> ## Documentation Index > Fetch the complete documentation index at: https://docs.shareofmodel.ai/llms.txt > Use this file to discover all available pages before exploring further. # Get the HTML of a website evaluation result > Return the HTML of a page the GEO audit analysed, as the crawler fetched it: `no_js` is what an AI crawler that does not run JavaScript receives, `js_rendered` the page after its JavaScript ran. Long pages can be read in chunks with `offset` and `limit`, counted in characters; `next_offset` gives the next chunk and is null on the last one. Each result of the audit gives the length of both versions (`no_js_html_chars`, `js_rendered_html_chars`); a null length means no HTML is stored, and this endpoint then returns 404. ## OpenAPI ````yaml https://openapi.shareofmodel.ai/swagger.json get /v1/organizations/{organization_id}/workspaces/{workspace_id}/website_evaluations/{id}/results/{result_id}/html openapi: 3.0.3 info: title: Share Of Model API version: v1 description: >- ## Model Context Protocol (MCP) In addition to this REST API, Share of Model exposes a **Model Context Protocol** server that lets AI assistants (Claude Desktop, Claude Code, MCP Inspector, custom agents…) call our endpoints directly as tools. Any MCP-compatible client can interact with Share of Model without writing custom integration code — connect once with your usual login and start asking the assistant to query the data for you. ### Connecting from Claude Desktop Open **Settings → Connectors**, scroll to the bottom and click **Add custom connector**, then paste `https://mcp.shareofmodel.ai/mcp/`. A browser window opens for you to log in with your Share of Model account (same login as the web app), and the assistant gains access to the tools. ### Connecting from Claude Code ```bash claude mcp add --transport http share-of-model https://mcp.shareofmodel.ai/mcp/ ``` The first time you call a tool, Claude Code opens your browser to complete the login. ### Connecting from MCP Inspector ```bash npx @modelcontextprotocol/inspector ``` In the Inspector UI, pick **Streamable HTTP** as transport, paste `https://mcp.shareofmodel.ai/mcp/`, and click **Connect**. The first connection prompts you to log in. ### Available tools Every read-only (`GET`) endpoint of this specification and of the Search API specification is exposed as an MCP tool, except account administration (API keys, platform integrations and accounts, user roles, favourites, SSO and SCIM). Write endpoints are exposed only when they are marked for agents: creating and pricing brand analyses, Search analyses and GEO audits, creating personas, and managing asset evaluations. Write tools act with the role of the signed-in user, so creating requires the Organization Editor or Owner role, or Workspace Editor in the target workspace. Before creating an analysis or a GEO audit, the assistant shows the full setup and its cost and waits for an explicit confirmation. ### Example prompts Once connected, try asking your assistant things like: - _"List the workspaces I have access to."_ - _"Show me the latest searches in workspace X."_ - _"Compare the share of model between brand A and brand B over the last 30 days."_ - _"Set up a brand analysis for brand A in France."_ For more details on the protocol itself, see the [Model Context Protocol specification](https://modelcontextprotocol.io/). servers: - description: Production API url: https://api.shareofmodel.ai/ - description: Development API url: https://api.dev.shareofmodel.ai/ security: [] tags: - name: Auth description: Endpoints needed for API authentication. - name: Organizations description: Endpoints related to organizations, to list all available organizations. - name: Workspaces description: Endpoints related to workspaces, to list all available workspaces. - name: Analyses description: Endpoints related to analyses and analyses management. - name: Asset Evaluations description: Endpoints related to assets and asset evaluations. - name: Brand Catalog description: Endpoints related to general brand information. - name: Content Briefs description: Endpoints related to content briefs generation and optimisation. - name: Metrics description: >+ Endpoints related to brand metrics. **LEXICON** **Brand Awareness**: What opinion the LLMs have concerning specific brands, related to certain categories. **Brand Perception**: The general sentiment of the LLMs towards a brand, based on the pros and cons they mention. paths: /v1/organizations/{organization_id}/workspaces/{workspace_id}/website_evaluations/{id}/results/{result_id}/html: get: tags: - Website Evaluation summary: Get the HTML of a website evaluation result description: >- Return the HTML of a page the GEO audit analysed, as the crawler fetched it: `no_js` is what an AI crawler that does not run JavaScript receives, `js_rendered` the page after its JavaScript ran. Long pages can be read in chunks with `offset` and `limit`, counted in characters; `next_offset` gives the next chunk and is null on the last one. Each result of the audit gives the length of both versions (`no_js_html_chars`, `js_rendered_html_chars`); a null length means no HTML is stored, and this endpoint then returns 404. operationId: get_website_evaluation_result_html parameters: - in: query name: html_type schema: enum: - no_js - js_rendered type: string x-spec-enum-id: 123a7ad4b463dc50 minLength: 1 description: >- `no_js`: the HTML as served, without running JavaScript, which is what most AI crawlers receive. `js_rendered`: the HTML after the page's JavaScript ran in a browser. * `no_js` - no_js * `js_rendered` - js_rendered required: true - in: path name: id schema: type: string format: uuid description: A UUID string identifying this website evaluation. required: true - in: query name: limit schema: type: integer minimum: 1 description: >- Return at most this many characters. Without it, the page is returned from `offset` to its end. Pages over 50,000 characters are too large for most agents to read at once. - in: query name: offset schema: type: integer minimum: 0 default: 0 description: >- First character to return. Use the `next_offset` of the previous chunk. - in: path name: organization_id schema: type: string format: uuid description: A UUID string identifying the organization. required: true - in: path name: result_id schema: type: string format: uuid description: A UUID string identifying the website evaluation result. required: true - in: path name: workspace_id schema: type: string format: uuid description: A UUID string identifying the workspace. required: true responses: '200': content: application/json: schema: $ref: '#/components/schemas/WebsiteEvaluationResultHtml' description: '' '400': description: Missing or invalid `html_type`, `offset` or `limit`. '404': description: Audit or result not found, or no HTML of this type is stored. security: - Bearer: [] components: schemas: WebsiteEvaluationResultHtml: type: object properties: html_type: enum: - no_js - js_rendered type: string description: |- * `no_js` - no_js * `js_rendered` - js_rendered x-spec-enum-id: 123a7ad4b463dc50 total_chars: type: integer description: Length of the whole page, in characters. offset: type: integer description: Position of the first character of `content` in the page. next_offset: type: integer nullable: true description: The `offset` that reads the next chunk; null on the last chunk. content: type: string description: The HTML from `offset`, at most `limit` characters. required: - content - html_type - next_offset - offset - total_chars securitySchemes: Bearer: type: apiKey in: header name: Authorization ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.