> ## 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 latest suggestion for a campaign optimization > Retrieve the latest suggestion for a specific campaign optimization. Required permission: `read:analysis`. The response format depends on the Accept header. Supported formats: JSON (default), CSV (Google Ads only), XLSX (TikTok only). **Suggestion Item Structure (Google Ads — `optimization_suggestions.asset_groups.[]`)** Each suggestion item in the array contains: ```json { "keyword": "running shoes for beginners", "suggestion": "add", "keyword_en": "running shoes for beginners", "relevancy_score": 85, "strength": "very_strong", "currently_used_in": 2 } ``` Fields: - `keyword` (string): The search theme text in the campaign language. - `suggestion` (string): Action — `add`, `keep`, or `remove`. - `keyword_en` (string, optional): English translation. Only present when `translate_to_en=true` and language is not English. - `relevancy_score` (int, 0–100): Semantic similarity between the keyword and the asset group. Computed via embedding distance. - `strength` (string): Label derived from the relevancy score — `very_strong` (80–100), `strong` (60–79), `average` (40–59), `weak` (20–39), `very_weak` (0–19). - `currently_used_in` (int, ≥1): Number of asset groups **within this optimization** that include the same keyword. Represents overlap across the selected asset group set, not live Google Ads usage. **Note:** `relevancy_score`, `strength`, and `currently_used_in` are only present for Google Ads suggestions. TikTok suggestions do not include these fields. ## OpenAPI ````yaml https://openapi.shareofmodel.ai/swagger.json get /v1/organizations/{organization_id}/workspaces/{workspace_id}/campaign_optimizations/{campaign_optimization_id}/suggestions 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 Only endpoints tagged `mcp` in this OpenAPI spec are exposed as MCP tools, and only read-only (`GET`) routes are exposed. Everything tagged `mcp` below is callable from any compliant MCP client. ### 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."_ 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}/campaign_optimizations/{campaign_optimization_id}/suggestions: get: tags: - Campaign Optimizations summary: Get the latest suggestion for a campaign optimization description: > Retrieve the latest suggestion for a specific campaign optimization. Required permission: `read:analysis`. The response format depends on the Accept header. Supported formats: JSON (default), CSV (Google Ads only), XLSX (TikTok only). **Suggestion Item Structure (Google Ads — `optimization_suggestions.asset_groups.[]`)** Each suggestion item in the array contains: ```json { "keyword": "running shoes for beginners", "suggestion": "add", "keyword_en": "running shoes for beginners", "relevancy_score": 85, "strength": "very_strong", "currently_used_in": 2 } ``` Fields: - `keyword` (string): The search theme text in the campaign language. - `suggestion` (string): Action — `add`, `keep`, or `remove`. - `keyword_en` (string, optional): English translation. Only present when `translate_to_en=true` and language is not English. - `relevancy_score` (int, 0–100): Semantic similarity between the keyword and the asset group. Computed via embedding distance. - `strength` (string): Label derived from the relevancy score — `very_strong` (80–100), `strong` (60–79), `average` (40–59), `weak` (20–39), `very_weak` (0–19). - `currently_used_in` (int, ≥1): Number of asset groups **within this optimization** that include the same keyword. Represents overlap across the selected asset group set, not live Google Ads usage. **Note:** `relevancy_score`, `strength`, and `currently_used_in` are only present for Google Ads suggestions. TikTok suggestions do not include these fields. operationId: get_suggestions parameters: - in: header name: Accept schema: type: string description: >- Content type for the response. Possible values: 'application/json' (default, returns JSON with suggestion data), 'text/csv' (returns CSV file, Google Ads only), 'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet' (returns XLSX file, TikTok only). - in: path name: campaign_optimization_id schema: type: string required: true - in: query name: format schema: type: string enum: - csv - json - xlsx - in: path name: id schema: type: string format: uuid description: A UUID string identifying the campaign optimization. required: true - in: path name: organization_id schema: type: string required: true - in: query name: translate_to_en schema: type: boolean default: false description: >- If true and campaign language is not English, translates keywords to English and adds keyword_en field. Only applies to JSON responses. - in: path name: workspace_id schema: type: string format: uuid required: true responses: '200': content: application/json: schema: type: array items: $ref: '#/components/schemas/CampaignOptimizationWithSuggestion' text/csv: schema: type: array items: $ref: '#/components/schemas/CampaignOptimizationWithSuggestion' application/vnd.openxmlformats-officedocument.spreadsheetml.sheet: schema: type: array items: $ref: '#/components/schemas/CampaignOptimizationWithSuggestion' description: >- Details of the latest suggestion. Content type depends on Accept header: JSON (application/json), CSV (text/csv, Google Ads only), or XLSX (application/vnd.openxmlformats-officedocument.spreadsheetml.sheet, TikTok only). '400': description: >- Bad request. Returned when: CSV is requested for TikTok platform, XLSX is requested for Google Ads platform, or the Accept header cannot be satisfied. '404': description: Campaign Optimization or suggestion not found. security: - Bearer: [] components: schemas: CampaignOptimizationWithSuggestion: type: object properties: id: type: string format: uuid readOnly: true suggestion: readOnly: true created_at: type: string format: date-time readOnly: true title: Created workspace_id: type: string format: uuid platform_integration_id: type: string format: uuid status: enum: - pending - in_progress - completed - failed - suggestions_applied type: string description: |- * `pending` - pending * `in_progress` - in progress * `completed` - completed * `failed` - failed * `suggestions_applied` - suggestions applied x-spec-enum-id: eae3ee0747a684c4 platform: enum: - google_ads - tiktok type: string description: |- * `google_ads` - google ads * `tiktok` - tiktok x-spec-enum-id: 56e9e914e95b1bf9 campaign: {} language: enum: - ar - da - de - en - es - eu - fi - fil - fr - he - hi - hu - id - it - ja - ko - nl - pl - pt - ro - sv - th - tr - ur - vi - zh - zh-TW - '' type: string description: |- * `ar` - ar * `da` - da * `de` - de * `en` - en * `es` - es * `eu` - eu * `fi` - fi * `fil` - fil * `fr` - fr * `he` - he * `hi` - hi * `hu` - hu * `id` - id * `it` - it * `ja` - ja * `ko` - ko * `nl` - nl * `pl` - pl * `pt` - pt * `ro` - ro * `sv` - sv * `th` - th * `tr` - tr * `ur` - ur * `vi` - vi * `zh` - zh * `zh-TW` - zh TW x-spec-enum-id: eb433b6ba098186f name: type: string maxLength: 255 analysis: type: string format: uuid required: - analysis - campaign - created_at - id - name - platform - platform_integration_id - suggestion - workspace_id securitySchemes: Bearer: type: apiKey in: header name: Authorization ````