1. Conduid
  2. Files
  3. io.github.willa-code/visual-intent-layer
MCP server · Files

io.github.willa-code/visual-intent-layer

Point at visible targets in an agent-built interface, and deliver grounded Annotations.

Unclaimed files
37Low

Scored a month ago · breakdown

About io.github.willa-code/visual-intent-layer

io.github.willa-code/visual-intent-layer is an MCP server published by willa-code in the Files category: point at visible targets in an agent-built interface, and deliver grounded Annotations.

Recent commit activity is the strongest signal that reported issues will get attention.

Install

Claude Code
claude mcp add io-github-willa-code-visual-intent-layer -- npx -y visual-intent-layer
npx
npx -y visual-intent-layer

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Ask AI

✦

Ask AI about io.github.willa-code/visual-intent-layer

Powered by Claude · Grounded in docs

I know everything about io.github.willa-code/visual-intent-layer. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

6 checks have not been run yet.

Releases

v0.4.0Visual Intent Layer 0.4.0 · 20 Sep 2026Two features and nine fixes since 0.3.2, plus the repository's first LICENSE file. Features The surface is grounded in what you pointed at. Rows and records now carry the words you selected, the rectangle you drew and the element you…
v0.3.2Visual Intent Layer 0.3.2 · 18 Sep 2026The published package now carries the front door and the manual. The npm page is a front door, and the manual ships with it The README was both the front door and the whole product manual — 337 lines, where someone registering the server…
v0.3.1v0.3.1 — a relation drag that survives the rail taking focus · 18 Sep 2026What was wrong A relation drag could be silently dropped. On a busy machine, the rail re-renders the Annotation card shortly after you select a target, and that render moves focus into the card's note field. The artifact frame lost focus,…
v0.3.00.3.0 · 18 Sep 2026The Annotation is the unit of work 0.3.0 rebuilds the Review Surface around durable Annotations. A Builder-Reviewer points at visible targets, writes a note on each, and sends them as one versioned Visual Intent Envelope. Each…
v0.2.1v0.2.1 — Fix packaged snippet version pin · 15 Sep 2026Full Changelog: https://github.com/willa-code/visual-intent-layer/compare/v0.2.0...v0.2.1
Questions

About io.github.willa-code/visual-intent-layer

How do I install io.github.willa-code/visual-intent-layer?

Run claude mcp add io-github-willa-code-visual-intent-layer -- npx -y visual-intent-layer, then add the server to your MCP client's configuration.

Is io.github.willa-code/visual-intent-layer safe to use with an AI agent?

Its trust score is 37 out of 100 (low). Conduid hasn't run static security checks on this repository yet, so review the source yourself before granting it credentials. It has no ConduID identity yet, so agent calls to it are not receipted.

Is io.github.willa-code/visual-intent-layer still maintained?

Yes — the latest release is v0.4.0 (20 Sep 2026), and the last commit was a month ago. The repository has 0 stars.