Skip to main content
Glama

search_linkedin_users

Find LinkedIn users by applying filters such as name, job title, company, location, industry, education, and keywords to identify relevant professionals.

Instructions

Search for LinkedIn users with various filters like keywords, name, title, company, location etc.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
company_keywordsNoExact word in the company name
countYesMaximum number of results (max 1000)
current_companyNoCompany URN or name
educationNoEducation URN or name
first_nameNoExact first name
industryNoIndustry URN or name
keywordsNoAny keyword for searching in the user page.
last_nameNoExact last name
locationNoLocation name or URN
past_companyNoPast company URN or name
school_keywordsNoExact word in the school name
timeoutNoTimeout in seconds (20-1500)
titleNoExact word in the title

Implementation Reference

  • src/index.ts:173-219 (registration)
    Registration of the 'search_linkedin_users' tool using McpServer.tool(), including inline Zod schema and the full handler function that prepares request data and calls the AnySite API via makeRequest.
    // Register search_linkedin_users tool server.tool( "search_linkedin_users", "Search for LinkedIn users with various filters", { keywords: z.string().optional().describe("Search keywords"), first_name: z.string().optional().describe("First name"), last_name: z.string().optional().describe("Last name"), title: z.string().optional().describe("Job title"), company_keywords: z.string().optional().describe("Company keywords"), count: z.number().default(10).describe("Max results"), timeout: z.number().default(300).describe("Timeout in seconds") }, async ({ keywords, first_name, last_name, title, company_keywords, count, timeout }) => { const requestData: any = { timeout, count }; if (keywords) requestData.keywords = keywords; if (first_name) requestData.first_name = first_name; if (last_name) requestData.last_name = last_name; if (title) requestData.title = title; if (company_keywords) requestData.company_keywords = company_keywords; log("Starting LinkedIn users search with:", JSON.stringify(requestData)); try { const response = await makeRequest(API_CONFIG.ENDPOINTS.SEARCH_USERS, requestData); log(`Search complete, found ${response.length} results`); return { content: [ { type: "text", text: JSON.stringify(response, null, 2) } ] }; } catch (error) { log("LinkedIn search error:", error); return { content: [ { type: "text", text: `LinkedIn search API error: ${formatError(error)}` } ], isError: true }; } } );
  • Handler function that constructs the API request payload from input parameters, calls makeRequest to the /api/linkedin/search/users endpoint, and returns the JSON response or error.
    async ({ keywords, first_name, last_name, title, company_keywords, count, timeout }) => { const requestData: any = { timeout, count }; if (keywords) requestData.keywords = keywords; if (first_name) requestData.first_name = first_name; if (last_name) requestData.last_name = last_name; if (title) requestData.title = title; if (company_keywords) requestData.company_keywords = company_keywords; log("Starting LinkedIn users search with:", JSON.stringify(requestData)); try { const response = await makeRequest(API_CONFIG.ENDPOINTS.SEARCH_USERS, requestData); log(`Search complete, found ${response.length} results`); return { content: [ { type: "text", text: JSON.stringify(response, null, 2) } ] }; } catch (error) { log("LinkedIn search error:", error); return { content: [ { type: "text", text: `LinkedIn search API error: ${formatError(error)}` } ], isError: true }; }
  • Zod input schema defining optional search parameters like keywords, names, title, company_keywords, with defaults for count and timeout.
    { keywords: z.string().optional().describe("Search keywords"), first_name: z.string().optional().describe("First name"), last_name: z.string().optional().describe("Last name"), title: z.string().optional().describe("Job title"), company_keywords: z.string().optional().describe("Company keywords"), count: z.number().default(10).describe("Max results"), timeout: z.number().default(300).describe("Timeout in seconds")
  • API endpoint constant used by the handler: '/api/linkedin/search/users'
    SEARCH_USERS: "/api/linkedin/search/users",
  • makeRequest helper function used by the handler to perform HTTPS POST requests to the AnySite API with authentication.
    const makeRequest = (endpoint: string, data: any, method: string = "POST"): Promise<any> => { return new Promise((resolve, reject) => { const url = new URL(endpoint, API_CONFIG.BASE_URL); const postData = JSON.stringify(data); const options = { hostname: url.hostname, port: url.port || 443, path: url.pathname, method: method, headers: { "Content-Type": "application/json", "Content-Length": Buffer.byteLength(postData), "access-token": API_KEY, ...(ACCOUNT_ID && { "x-account-id": ACCOUNT_ID }) } }; const req = https.request(options, (res) => { let responseData = ""; res.on("data", (chunk) => { responseData += chunk; }); res.on("end", () => { try { const parsed = JSON.parse(responseData); if (res.statusCode && res.statusCode >= 200 && res.statusCode < 300) { resolve(parsed); } else { reject(new Error(`API error ${res.statusCode}: ${JSON.stringify(parsed)}`)); } } catch (e) { reject(new Error(`Failed to parse response: ${responseData}`)); } }); }); req.on("error", (error) => { reject(error); }); req.write(postData); req.end(); });

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/anysiteio/hdw-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server