Web-LLM Playwright
This MCP server provides browser-based local LLM inference by integrating @mlc-ai/web-llm with Playwright automation, running models entirely in a headless Chromium browser without external API dependencies. Built by ragingwind using TypeScript, it loads Web-LLM from CDN into an HTML interface and exposes programmatic access through browser evaluation, supporting multiple quantized models like Llama-3.2, Phi-3.5, and Mistral with dynamic model switching, chat sessions, and screenshot debugging capabilities. The implementation offers true local inference with no data transmission to external services, making it valuable for privacy-sensitive applications, offline AI workflows, and scenarios requiring local model deployment without complex GPU setup or native runtime dependencies.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-28.
Scan details: Circle-IR · 2026-09-28 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- devops-ci
- Source
- PulseMCP
- Repository
- github.com/ragingwind/web-llm-mcp-server
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve Web-LLM Playwright from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.