Anti-Vibe
NPM · ANTI-VIBE-MCP
Read coding-agent output one sentence at a time, skim it by heading, or speed-read it.
Available components
Last scanned (4 hours ago)
Scores higher than 38% of npm servers
Category Developer Tools
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security98
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- No install/post-install scripts declared.Pass
- 60 of 159 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 8 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability66
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 881 tokens (~293/item across 3 items; 3 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management0
- Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
- Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety75
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "rsvpify_markdown" implies "send" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
- An AI judge read all 3 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Unverified: 1 category
A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 14 Oct 26 +29
- Injection markers: unverified → pass ▲ security
- First check of Judged manipulation: pass security
- Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window). security
- Tool coverage: unverified → 100 ▲ functional
- MCP protocol: unverified → pass ▲ functional
- First check of Schema quality: fail functional
- First check of Schema quality: excellent functional
- First check of Schema quality: fail functional
- First check of Destructive annotations: 0 functional
- First check of Tool coverage: 100 functional
- First check of Tool coverage: 100 functional
- 13 Oct 26 0
- Security disclosure: unverified → fail ▼ functional
- 12 Oct 26 +15
- Malware scan: unverified → pass ▲ security
- Known CVEs: partial → pass ▲ security
- Security disclosure: fail → unverified ▼ functional
- Dependency health: partial → 0.80 functional
- 9 Oct 26 23
First indexed and scored.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 17 Oct 2026 · Analysed npm/anti-vibe-mcp@0.4.7
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | npm |
Background: How many MCP packages publish verified provenance →
Dependencies 159 packages
| Packages resolved | 159 |
|---|---|
| Stale | 60 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
review_flow Send a flow-ordered code review to Anti-Vibe ~331
Push a FLOW-ORDERED code review to Anti-Vibe: the human walks the change in runtime execution order (like a sequence diagram), not file-by-file. Send ONLY the traversal STRUCTURE — never the diff text. Anti-Vibe resolves each hunk by running `git diff` in the repo and matching your locators. Order `flow` stops top→bottom in call order (entry → handler → service → effect); put models/schemas/contracts/types in `foundation` and list them bottom→up. Each stop maps to a FILE — the reviewer steps through all of that file's hunks one at a time. `locator` is an OPTIONAL hint (exact `hunkHeader` "@@ -a,b +c,d @@ ..." or `lineRange`) that just sets the match-confidence badge. Give each stop a one-line summary. For unchanged connective steps (a dispatcher/existing handler the flow passes through), add a stop with `context: true` and no locator so the sequence reads continuously. When a stop's file has several hunks, add `hunkFlow` to order them for reading in execution order (behavior change before plumbing) with a one-line note per hunk.
| Name | Type | Req | Description |
|---|---|---|---|
| diffBase | string | – | git diff base, e.g. "HEAD~1" or "main...HEAD" (default: working tree). |
| repoPath | string | – | Repo to run git diff in (defaults to ANTIVIBE_REPO_DIR or cwd). |
| stops | array | yes | Ordered traversal of the review. |
| title | string | – | Title for the review. |
| Name | Type | Req | Description |
|---|---|---|---|
| documentId | string | yes | – |
| resolvedCount | number | yes | – |
| stopCount | number | yes | – |
| url | string | yes | – |
No examples provided.
review_markdown Send markdown to Anti-Vibe for review ~263
Send markdown to the Anti-Vibe reader so a human can review it without fatigue, moving heading-by-heading and optionally speed-reading each section. Provide your output as well-structured Markdown — use `#`/`##`/`###` headings to break it into sections (Anti-Vibe navigates by heading), plus normal Markdown for lists, tables, code blocks and emphasis. Pass the full content in `markdown`. For CODE REVIEW / diff content: one `###` heading per file, and NEVER paste a whole file or diff as a single fenced block — each fenced block is one atomic step in the reader, so an oversized block becomes an unreviewable wall. Split code into small fenced blocks (one function or one logical hunk, ~15 lines each) and precede each block with one line of prose saying WHY that piece exists. This applies doubly to NEW files: present them one function/section at a time, never verbatim top-to-bottom. Opens the Anti-Vibe tab on first use and live-updates it on later calls.
| Name | Type | Req | Description |
|---|---|---|---|
| markdown | string | yes | The full document as Markdown, ideally with #/## headings. |
| title | string | – | Optional title; used as an H1 if the markdown has none. |
| Name | Type | Req | Description |
|---|---|---|---|
| documentId | string | yes | – |
| sectionCount | number | yes | – |
| url | string | yes | – |
| wordCount | number | yes | – |
No examples provided.
rsvpify_markdown Rewrite agent output as RSVP prose and send to Anti-Vibe ~287
Send an agent response to the Anti-Vibe reader OPTIMIZED for RSVP speed-reading, where one word is flashed at a time. Because raw agent output reads badly word-by-word, YOU must rewrite the content before passing it in `markdown`: (1) Rephrase into flowing, natural prose — full sentences, minimal symbols, no bullet fragments or telegraphic notes; write it as if it were read aloud. (2) Replace every code block with a short PROSE SUMMARY of what the code does (e.g. "A function that validates the token expiry using a strict less-than check."). Do not paste raw code into the prose — summarize it. (3) Keep `#`/`##` headings as the section spine. (4) When a TABLE or other structured element is essential to keep verbatim, include it as a normal Markdown table/code block — Anti-Vibe renders these as atomic blocks and AUTO-PAUSES the RSVP stream on them so the reader stops and studies them, then resumes. Use this tool for content a human will speed-read; use `review_markdown` to preserve the original code and structure verbatim.
| Name | Type | Req | Description |
|---|---|---|---|
| markdown | string | yes | Your rewritten prose: natural sentences, code replaced by summaries, tables kept verbatim. |
| title | string | – | Optional title; used as an H1 if the prose has none. |
| Name | Type | Req | Description |
|---|---|---|---|
| documentId | string | yes | – |
| sectionCount | number | yes | – |
| url | string | yes | – |
| wordCount | number | yes | – |
No examples provided.
How do I install the Anti-Vibe MCP server?
Anti-Vibe runs locally as an npm package, launched with npx -y anti-vibe-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · anti-vibe-mcp
claude mcp add hellstellar-anti-vibe -- npx -y anti-vibe-mcp
What is the Anti-Vibe MCP server?
Anti-Vibe is an MCP server listed in the public MCP registry as io.github.Hellstellar/anti-vibe. Read coding-agent output one sentence at a time, skim it by heading, or speed-read it. This page covers its npm package (anti-vibe-mcp).
Is the Anti-Vibe MCP server safe to use?
Anti-Vibe scores 67 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 17 October 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the Anti-Vibe MCP server expose?
Anti-Vibe exposes 3 tools: review_markdown, rsvpify_markdown, review_flow. Their descriptions and schemas cost roughly 881 tokens of context every time the server is loaded.
Is the Anti-Vibe MCP server still maintained?
Anti-Vibe is still listed as active in the MCP registry. We last reached this channel on 17 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the Anti-Vibe MCP server under?
Anti-Vibe declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.