Skip to main content
Glama
Stewyboy1990

CompanyScope

get_key_people

Identify key people at a company including founders, executives, and team members by scraping the company's website, Wikipedia, and GitHub. Returns names, titles, and sources. Provide a domain name to get started.

Instructions

Find key people at a company including founders, C-suite executives, and team members. Scrapes the company's website (e.g. /about, /team pages), checks Wikipedia, and cross-references GitHub org members. Returns names, titles, and sources. Use this when you need leadership or team information specifically. Requires a domain name.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
domainYesCompany website domain without protocol (e.g. 'openai.com'). The tool will scrape the site's about/team pages.

Implementation Reference

  • The core handler function `buildKeyPeople` that implements the get_key_people tool logic. It takes a domain and env, normalizes the domain, checks cache, then fetches key people from three sources in parallel: web scraping (website about/team pages), Hunter.io API, and OpenCorporates corporate registry. Results are deduplicated by name and returned with source attribution.
    export async function buildKeyPeople(
      domainOrName: string,
      env: Env
    ): Promise<{
      domain: string;
      people: Person[];
      sources: string[];
    }> {
      const domain = normalizeDomain(domainOrName);
    
      const cacheKey = `keypeople:${domain}`;
      const cached = await getCachedJSON<{ domain: string; people: Person[]; sources: string[] }>(env, cacheKey);
      if (cached) return cached;
    
      const companyNameGuess = domain.split(".")[0];
    
      const [webData, hunterData, corpData] = await Promise.allSettled([
        scrapeCompanyWebsite(domain),
        fetchHunterData(domain, env.HUNTER_API_KEY),
        searchOpenCorporates(companyNameGuess, env.OPENCORPORATES_TOKEN),
      ]);
    
      const web = webData.status === "fulfilled" ? webData.value : {};
      const hunter = hunterData.status === "fulfilled" ? hunterData.value : null;
      const corp = corpData.status === "fulfilled" ? corpData.value : null;
    
      const people: Person[] = [];
      const seen = new Set<string>();
    
      for (const source of [
        corp?.officers?.map((o) => ({
          name: o.name,
          title: o.position,
          source: "opencorporates" as const,
        })) || [],
        hunter?.people?.map((p) => ({
          name: p.name,
          title: p.title,
          source: "hunter.io" as const,
        })) || [],
        web.keyPeople || [],
      ]) {
        for (const p of source) {
          if (p.name && !seen.has(p.name.toLowerCase())) {
            seen.add(p.name.toLowerCase());
            people.push(p);
          }
        }
      }
    
      const result = {
        domain,
        people: people.slice(0, 20),
        sources: [
          ...(web.sources || []),
          ...(hunter ? ["hunter.io"] : []),
          ...(corp ? ["opencorporates.com"] : []),
        ],
      };
    
      await setCachedJSON(env, cacheKey, result);
      return result;
    }
  • src/index.ts:199-215 (registration)
    Tool registration for 'get_key_people' in the Cloudflare Worker (src/index.ts). Registers the tool with MCP SDK, defines the 'domain' input schema using Zod, and the handler calls `buildKeyPeople(domain, env)`.
    // Tool 3: Key people
    server.tool(
      "get_key_people",
      "Find key people at a company including founders, C-suite executives, and team members. Scrapes the company's website (e.g. /about, /team pages), checks Wikipedia, and cross-references GitHub org members. Returns names, titles, and sources. Use this when you need leadership or team information specifically. Requires a domain name.",
      { domain: z.string().describe("Company website domain without protocol (e.g. 'openai.com'). The tool will scrape the site's about/team pages.") },
      async ({ domain }) => {
        const result = await buildKeyPeople(domain, env);
        return {
          content: [
            {
              type: "text" as const,
              text: JSON.stringify(result, null, 2),
            },
          ],
        };
      }
    );
  • src/server.js:94-109 (registration)
    Tool registration for 'get_key_people' in the local stdio proxy server (src/server.js). Registers the tool and proxies calls to the remote CompanyScope API via `callRemoteTool('get_key_people', { domain })`.
    // Tool 3: Key people
    server.tool(
      "get_key_people",
      "Find key people at a company including founders, C-suite executives, and team members. Scrapes the company's website (e.g. /about, /team pages), checks Wikipedia, and cross-references GitHub org members. Returns names, titles, and sources. Use this when you need leadership or team information specifically. Requires a domain name.",
      {
        domain: z
          .string()
          .describe(
            "Company website domain without protocol (e.g. 'openai.com'). The tool will scrape the site's about/team pages."
          ),
      },
      async ({ domain }) => {
        const result = await callRemoteTool("get_key_people", { domain });
        return result;
      }
    );
  • bin/cli.js:83-88 (registration)
    Tool registration for 'get_key_people' in the CLI (bin/cli.js). Registers the tool for npx invocation, proxying to the remote API.
    server.tool(
      "get_key_people",
      "Find key people at a company including founders, C-suite executives, and team members. Scrapes the company's website (e.g. /about, /team pages), checks Wikipedia, and cross-references GitHub org members. Returns names, titles, and sources. Use this when you need leadership or team information specifically. Requires a domain name.",
      { domain: z.string().describe("Company website domain without protocol (e.g. 'openai.com'). The tool will scrape the site's about/team pages.") },
      async ({ domain }) => callRemoteTool("get_key_people", { domain })
    );
  • The `Person` interface used by the key people handler. Defines the shape: name (string), title (string|null), and source (string).
    export interface Person {
      name: string;
      title: string | null;
      source: string;
    }
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Describes the scraping process (website, Wikipedia, GitHub), the data returned (names, titles, sources). With no annotations, this is sufficient behavioral disclosure. Could be improved by mentioning potential failure modes or rate limits, but overall transparent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences concisely cover purpose, method, use case, and requirement. No extraneous words. Front-loaded with the main action.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given a single parameter and no output schema, the description covers the essential aspects: input, process, output, and use case. It could be more complete by mentioning limitations (e.g., only public info, or if site blocks scraping), but it's largely adequate.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema covers the single parameter 'domain' at 100%. The description adds further context: 'without protocol (e.g. 'openai.com')' and explains how the domain is used (scraping about/team pages). This adds value beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly defines the tool as finding key people (founders, C-suite, team members) at a company. Differentiates from sibling tools like get_company_news or get_financials by focusing specifically on leadership and team information.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states when to use: 'when you need leadership or team information specifically.' Also specifies a prerequisite: 'Requires a domain name.' Does not provide explicit exclusions or alternatives, but the context is clear enough.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

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/Stewyboy1990/companyscope-mcp'

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