Skip to main content
Glama

extract_company_landscape

Read-only

Analyze companies by extracting real-time intelligence from SEC filings, government contracts, global news, product changelogs, and financial data in a unified report.

Instructions

Composite company intelligence tool. The most complete single-call company analysis available. Simultaneously queries 5 unique sources: (1) SEC EDGAR for 8-K material event filings — what the company legally just disclosed, (2) USASpending.gov for federal contract footprint — who is giving them government money, (3) GDELT for global news intelligence — what the world is saying about them right now, (4) their product changelog — are they actually shipping, (5) Yahoo Finance — what the market is pricing in. Returns a unified 5-source timestamped report. Unique: this combination is not available in any other MCP server.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
companyYesCompany name e.g. 'Palantir', 'Anthropic', 'OpenAI'
tickerNoStock ticker for finance data e.g. 'PLTR'. Leave blank for private companies.
github_urlNoOptional GitHub repo or org URL e.g. 'https://github.com/palantir'. Improves changelog accuracy.
max_lengthNo

Implementation Reference

  • The handler function for 'extract_company_landscape' which concurrently fetches and aggregates intelligence from SEC filings, government contracts, news, changelogs, and market data.
    async ({ company, ticker, github_url, max_length }) => {
      const perSection = Math.floor((max_length ?? 15000) / 5);
      const repoQuery = github_url ?? company;
    
      const [secResult, contractsResult, gdeltResult, changelogResult, financeResult] = await Promise.allSettled([
        // 1. What did they legally just disclose
        secFilingsAdapter({ url: company, maxLength: perSection }),
        // 2. Who is giving them government money
        govContractsAdapter({ url: company, maxLength: perSection }),
        // 3. What is global news saying right now
        gdeltAdapter({ url: company, maxLength: perSection }),
        // 4. Are they actually shipping product
        changelogAdapter({ url: repoQuery, maxLength: perSection }),
        // 5. What is the market pricing in
        financeAdapter({ url: ticker ?? company, maxLength: perSection }),
      ]);
    
      const section = (
        label: string,
        result: PromiseSettledResult<{ raw: string; content_date: string | null; freshness_confidence: string }>
      ) =>
        result.status === "fulfilled"
          ? `## ${label}\n${result.value.raw}`
          : `## ${label}\n[Unavailable: ${(result as PromiseRejectedResult).reason}]`;
    
      const combined = [
        `# Company Intelligence Landscape: "${company}"${ticker ? ` (${ticker})` : ""}`,
        `Generated: ${new Date().toISOString()}`,
        `Sources: SEC EDGAR · USASpending.gov · GDELT · Changelog · Yahoo Finance`,
        "",
        section("📋 SEC 8-K Filings — Legal Disclosures", secResult),
        section("🏛️ Federal Contract Awards (USASpending.gov)", contractsResult),
        section("🌍 Global News Intelligence (GDELT)", gdeltResult),
        section("🔄 Product Release Velocity (Changelog)", changelogResult),
        section("📈 Market Data (Yahoo Finance)", financeResult),
      ].join("\n\n");
    
      return { content: [{ type: "text", text: combined }] };
    }
  • src/server.ts:483-501 (registration)
    Registration of the 'extract_company_landscape' tool with its schema definition in src/server.ts.
    server.registerTool(
      "extract_company_landscape",
      {
        description:
          "Composite company intelligence tool. The most complete single-call company analysis available. Simultaneously queries 5 unique sources: (1) SEC EDGAR for 8-K material event filings — what the company legally just disclosed, (2) USASpending.gov for federal contract footprint — who is giving them government money, (3) GDELT for global news intelligence — what the world is saying about them right now, (4) their product changelog — are they actually shipping, (5) Yahoo Finance — what the market is pricing in. Returns a unified 5-source timestamped report. Unique: this combination is not available in any other MCP server.",
        inputSchema: z.object({
          company: z.string().describe(
            "Company name e.g. 'Palantir', 'Anthropic', 'OpenAI'"
          ),
          ticker: z.string().optional().describe(
            "Stock ticker for finance data e.g. 'PLTR'. Leave blank for private companies."
          ),
          github_url: z.string().optional().describe(
            "Optional GitHub repo or org URL e.g. 'https://github.com/palantir'. Improves changelog accuracy."
          ),
          max_length: z.number().optional().default(15000),
        }),
        annotations: { readOnlyHint: true, openWorldHint: true },
      },
Behavior4/5

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

Annotations provide readOnlyHint=true and openWorldHint=true, indicating safe read operations with open-world assumptions. The description adds valuable behavioral context beyond annotations: it specifies the tool queries 5 specific external sources, returns a 'unified 5-source timestamped report,' mentions data sources like SEC filings and government contracts, and notes the 'max_length' parameter controls output size. It doesn't contradict annotations and provides useful implementation details.

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?

The description is efficiently structured: first sentence establishes purpose, subsequent sentences detail the 5 sources with parenthetical explanations, and final sentences describe output and uniqueness. Every sentence adds value—no wasted words. It's appropriately sized for a complex tool and front-loads key information about being a composite analysis tool.

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 the tool's complexity (4 parameters, multiple data sources, no output schema), the description provides strong context: it lists all 5 data sources, explains the composite nature, and notes the unified report output. However, without an output schema, it could better describe the report structure or format. The annotations cover safety aspects, and parameter documentation is mostly adequate, making it nearly complete for agent use.

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 description coverage is 75% (3 of 4 parameters have descriptions), providing good baseline documentation. The description adds meaningful context: it explains that 'github_url' improves changelog accuracy (beyond schema's 'optional' note) and implies 'max_length' controls report size (though not explicitly stated). However, it doesn't fully explain parameter interactions (e.g., how ticker affects finance data when blank).

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 explicitly states the tool performs 'company intelligence' and 'analysis', specifying it queries 5 unique sources (SEC EDGAR, USASpending.gov, GDELT, product changelog, Yahoo Finance) to return a unified report. It clearly distinguishes from siblings by emphasizing it's a 'composite' tool combining sources that are available individually in other tools like extract_sec_filings, extract_govcontracts, extract_gdelt, extract_finance_landscape, and extract_changelog.

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

Usage Guidelines5/5

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

The description provides explicit guidance on when to use this tool: it's 'the most complete single-call company analysis available' and 'this combination is not available in any other MCP server.' This clearly indicates it should be used when comprehensive multi-source analysis is needed, rather than the individual sibling tools that query single sources. It also implies when not to use it (when only specific single-source data is required).

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/PrinceGabriel-lgtm/freshcontext-mcp'

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