Connect via MCP
This site supports WebMCP, which means your AI agent can interact with it directly. Search posts, read content, and explore the blog without screenshots or scraping.
How to Connect
1. Install the WebMCP MCP server
Run this in your terminal (picks up your MCP client automatically):
npx -y @jason.today/webmcp@latest --config claude
Replace claude with cursor etc if you use a different client.
2. Generate a token
Either:
- Ask Cursor: "Generate a WebMCP token"
- Or run:
npx @jason.today/webmcp --new
npx @jason.today/webmcp --new
3. Paste the token
Visit brighterwebsites.com.au/mcp/, click the coloured square (bottom right), paste the token.
Once connected, your agent has access to the tools below.
4. Restart Claude/Cursor if needed so it picks up the new MCP server.
5. Test in Cursor chat. Try prompts like:
Available Tools
search_content
Search service pages, case studies, and articles by keyword.
Optionally filter by
content type (purpose: service-page, pillar, case-study, etc.) or
search intent (intent: informational, commercial, transact_lead, trust).
Optionally filter by
content type (purpose: service-page, pillar, case-study, etc.) or
search intent (intent: informational, commercial, transact_lead, trust).
list_content
List all published content. Filter by purpose or intent to narrow results.
get_content
Get the full text of a page or article by its slug.
Note: pages built with Breakdancereturn a note pointing to the markdown endpoint for full text — use the page URL with Accept: text/markdown instead.
Note: pages built with Breakdancereturn a note pointing to the markdown endpoint for full text — use the page URL with Accept: text/markdown instead.
get_site_info
Get context about Brighter Websites — who we are, what we do, who we serve,
our services and topic areas. Call this first.
our services and topic areas. Call this first.
What is WebMCP?
There are two things called "WebMCP" right now, and they solve the same problem differently.
Used on this site
jasonjmcghee/WebMCP
An open source JavaScript library that lets any website expose MCP tools to AI agents via a local WebSocket bridge. Works today with Claude Desktop, Cursor, and any MCP client. No special browser required.
GitHub · npm
Browser spec
W3C/Chrome WebMCP
A proposed W3C web standard backed by Google Chrome and Microsoft Edge that adds a native navigator.modelContext API to browsers. Currently in early preview behind a flag in Chrome Beta (146+). Not yet in stable browsers.
MCP Spec · W3C ProposalResources
Implemented and adopted from
Agentic Resource Discovery | Suganthan Mohanadasan
How to Make Your Website Agent-Ready | Suganthan Mohanadasan
Implementing WebMCP on your website | Suganthan Mohanadasan