun, fast, and a great way to ship a bug you'll spend Saturday debugging. Anti-Vibe is the retro-cyberpunk reader for people who actually read the diff — LLM / agent output, reviewed section by section without the fatigue that makes you give up and click "Approve" at line 6.
Read it one sentence at a time: each sentence, list item, or table row alone on the screen, with everything else out of sight. Skim by heading and skip what doesn't matter. Speed-read it when you're in a hurry. No wall of text to bounce off.
Full disclosure: yes, a tool for not vibe coding is itself vibe coded — for now. The irony is not lost on us; we're firing shots from inside the glass house. The plan is to close the loop and use Anti-Vibe on its own source until it's earned its way out of "vibe coded" and into "actually reviewed."
Why
LLMs and agents generate walls of text faster than any human can read them, and the cost of reviewing it is real — not just the time. This app attacks that cost from several sides:
- Less reading fatigue — one sentence at a time means there's no wall of text to scan, and the reading view's top/bottom fade keeps the focus on the middle of the screen, easing the load.
- Lower inertia to review — section-by-section navigation means you commit to one small chunk at a time instead of facing the whole document. Glance at a heading, decide, skip it or speed-read it.
- Faster review — opt-in RSVP blasts through the sections worth reading at your target WPM; review keeps pace with how much AI output you now generate.
- Less screen time — faster, gentler review means fewer hours staring at walls of text.
- Easier to focus (great for ADHD) — one word, one sentence, or one section at a time, fixed in place, with everything else dimmed away. By removing the wall of text — and any progress counter or sense of how much is left — Anti-Vibe keeps attention on the single thing in front of you, which can make focusing and starting far easier for ADHD and other attention/focus challenges.
The goal is review tooling that's easier on your eyes and attention, not only quicker — a focus and wellbeing angle baked into a speed tool. See docs/VISION.md for where it could go.
Screenshots
Shown in the Cream theme (warm, soft, left-aligned prose). There's also a CRT theme — dark, pixel, scanlines — if you want your code review to feel like it's coming from a 1983 terminal.
Landing — paste or open a .md file
Reading view — a section with a top/bottom fade
One sentence at a time — step through a section, one unit on screen
Speed-read (RSVP) — one word at a time, ORP pivot accented
Features
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Anti-Vibe: common questions
- Is Anti-Vibe MCP server safe?
- Yes, by our scan: it is graded A (92/100). Read the Anti-Vibe safety report
- How do I install Anti-Vibe?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does Anti-Vibe need an API key?
- No secret keys are declared. It reads 1 setting from the environment.
- Is Anti-Vibe maintained?
- The last commit was 27 days ago (2026-10-08). The latest release is v0.4.7.
- What can I use instead of Anti-Vibe?
- Servers from other publishers that do the same job: Serena MCP: the IDE for your agent MCP server, Figma Context MCP server and SuperCompress MCP server.
- How does Anti-Vibe compare with other AI and agents MCP servers?
- safety score 92/100 (higher than 90% of 4,460 AI and agents servers); tools 3 (the typical AI and agents server has 6); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.
Alternatives to Anti-Vibe
Same job from other publishers: the closest match first, then the best rated.
- Serena MCP: the IDE for your agentA powerful toolkit for coding, providing semantic retrieval and editing capabilities.not reviewedWidely usedC
- Figma ContextGive your coding agent access to your Figma data. Implement designs in any framework in one-shot.not reviewedWidely usedB
- SuperCompressCompress coding-agent context ~64%. Hosted Neural Keep MCP for Cursor/Claude/Codex.not reviewedEstablishedB
- OrcareplayRead, replay and fork recorded coding-agent runs.not reviewedEstablishedA
- llmtrimMCP server and proxy that compresses LLM prompts, tool output, and replies to cut token cost.not reviewedEstablishedA