MCP.Market

Anylens MCP server

by Slowper·io.github.Slowper/anylens·v0.5.3
No reviews yet

Turn videos, PDFs, screenshots, and articles into anchored, cached understanding for agents.

A88/100grade A
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
A88/100

full report

Adoption
New

0 stars30 downloads/wk

Reviews

Write one

Nobody has reviewed Anylens yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Anylens tools (11)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • analyze

    Analyze a URL — video, audio, PDF (incl. scanned/figure-heavy via vision), web article, or image — into a cached Understanding Object. Returns a job id to poll with `status` — or the finished summary instantly when the URL was analyzed before.

  • ask

    Ask one question about an already-analyzed source. Answers come only from the cached analysis, with anchors — and say plainly when the source does not answer the question. No re-analysis, so it is fast and cheap; answers are cached per question.

  • audio

    Narrate a lens render to an mp3 — listen instead of reading or watching. Uses the offline system voice (macOS), and strips timestamps, diagrams, and markdown so the script actually sounds like prose.

  • clip

    Cut the segment of a video/audio source that matches a plain-language query ("the part where they explain attention"). Downloads only those seconds, so it is fast even on long sources. Returns the clip file path plus a deep link. Refuses rather than guessing when the source does not contain it.

  • export

    Export a lens render: markdown (Obsidian-ready, with frontmatter), anki (TSV flashcard deck — needs the student lens), json (full contract), or html (self-contained page). Writes the file and returns its path; small files also come back inline.

  • lens

    Render a cached Understanding Object through a lens (see `lenses` for the catalog; "raw" returns the object itself, no LLM). Returns { data, markdown } — structured for agents, readable for humans; include_html adds a self-contained explainer page. Optional focusing question. Renders are cached.

  • lenses

    List available lens profiles (name, title, when to use, audience).

  • status

    Poll an analyze job. Long-polls up to wait_seconds; returns the finished summary (with source_id) when done. While running, reports elapsed seconds and the stage history so you can see where the time goes.

  • style_apply

    Apply a saved style to NEW work: pass a brief to get a production plan (beat table, audio direction, shot-level prompts) in that style, or content to have it reshaped. Returns { markdown, data } plus an explicit list of rules it could not follow.

  • style_extract

    Learn a reusable style from one or more already-analysed sources and save it as a named pack. More sources means genre norms rather than one piece's choices. Sources need the production pass (analyze with include_production).

  • style_list

    List saved style packs — reusable craft learned from analysed sources (pacing, structure, motion, audio, typography rules), each rule traced to the sources it came from.

Public scan report

scanner v0.1.9 · 2026-09-24 · same rubric, same numbers if you re-run it

no findings
  • Code scan65 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 48 days ago12/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 88/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Anylens compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
88/100
higher than 75% of 48,255 servers
Tools
11
the typical server has 7
Tools that change things
0%
typical: 0%. Fewer write tools means less an agent can break
Downloads a week
30
more than 18% of 12,191 servers with a package

What its tools let an agent do: 11 read

Install Anylens in Claude Code, Cursor or VS Code

Runs npx -y anylens on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add anylens -- npx -y anylens
Add to Cursor

What the publisher says

From the Anylens repository's README, as published. We do not edit it. Read it on GitHub

anylens

Any link, any lens. Paste a URL — a conference talk, a product demo, a dense PDF, an article — and get it back as understanding shaped for who's asking, with every claim linked to the exact second or page it came from.

Agents can read text. anylens lets them read everything else — and lets you check their work.

analyze(url)  →  one cached Understanding  →  lens(source, "student")
                                           →  lens(source, "spec")
                                           →  lens(source, "uiux")   …

Why not just ask a chatbot to summarize it?

A summary is a dead end. You can't verify it, you can't get a different cut of it without paying for it again, it's blind to what was on screen, and no agent can act on it. anylens fixes those four things:

blurred with inferred. Missing analysis is named, not hidden.

  • Verifiable — every claim carries its timestamp or page. stated is never

forever; a second lens is cheap and instant.

  • Many readers, one extraction — the expensive pass runs once and is cached

just the words. A silent ten-second screen recording still produces a full analysis.

  • Reads what was shown*** — on-screen code, slides, UI states, demos, not

implementable requirements with acceptance criteria, over MCP.

  • Built for agents too — the spec lens turns any source into

the sound design, the shot rhythm, the motion and typography, and turns it into a recipe you (or a generator) can rebuild from. Content lenses let an agent know; the blueprint lens lets it make.

  • Knows how it was made — for video, a production pass captures the music,

Lenses

Lenses are single markdown files in src/lenses/. Adding one is adding a file — no code.

Beyond lenses: anylens can learn a reusable style from analyzed videos — the pacing, structure, look, motion, and sound as portable rules, every rule carrying the timestamp it was learned from — then plan new work in that style (styleextract / styleapply over MCP, or "Learn this style" in the web UI).

Quickstart

Prerequisites: Bun 1.3+, yt-dlp, and ffmpeg (brew install yt-dlp ffmpeg on macOS).

git clone https://github.com/Slowper/anylens && cd anylens
bun install

Keys — run bun run web and paste them on the Your keys page (they're validated as you save), or create ~/.anylens/env (mode 600) yourself:

GOOGLE_API_KEY=...      # required: analysis, structuring, lens rendering
GROQ_API_KEY=...        # optional: Whisper transcripts for sources without captions
ANTHROPIC_API_KEY=...   # optional: run the writing on Claude instead
OPENAI_API_KEY=...      # optional: run the writing on an OpenAI model instead

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Anylens: common questions

Is Anylens MCP server safe?
Yes, by our scan: it is graded A (88/100). Read the Anylens safety report
How do I install Anylens?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Anylens need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Anylens maintained?
The last commit was 89 days ago (2026-08-07). The latest release is v0.5.3.
How does Anylens compare with other MCP servers?
safety score 88/100 (higher than 75% of 48,255 servers); tools 11 (the typical server has 7); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.