Skip to main content
Glama

extract_gdelt

Read-only

Fetch global news intelligence from GDELT Project to monitor worldwide news in 100+ languages, updated every 15 minutes, covering topics Western sources often miss.

Instructions

Fetch global news intelligence from the GDELT Project. GDELT monitors broadcast, print, and web news from every country in 100+ languages, updated every 15 minutes. Returns articles with title, source domain, country of origin, language, and publication date — covering news worldwide that Western sources miss. Free, no auth. Pass any company name, topic, or keyword. Unique: not available in any other MCP server.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlYesQuery: company name, topic, or keyword e.g. 'Palantir', 'artificial intelligence', 'MCP server'
max_lengthNo

Implementation Reference

  • The core logic for fetching and processing GDELT news intelligence.
    export async function gdeltAdapter(options: ExtractOptions): Promise<AdapterResult> {
      const query = (options.url ?? "").trim();
      const maxLength = options.maxLength ?? 6000;
    
      if (!query) throw new Error("Query required: company name, topic, or keyword");
    
      const data = await fetchGdelt(query);
      return formatArticles(data, query, maxLength);
    }
  • src/server.ts:456-476 (registration)
    Registration of the "extract_gdelt" tool and its execution wrapper.
    server.registerTool(
      "extract_gdelt",
      {
        description:
          "Fetch global news intelligence from the GDELT Project. GDELT monitors broadcast, print, and web news from every country in 100+ languages, updated every 15 minutes. Returns articles with title, source domain, country of origin, language, and publication date — covering news worldwide that Western sources miss. Free, no auth. Pass any company name, topic, or keyword. Unique: not available in any other MCP server.",
        inputSchema: z.object({
          url: z.string().describe("Query: company name, topic, or keyword e.g. 'Palantir', 'artificial intelligence', 'MCP server'"),
          max_length: z.number().optional().default(6000),
        }),
        annotations: { readOnlyHint: true, openWorldHint: true },
      },
      async ({ url, max_length }) => {
        try {
          const result = await gdeltAdapter({ url, maxLength: max_length });
          const ctx = stampFreshness(result, { url, maxLength: max_length }, "gdelt");
          return { content: [{ type: "text", text: formatForLLM(ctx) }] };
        } catch (err) {
          return { content: [{ type: "text", text: formatSecurityError(err) }] };
        }
      }
    );
Behavior4/5

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

Annotations indicate readOnlyHint=true and openWorldHint=true, which the description supports by mentioning 'Free, no auth' and 'updated every 15 minutes.' It adds valuable context beyond annotations by specifying the update frequency, coverage breadth, and that it returns articles with specific fields like title and source domain. No contradictions with annotations are present.

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 front-loaded with key information (action, resource, scope) and efficiently structured in three sentences that each add value: the first explains the tool's function, the second details coverage and output, and the third highlights uniqueness and usage. There is no wasted text, making it highly concise and well-organized.

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 moderate complexity (2 parameters, no output schema), the description is largely complete. It covers purpose, usage context, behavioral traits, and output format (articles with specific fields). However, it lacks details on error handling, rate limits (implied by 'updated every 15 minutes'), or explicit output structure, which could enhance completeness for an agent.

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 description coverage is 50%, with the 'url' parameter well-described in both schema and description as a query for topics. The description adds meaning by explaining what to pass ('any company name, topic, or keyword') and implies the tool's flexibility. However, it does not address the 'max_length' parameter or provide additional details beyond the schema's default value, leaving some gaps in parameter understanding.

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 the specific action ('fetch global news intelligence'), resource ('GDELT Project'), and scope ('monitors broadcast, print, and web news from every country in 100+ languages'). It explicitly distinguishes this tool from siblings by stating 'Unique: not available in any other MCP server,' making its purpose distinct within the server's ecosystem.

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 provides clear context for when to use this tool: for fetching global news intelligence with broad coverage, especially 'covering news worldwide that Western sources miss.' However, it does not explicitly state when not to use it or name specific alternatives among the sibling tools, such as extract_hackernews or extract_scholar, which might serve similar information-gathering purposes.

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