Read blog post
Read bounded structured content from the current published article.
Availability
This tool runs through browser WebMCP on a GoVisit page that registers get_blog_post. It needs that page’s published context; it has no stateless HTTP endpoint or generated Agent Skill.
Call in a compatible browser
const modelContext = document.modelContext;
if (!modelContext) throw new Error("This browser does not expose WebMCP on this page.");
const tool = (await modelContext.getTools()).find((entry) => entry.name === 'get_blog_post');
if (!tool) throw new Error('get_blog_post is not registered for the current page.');
const result = await modelContext.executeTool(tool, {});
console.log(result);
Registration is page-scoped; the exact URL patterns below the contract are generated from the catalog. Check getTools() before calling.
Input and output contract
Input schema
{
"type": "object",
"properties": {
"section": {
"type": "string",
"minLength": 1,
"maxLength": 200,
"description": "Optional heading anchor identifying one published section."
}
},
"additionalProperties": false
}Output schema
{
"type": "object",
"properties": {
"data": {
"type": "object",
"properties": {
"content": {
"type": "array"
},
"truncated": {
"type": "boolean"
}
},
"required": [
"content",
"truncated"
]
}
},
"required": [
"data"
]
}The schemas above are rendered server-side from config/webmcp-tools.json, the canonical reviewed tool catalog. The WebMCP manifest also publishes the machine-readable contract; native RegisteredTool entries advertise an output-contract URL because that interface does not provide an inline outputSchema field.
Interpretation limits
The reader inspects only the currently rendered blog post. It does not fetch other articles; a selected section uses its heading anchor and may report truncation.
For the full current contract and linked context, see the WebMCP manifest and the WebMCP overview.