analyze_linkedin_chat
Analyze LinkedIn profiles, content, and network data through conversational queries to extract insights and answer questions about professional connections and activities.
Instructions
Ask questions about the user's LinkedIn profile, content, or network, with support for multi-turn conversations.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | The question or request about LinkedIn data to be analyzed. | |
| conversation_history | No | Optional. Previous messages in the conversation for context. Each message must have 'role' (user/assistant) and 'content' (text). |
Implementation Reference
- cli.js:424-511 (handler)Handler implementation for the 'analyze_linkedin_chat' tool. Validates 'query' (required string) and 'conversation_history' (optional array of messages), proxies the request to the backend API endpoint, and returns the reply text or an error message.
} else if (name === 'analyze_linkedin_chat') { console.error(`${packageName}: Received call for analyze_linkedin_chat tool.`); const apiKey = process.env.LINKEDIN_MCP_API_KEY; const query = args?.query; const conversationHistory = args?.conversation_history || []; if (!apiKey) { sendResponse({ jsonrpc: "2.0", error: { code: -32001, message: "Server Configuration Error: API Key not set." }, id }); return; } if (typeof query !== 'string' || query.trim() === '') { sendResponse({ jsonrpc: "2.0", error: { code: -32602, message: "Invalid arguments: 'query' (string) required." }, id }); return; } if (!Array.isArray(conversationHistory)) { sendResponse({ jsonrpc: "2.0", error: { code: -32602, message: "Invalid arguments: 'conversation_history' must be an array." }, id }); return; } try { const headers = { "Authorization": `Bearer ${apiKey}`, "Content-Type": "application/json", "Accept": "application/json" }; const payload = { "query": query, "conversation_history": conversationHistory }; console.error(`${packageName}: Calling analyze chat API: ${backendAnalyzeChatApiUrl} with payload:`, JSON.stringify(payload, null, 2)); const apiResponse = await axios.post(backendAnalyzeChatApiUrl, payload, { headers, timeout: 60000 }); console.error(`${packageName}: Analyze chat API response status: ${apiResponse.status}`); console.error(`${packageName}: Analyze chat API response data:`, JSON.stringify(apiResponse.data, null, 2)); if (apiResponse.data && apiResponse.data.reply) { sendResponse({ jsonrpc: "2.0", result: { content: [ { type: "text", text: apiResponse.data.reply } ], isError: false }, id }); } else { const errorMessage = apiResponse.data?.error || "Backend API Error (no detail)"; console.error(`${packageName}: Analyze chat API Error: ${errorMessage}`); sendResponse({ jsonrpc: "2.0", result: { content: [ { type: "text", text: `Failed to analyze LinkedIn chat: ${errorMessage}` } ], isError: true }, id }); } } catch (error) { let errorMessage = `Failed to call analyze chat API: ${error.message}`; if (error.response) { // Extract the error message directly from the backend response const backendError = error.response.data?.error || error.response.data?.message; errorMessage = backendError || `Backend API Error (Status ${error.response.status})`; console.error(`${packageName}: Analyze chat API Error Response:`, error.response.data); } else if (error.request) { errorMessage = "No response received from analyze chat API."; } console.error(`${packageName}: ${errorMessage}`); sendResponse({ jsonrpc: "2.0", result: { content: [ { type: "text", text: `Failed to analyze LinkedIn chat: ${errorMessage}` } ], isError: true }, id }); } - cli.js:1271-1301 (schema)Input schema definition for the 'analyze_linkedin_chat' tool, defining the expected parameters: required 'query' string and optional 'conversation_history' array of role/content objects.
name: "analyze_linkedin_chat", description: "Ask questions about the user's LinkedIn profile, content, or network, with support for multi-turn conversations.", inputSchema: { type: "object", properties: { query: { type: "string", description: "The question or request about LinkedIn data to be analyzed." }, conversation_history: { type: "array", description: "Optional. Previous messages in the conversation for context. Each message must have 'role' (user/assistant) and 'content' (text).", items: { type: "object", properties: { role: { type: "string", description: "The sender of the message: 'user' or 'assistant'." }, content: { type: "string", description: "The text content of the message." } }, required: ["role", "content"] } } }, required: ["query"] } }, - cli.js:1181-1373 (registration)The tool is registered by being included in the 'tools/list' response, which lists all available tools with their schemas.
if (method === 'tools/list') { console.error(`${packageName}: Received tools/list request, sending known tool.`); sendResponse({ jsonrpc: "2.0", id: id, result: { tools: [ { name: "publish_linkedin_post", description: "Publish a text post to LinkedIn, optionally including media (images/videos) specified by URL.", inputSchema: { type: "object", properties: { post_text: { type: "string", description: "The text content of the LinkedIn post." }, media: { type: "array", description: "Optional. A list of media items to attach to the post. Each item must have a 'file_url' pointing to a direct image or video URL and a 'filename'.", items: { type: "object", properties: { file_url: { type: "string", description: "A direct URL to the image or video file (e.g., ending in .jpg, .png, .mp4)." }, filename: { type: "string", description: "A filename for the media item (e.g., 'promo_video.mp4')." } }, required: ["file_url", "filename"] } } }, required: ["post_text"] } }, { name: "schedule_linkedin_post", description: "Schedule a text post for LinkedIn at a specific future date and time, optionally including media (images/videos) specified by URL.", inputSchema: { type: "object", properties: { post_text: { type: "string", description: "The text content of the LinkedIn post to be scheduled." }, scheduled_date: { type: "string", description: "The date and time to publish the post, in ISO 8601 format (e.g., '2025-12-31T10:00:00Z' or '2025-12-31T15:30:00+05:30'). Must be in the future." }, media: { type: "array", description: "Optional. A list of media items to attach to the post. Each item must have a 'file_url' pointing to a direct image or video URL and a 'filename'.", items: { type: "object", properties: { file_url: { type: "string", description: "A direct URL to the image or video file (e.g., ending in .jpg, .png, .mp4)." }, filename: { type: "string", description: "A filename for the media item (e.g., 'meeting_notes.mp4')." } }, required: ["file_url", "filename"] } } }, required: ["post_text", "scheduled_date"] } }, { name: "publish_twitter_post", description: "Publish a text post (tweet) to Twitter.", inputSchema: { type: "object", properties: { post_text: { type: "string", description: "The text content of the tweet (maximum 280 characters)." } }, required: ["post_text"] } }, { name: "analyze_linkedin_chat", description: "Ask questions about the user's LinkedIn profile, content, or network, with support for multi-turn conversations.", inputSchema: { type: "object", properties: { query: { type: "string", description: "The question or request about LinkedIn data to be analyzed." }, conversation_history: { type: "array", description: "Optional. Previous messages in the conversation for context. Each message must have 'role' (user/assistant) and 'content' (text).", items: { type: "object", properties: { role: { type: "string", description: "The sender of the message: 'user' or 'assistant'." }, content: { type: "string", description: "The text content of the message." } }, required: ["role", "content"] } } }, required: ["query"] } }, { name: "generate_linkedin_post", description: "Generate three LinkedIn post variants from any content (article, newsletter, notes, etc.) to optimize engagement.", inputSchema: { type: "object", properties: { content: { type: "string", description: "The source content to transform into LinkedIn posts. Can be articles, emails, newsletters, notes, etc." }, content_type: { type: "string", description: "Optional. A short description of the content type (e.g., 'article', 'newsletter', 'notes'). Defaults to 'article'." } }, required: ["content"] } }, { name: "get_linkedin_posts", description: "Retrieve the user's recent LinkedIn posts with engagement metrics.", inputSchema: { type: "object", properties: { limit: { type: "number", description: "Optional. Number of posts to retrieve (1-20). Defaults to 5." } } } }, { name: "get_linkedin_profile", description: "Retrieve the user's LinkedIn profile information including headline, summary, experience, and education.", inputSchema: { type: "object", properties: {} } }, { name: "set_linkedin_url", description: "Set or update the LinkedIn profile URL to analyze. Required before using profile/posts retrieval tools if not set previously.", inputSchema: { type: "object", properties: { linkedin_url: { type: "string", description: "The full LinkedIn profile URL (e.g., https://www.linkedin.com/in/username/)" } }, required: ["linkedin_url"] } }, { name: "refresh_linkedin_profile", description: "Force a refresh of the LinkedIn profile data to update any recent changes.", inputSchema: { type: "object", properties: {} } }, { name: "refresh_linkedin_posts", description: "Force a refresh of LinkedIn posts data to capture recently published content.", inputSchema: { type: "object", properties: {} } } ] } }); - cli.js:14-14 (helper)Backend API endpoint URL used by the analyze_linkedin_chat handler.
const backendAnalyzeChatApiUrl = 'https://ligo.ertiqah.com/api/mcp/analyze-linkedin-chat';