LinkedIn MCP Server

Instructions

Implementation Reference

• src/index.ts:884-909 (handler)

  The handler function that implements the core logic of the 'search_posts' tool. It builds request parameters from input args, calls the '/post-search' API endpoint, cleans the post data using DataCleaners.cleanPost, applies max_items limit, and returns formatted response with pagination.
  private async searchPosts(args: Record<string, any>): Promise<CallToolResult> { const params: Record<string, any> = {}; if (args.search) params.search = args.search; if (args.profile) params.profile = args.profile; if (args.profileId) params.profileId = args.profileId; if (args.company) params.company = args.company; if (args.companyId) params.companyId = args.companyId; if (args.authorsCompany) params.authorsCompany = args.authorsCompany; if (args.authorsCompanyId) params.authorsCompanyId = args.authorsCompanyId; if (args.group) params.group = args.group; if (args.postedLimit) params.postedLimit = args.postedLimit; if (args.sortBy) params.sortBy = args.sortBy; if (args.page) params.page = args.page; if (args.paginationToken) params.paginationToken = args.paginationToken; const data = await this.makeRequest('/post-search', params); const maxItems = args.max_items || 10; const cleaned = (data.elements || []).slice(0, maxItems).map(DataCleaners.cleanPost); return this.formatResponse(cleaned, { saveDir: args.save_dir, toolName: 'search_posts', pagination: data.pagination, }); }
• src/index.ts:430-453 (registration)

  Registration of the 'search_posts' tool in the ListToolsRequestSchema handler, defining name, description, and input schema.
  { name: 'search_posts', description: 'Search LinkedIn posts. Returns cleaned data in TOON format.', inputSchema: { type: 'object', properties: { search: { type: 'string', description: 'Keywords to search' }, profile: { type: 'string', description: 'Filter by author profile URL' }, profileId: { type: 'string', description: 'Filter by author profile ID' }, company: { type: 'string', description: 'Filter by company name' }, companyId: { type: 'string', description: 'Filter by company ID' }, authorsCompany: { type: 'string', description: 'Search posts from employees of a company' }, authorsCompanyId: { type: 'string', description: 'Filter by company ID of post authors' }, group: { type: 'string', description: 'Filter by group name' }, postedLimit: { type: 'string', description: 'Filter by time: 24h, week, month', enum: ['24h', 'week', 'month'] }, sortBy: { type: 'string', description: 'Sort by: relevance or date', enum: ['relevance', 'date'] }, page: { type: 'integer', description: 'Page number', default: 1 }, paginationToken: { type: 'string', description: 'Pagination token' }, save_dir: { type: 'string', description: 'Directory to save cleaned JSON data' }, max_items: { type: 'integer', description: 'Maximum results (default: 10)', default: 10 }, }, required: [], }, } as Tool,
• src/index.ts:433-452 (schema)

  Input schema definition for the 'search_posts' tool, specifying parameters for search query, filters, pagination, and optional save options.
  inputSchema: { type: 'object', properties: { search: { type: 'string', description: 'Keywords to search' }, profile: { type: 'string', description: 'Filter by author profile URL' }, profileId: { type: 'string', description: 'Filter by author profile ID' }, company: { type: 'string', description: 'Filter by company name' }, companyId: { type: 'string', description: 'Filter by company ID' }, authorsCompany: { type: 'string', description: 'Search posts from employees of a company' }, authorsCompanyId: { type: 'string', description: 'Filter by company ID of post authors' }, group: { type: 'string', description: 'Filter by group name' }, postedLimit: { type: 'string', description: 'Filter by time: 24h, week, month', enum: ['24h', 'week', 'month'] }, sortBy: { type: 'string', description: 'Sort by: relevance or date', enum: ['relevance', 'date'] }, page: { type: 'integer', description: 'Page number', default: 1 }, paginationToken: { type: 'string', description: 'Pagination token' }, save_dir: { type: 'string', description: 'Directory to save cleaned JSON data' }, max_items: { type: 'integer', description: 'Maximum results (default: 10)', default: 10 }, }, required: [], },
• src/index.ts:132-147 (helper)

  Helper function in DataCleaners that processes and cleans raw post data from the API response, extracting key fields like content, author, engagement metrics, used in searchPosts handler.
  cleanPost(raw: any): any { if (!raw) return null; return { id: raw.id, linkedinUrl: raw.linkedinUrl, content: raw.content, authorName: raw.author?.name, authorType: raw.author?.type, postedAgo: raw.postedAt?.postedAgoText || raw.postedAt?.postedAgoShort, likes: raw.engagement?.likes, comments: raw.engagement?.comments, shares: raw.engagement?.shares, hasVideo: !!raw.postVideo, hasImages: (raw.postImages?.length || 0) > 0, }; },
• src/index.ts:545-545 (registration)

  Switch case in CallToolRequestSchema handler that routes calls to the 'search_posts' tool to its handler method.
  case 'search_posts': return await this.searchPosts(args as Record<string, any>);