Skip to main content
Glama

extract_changelog

Read-only

Extract version history and release notes from GitHub repositories, npm packages, or websites to track updates, maintenance activity, and feature releases.

Instructions

Extract update history from any product, repo, or package. Accepts a GitHub URL (uses Releases API), an npm package name, or any website URL (auto-discovers /changelog, /releases, /CHANGELOG.md). Returns version numbers, release dates, and entry content — all timestamped. Use this to check if a tool is actively maintained, when a feature shipped, or how fast a team moves.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlYesGitHub repo URL (https://github.com/owner/repo), npm package name (e.g. 'freshcontext-mcp'), or any website URL (https://example.com). Auto-discovers changelog paths.
max_lengthNoMax content length

Implementation Reference

  • The changelogAdapter function acts as the main entry point for the "extract_changelog" tool, routing the input to GitHub API, npm registry, or browser-based discovery based on the URL type.
    export async function changelogAdapter(options: ExtractOptions): Promise<AdapterResult> {
      const input = (options.url ?? "").trim();
      const maxLength = options.maxLength ?? 6000;
    
      // npm package name (no http, no dots at start, no slashes)
      if (!input.startsWith("http") && !input.includes("/") && input.length > 0) {
        return fetchNpmChangelog(input, maxLength);
      }
    
      // GitHub repo URL → use releases API
      const ghMatch = input.match(/github\.com\/([^/]+)\/([^/?\s]+)/);
      if (ghMatch) {
        try {
          return await fetchGitHubReleases(ghMatch[1], ghMatch[2], maxLength);
        } catch {
          // Fall through to browser scrape if API fails
        }
      }
    
      // Any other URL → discover changelog
      return discoverChangelog(input, maxLength);
    }
  • src/server.ts:242-255 (registration)
    The "extract_changelog" tool is registered here with its schema and handler function in src/server.ts.
    server.registerTool(
      "extract_changelog",
      {
        description:
          "Extract update history from any product, repo, or package. Accepts a GitHub URL (uses Releases API), an npm package name, or any website URL (auto-discovers /changelog, /releases, /CHANGELOG.md). Returns version numbers, release dates, and entry content — all timestamped. Use this to check if a tool is actively maintained, when a feature shipped, or how fast a team moves.",
        inputSchema: z.object({
          url: z.string().describe(
            "GitHub repo URL (https://github.com/owner/repo), npm package name (e.g. 'freshcontext-mcp'), or any website URL (https://example.com). Auto-discovers changelog paths."
          ),
          max_length: z.number().optional().default(6000).describe("Max content length"),
        }),
        annotations: { readOnlyHint: true, openWorldHint: true },
      },
      async ({ url, max_length }) => {
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 flexible inputs. The description adds valuable behavioral context beyond annotations: it specifies auto-discovery of changelog paths (/changelog, /releases, etc.), mentions using GitHub Releases API for GitHub URLs, and describes the return format (version numbers, release dates, entry content, timestamped). No contradiction with annotations.

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 in two sentences: the first explains the tool's function and input types, the second provides usage examples. Every sentence adds value with no redundant information, making it front-loaded and appropriately sized.

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, 100% schema coverage, read-only annotations), the description is mostly complete. It explains purpose, usage, and behavioral context well. The main gap is the lack of output schema, but the description partially compensates by describing return content (version numbers, dates, entries).

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 100%, providing full documentation for both parameters. The description adds some semantic context by explaining what types of inputs are accepted (GitHub URL, npm package name, website URL) and hinting at auto-discovery behavior, but doesn't provide additional syntax or format details beyond what the schema already covers.

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 ('Extract update history') and resource scope ('from any product, repo, or package'), distinguishing it from sibling tools focused on extracting other data types like finance, GitHub, or SEC filings. It provides concrete examples of input types (GitHub URL, npm package name, website URL).

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 explicitly states when to use this tool ('to check if a tool is actively maintained, when a feature shipped, or how fast a team moves'), providing clear context and use cases. It distinguishes from siblings by focusing on changelog extraction rather than other data landscapes or searches.

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