Skip to main content
Glama

Screen Companies

screen_companies

Screen companies by financials, industry, IP, and litigation. Filter using SIC codes, revenue, assets, shell risk, patents, trademarks, and short interest.

Instructions

Screen companies using financial, industry, IP, and litigation filters. Combine SIC industry codes, revenue/asset brackets, shell risk scores, patent/trademark/litigation flags, and short interest levels. Cross-references SEC, OTC, Patents, Trademarks, and PACER datasets.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
sic_codeNoSIC industry code (e.g. '7372' for software)
industryNoIndustry keyword search (partial match)
min_revenueNoMinimum revenue in USD
max_revenueNoMaximum revenue in USD
min_assetsNoMinimum total assets in USD
max_assetsNoMaximum total assets in USD
max_shell_riskNoMaximum shell risk score (0-100)
min_filing_recencyNoMinimum filing recency score (0-100)
has_patentsNoFilter to companies with patent activity
has_trademarksNoFilter to companies with trademark registrations
has_litigationNoFilter to companies with court cases
min_short_interestNoMinimum short interest ratio
sort_byNoSort field: revenue, assets, shell_risk, filing_recency, short_interest
limitNoMaximum results (default 25, max 100)

Implementation Reference

  • The async handler function for the screen_companies tool. Accepts financial/IP/litigation filter parameters, builds query params, calls GET /api/v1/companies/screen, and returns the matching companies as formatted text.
      async (params) => {
        const queryParams: Record<string, string | number | undefined> = {
          sic_code: params.sic_code,
          industry: params.industry,
          min_revenue: params.min_revenue,
          max_revenue: params.max_revenue,
          min_assets: params.min_assets,
          max_assets: params.max_assets,
          max_shell_risk: params.max_shell_risk,
          min_filing_recency: params.min_filing_recency,
          has_patents: params.has_patents != null ? String(params.has_patents) : undefined,
          has_trademarks: params.has_trademarks != null ? String(params.has_trademarks) : undefined,
          has_litigation: params.has_litigation != null ? String(params.has_litigation) : undefined,
          min_short_interest: params.min_short_interest,
          sort_by: params.sort_by,
          limit: params.limit ?? 25,
        };
    
        const res = await apiGet<{ dataset: string; count: number; data: Record<string, unknown>[] }>(
          "/api/v1/companies/screen",
          queryParams,
        );
    
        if (!res.ok) {
          return {
            content: [
              {
                type: "text" as const,
                text: `API error (${res.status}): ${JSON.stringify(res.data)}`,
              },
            ],
            isError: true,
          };
        }
    
        const { count, data } = res.data;
        const summary = `Found ${count} company/companies matching filters.`;
        const json = JSON.stringify(data, null, 2);
    
        return {
          content: [{ type: "text" as const, text: `${summary}\n\n${json}` }],
        };
      },
    );
  • Input schema for screen_companies tool: defines all optional filter parameters (sic_code, industry, revenue range, asset range, shell_risk, filing_recency, has_patents, has_trademarks, has_litigation, short_interest, sort_by, limit) using Zod validation.
    inputSchema: {
      sic_code: z
        .string()
        .optional()
        .describe("SIC industry code (e.g. '7372' for software)"),
      industry: z
        .string()
        .optional()
        .describe("Industry keyword search (partial match)"),
      min_revenue: z
        .number()
        .optional()
        .describe("Minimum revenue in USD"),
      max_revenue: z
        .number()
        .optional()
        .describe("Maximum revenue in USD"),
      min_assets: z
        .number()
        .optional()
        .describe("Minimum total assets in USD"),
      max_assets: z
        .number()
        .optional()
        .describe("Maximum total assets in USD"),
      max_shell_risk: z
        .number()
        .int()
        .min(0)
        .max(100)
        .optional()
        .describe("Maximum shell risk score (0-100)"),
      min_filing_recency: z
        .number()
        .int()
        .min(0)
        .max(100)
        .optional()
        .describe("Minimum filing recency score (0-100)"),
      has_patents: z
        .boolean()
        .optional()
        .describe("Filter to companies with patent activity"),
      has_trademarks: z
        .boolean()
        .optional()
        .describe("Filter to companies with trademark registrations"),
      has_litigation: z
        .boolean()
        .optional()
        .describe("Filter to companies with court cases"),
      min_short_interest: z
        .number()
        .optional()
        .describe("Minimum short interest ratio"),
      sort_by: z
        .string()
        .optional()
        .describe("Sort field: revenue, assets, shell_risk, filing_recency, short_interest"),
      limit: z
        .number()
        .int()
        .min(1)
        .max(100)
        .optional()
        .describe("Maximum results (default 25, max 100)"),
    },
  • Registration of the 'screen_companies' tool via server.registerTool(), with title 'Screen Companies' and description explaining its cross-dataset screening capabilities.
    server.registerTool(
      "screen_companies",
      {
        title: "Screen Companies",
        description:
          "Screen companies using financial, industry, IP, and litigation filters. " +
          "Combine SIC industry codes, revenue/asset brackets, shell risk scores, " +
          "patent/trademark/litigation flags, and short interest levels. " +
          "Cross-references SEC, OTC, Patents, Trademarks, and PACER datasets.",
        inputSchema: {
          sic_code: z
            .string()
            .optional()
            .describe("SIC industry code (e.g. '7372' for software)"),
          industry: z
            .string()
            .optional()
            .describe("Industry keyword search (partial match)"),
          min_revenue: z
            .number()
            .optional()
            .describe("Minimum revenue in USD"),
          max_revenue: z
            .number()
            .optional()
            .describe("Maximum revenue in USD"),
          min_assets: z
            .number()
            .optional()
            .describe("Minimum total assets in USD"),
          max_assets: z
            .number()
            .optional()
            .describe("Maximum total assets in USD"),
          max_shell_risk: z
            .number()
            .int()
            .min(0)
            .max(100)
            .optional()
            .describe("Maximum shell risk score (0-100)"),
          min_filing_recency: z
            .number()
            .int()
            .min(0)
            .max(100)
            .optional()
            .describe("Minimum filing recency score (0-100)"),
          has_patents: z
            .boolean()
            .optional()
            .describe("Filter to companies with patent activity"),
          has_trademarks: z
            .boolean()
            .optional()
            .describe("Filter to companies with trademark registrations"),
          has_litigation: z
            .boolean()
            .optional()
            .describe("Filter to companies with court cases"),
          min_short_interest: z
            .number()
            .optional()
            .describe("Minimum short interest ratio"),
          sort_by: z
            .string()
            .optional()
            .describe("Sort field: revenue, assets, shell_risk, filing_recency, short_interest"),
          limit: z
            .number()
            .int()
            .min(1)
            .max(100)
            .optional()
            .describe("Maximum results (default 25, max 100)"),
        },
      },
      async (params) => {
        const queryParams: Record<string, string | number | undefined> = {
          sic_code: params.sic_code,
          industry: params.industry,
          min_revenue: params.min_revenue,
          max_revenue: params.max_revenue,
          min_assets: params.min_assets,
          max_assets: params.max_assets,
          max_shell_risk: params.max_shell_risk,
          min_filing_recency: params.min_filing_recency,
          has_patents: params.has_patents != null ? String(params.has_patents) : undefined,
          has_trademarks: params.has_trademarks != null ? String(params.has_trademarks) : undefined,
          has_litigation: params.has_litigation != null ? String(params.has_litigation) : undefined,
          min_short_interest: params.min_short_interest,
          sort_by: params.sort_by,
          limit: params.limit ?? 25,
        };
    
        const res = await apiGet<{ dataset: string; count: number; data: Record<string, unknown>[] }>(
          "/api/v1/companies/screen",
          queryParams,
        );
    
        if (!res.ok) {
          return {
            content: [
              {
                type: "text" as const,
                text: `API error (${res.status}): ${JSON.stringify(res.data)}`,
              },
            ],
            isError: true,
          };
        }
    
        const { count, data } = res.data;
        const summary = `Found ${count} company/companies matching filters.`;
        const json = JSON.stringify(data, null, 2);
    
        return {
          content: [{ type: "text" as const, text: `${summary}\n\n${json}` }],
        };
      },
    );
  • src/index.ts:46-46 (registration)
    Call to registerCompanyTools(server) which registers screen_companies along with company_profile and trader_signals.
    registerCompanyTools(server);
  • The apiGet helper function used by the screen_companies handler to make the HTTP GET request to the Verilex API.
    export async function apiGet<T = unknown>(
      path: string,
      params?: Record<string, string | number | undefined>,
    ): Promise<ApiResponse<T>> {
      const url = buildUrl(path, params);
    
      const headers: Record<string, string> = {
        Accept: "application/json",
        "User-Agent": "verilex-mcp-server/0.1.0",
      };
    
      // Forward x402 payment token if present in env (for paid endpoints)
      const paymentToken = process.env.VERILEX_PAYMENT_TOKEN;
      if (paymentToken) {
        headers["X-Payment-Token"] = paymentToken;
      }
    
      const res = await fetch(url, { headers });
      const data = (await res.json()) as T;
    
      const stale = res.headers.get("X-Data-Stale");
      const lastUpdated = res.headers.get("X-Data-Last-Updated");
      const ageSeconds = res.headers.get("X-Data-Age-Seconds");
    
      return {
        ok: res.ok,
        status: res.status,
        data,
        stale: stale === "true",
        lastUpdated: lastUpdated ?? undefined,
        ageSeconds: ageSeconds ? Number(ageSeconds) : undefined,
      };
    }
Behavior2/5

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

Without annotations, the description carries full burden. It mentions cross-referencing datasets but does not disclose behavior like result format (list vs. details), pagination, or performance characteristics. The limit parameter is the only behavioral hint.

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?

Two sentences, front-loaded with the main action, no fluff. Each sentence adds value: first defines the high-level purpose, second enumerates filter groups and data sources.

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

Completeness3/5

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

Given 14 parameters and multi-dataset cross-referencing, the description covers the filter options and sources well. However, with no output schema, it fails to hint at the response structure (e.g., list of tickers or full profiles), leaving a completeness gap.

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

Parameters3/5

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

Schema coverage is 100%, so baseline is 3. The description adds context by grouping filter types (financial, IP, litigation) and listing data sources, but does not add detailed semantics beyond what the schema's descriptions already provide.

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?

The description clearly states it screens companies using financial, industry, IP, and litigation filters, and cross-references multiple datasets. The verb 'screen' and specific filter types distinguish it from other search tools like search_sec_companies.

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?

The description effectively implies this tool is for multi-criteria screening of companies. It does not explicitly state when not to use it or name alternatives, but the context of sibling tools suggests other lookup options for specific queries.

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/carrierone/verilexdata-mcp'

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