Stylespeak
MCP server and CLI that makes CSS legible to AI agents — explains what applies and why.
Connector by Patrizzos · GitHub account verified by the MCP Registry
Chalk Labs
Need help deploying Stylespeak?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.
npx agentmarket install connector/patrizzos-stylespeak
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.
- Tools
- 1 read · 3 write · 0 delete · 1 not yet classified
- Secrets
- None asked for
- Install scripts
- Not scanned yet
- Runs as
- Node.js package
Tools by what they do 5
Read from the source code; the running server may list different tools.
Read 1 · Look things up without changing anything.
impact_preview
Write 3 · Create, change, send or run things.
live_resolveresolve_stylesstyle_manifest
Not yet classified 1 · We could not tell from the name and description.
trace_property
Files it touches
- Any path the agent passes to its tools
Tools (5)
Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].
impact_previewPredicts the blast radius of a proposed CSS change before it is made. Given a selector, property, and optional new value, returns every competing rule in the codebase that would be affected — showing which selectors will see a different value, which are shielded by higher specificity, which cascade relationships are uncertain, and which downstream rules are affected through CSS variable chains or inheritance. Works without a browser. Use this before making any CSS change to understand the full impact.
live_resolveResolves CSS for a selector by querying a live running browser via Chrome DevTools Protocol (CDP). Returns exact computed styles and every matched rule in cascade order — no static analysis, no heuristics, confidence is always exact. Requires Chrome or any Chromium browser (Edge, Brave, Arc) running with --remote-debugging-port=9222. Use this when you need ground truth. Fall back to resolve_styles when no browser is running.
resolve_stylesResolves what CSS actually applies to a given selector. Returns every property the selector would receive, which rule wins for each property, and which rules were overridden — with confidence levels (certain/likely/possible) since no real DOM is available. Call this before modifying styles for an element to understand the full cascade context first.
style_manifestBuilds a compressed, structured summary of a project's entire CSS knowledge — selectors, properties, variables, competition groups, and risk hotspots — that an agent can load ONCE at the start of a session and keep in context. Use this at the beginning of any CSS editing task to understand the landscape before querying individual selectors. Much faster than running resolve_styles on every selector. Follow up with resolve_styles, trace_property, or impact_preview for deep analysis of specific selectors surfaced in the manifest.
trace_propertyTraces a CSS property across all provided files — finding every rule that sets it, grouping competing rules that target overlapping selectors, and showing who wins in each group. Use this to understand the blast radius of a property before changing it, or to find out why a property value isn't applying as expected.
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Weekly downloads
- 25
- Last commit
- Oct 10, 2026 (20 days ago)
- Last release
- Aug 1, 2026 (3 months ago)
- Last package publish
- Oct 10, 2026 (20 days ago)
From GitHub (fetched Oct 24, 2026) and the package registry.
Details
- Registry name
io.github.Patrizzos/stylespeak- Version
- 1.2.0
- Auth
- No auth
- Packages
- npm @patrizzos/stylespeak
- License
- MIT
- Repository
- github.com/patrizzos/stylespeak
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
More from Patrizzos
- 0.509score
Envspeak
Patrizzos
MCP server and CLI that resolves config/env-var cascade across.env, docker-compose, and Kubernetes
ConnectorBFreshness: BLocal↓ 10/wkClaude Code +5 - 0.463score
Stylesafe
Patrizzos
MCP server and CLI that catches CSS cascade conflicts and Tailwind utility clashes before they ship.
ConnectorCFreshness: CLocalRead-only↓ 15/wkClaude Code +5
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get Stylespeak running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
Stylespeak MCP server. Agent Mart. https://agentmart.dev/connectors/patrizzos-stylespeak (last updated 2026-10-24)