Developer Tools MCP Server

包含 GitHub、npm、PyPI、Docker Hub、GitLab 和 StackOverflow 的開發者資源

文件

Developer Tools MCP — GitHub, npm, PyPI & Docs for Agents (nexgendata/developer-tools-mcp-server) Actor

MCP server exposing GitHub, npm, PyPI, Stack Overflow, arXiv and OpenAlex paper search as agent tools — package versions, licences, repos, issues, papers. Connect Claude, Cursor, n8n or the OpenAI Agents SDK. $0.02 per successful tool call.

Pricing

from $50.00 / 1,000 tool calls

This Actor is paid per event and usage. You are charged both the fixed price for specific events and for Apify platform usage.

Learn more: https://docs.apify.com/actors/running/actors-in-store.md#pay-per-event

What's an Apify Actor?

An Actor is a serverless cloud program that runs on the Apify platform. It has two run modes. In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours, and optionally produces a well-defined JSON output, datasets with results, or files in key-value store. In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server.

Apify vocabulary and the platform model are defined once, in the agent quickstart at https://apify.com/agents.md.

How to integrate an Actor?

If asked about integration, you help developers integrate Actors into their projects. You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready.

Do not guess an integration path. Every one of them is in the agent quickstart at https://apify.com/agents.md: the Apify MCP server, Agent Skills with the Apify CLI, the JavaScript and Python clients, the REST API, and the account-free path for an agent with no human to sign in. It also carries the rule on stating cost before the first paid run.

For examples already wired to this Actor's own input schema, see the API section below.

Each client library has reference documentation the quickstart does not restate: JavaScript/TypeScript (npm install apify-client) and Python (pip install apify-client).

README

🤖 Developer Tools MCP Server — GitHub, npm, PyPI & Stack Overflow for Claude / ChatGPT

Connect AI coding agents to live developer-ecosystem data through the Model Context Protocol — GitHub repo stats, npm / PyPI package metadata, Stack Overflow tag trends, and developer-tool intelligence. A drop-in alternative to the official GitHub MCP, internal dev portals, and ad-hoc REST wrappers.

Why This MCP Server Beats GitHub MCP, Snyk MCP, GitLab API & Internal Dev Portals

FeatureNexGenData Dev Tools MCPOfficial GitHub MCPSnyk MCPGitLab APIInternal dev portal
CostPay-per-event, ~$0.002 per tool callFree but rate-limited (~5,000 req/hr)Snyk subscription requiredFree / tier-gatedEngineering team time
CoverageGitHub + npm + PyPI + Stack Overflow + trending reposGitHub onlyVuln scanning onlyGitLab onlyWhatever you build
AuthApify API tokenGitHub PAT per userSnyk org tokenGitLab tokenSSO + internal
AI agent integrationNative MCP — Claude Desktop, Cursor, n8nYes (GitHub-only)LimitedNoneCustom
Time-to-first-call< 60 secondsPAT scope reviewSnyk onboardingGitLab setupBuild it yourself
Rate limitApify-managedGitHub strictSnyk planGitLab planInternal infra
Output formatStructured JSON optimized for LLM function-callingREST JSONJSONREST JSONCustom

Most teams pick this MCP server because it is the only way to give a single AI agent unified access to GitHub + npm + PyPI + Stack Overflow without juggling three rate-limited PATs and writing custom adapters.

What You Get

Tools exposed to your AI agent include:

  • search_github_repos — keyword + language + star-range search across all of GitHub
  • get_repo_stats — stars, forks, contributors, last-commit, license, issue counts
  • trending_repos — daily / weekly / monthly trending by language
  • npm_package_stats — downloads, dependents, version history for any npm package
  • pypi_package_stats — downloads + dependents for any PyPI package
  • stackoverflow_tag_trends — question volume + answer rate per tag over time
  • compare_packages — head-to-head download / star / activity comparison

All responses are structured JSON optimized for LLM function-calling — no scraping, no HTML, no schema drift.

Use Cases

  • AI engineering assistants — Claude or GPT-4 recommends packages based on live download counts + maintenance signal
  • Tech-stack research agents — chat-first agents answer "is fastapi or flask gaining traction in 2026?"
  • Vendor-evaluation bots — multi-step agents compare alternatives across npm + PyPI + GitHub stars
  • Tech debt copilots — agents flag dependencies with stagnant maintenance, high CVE volume, or low truck-factor
  • Developer-relations dashboards — agents auto-generate weekly "trending in your category" reports
  • n8n / Make.com workflows — trigger a Slack alert when a package crosses 1M downloads or a competitor's repo crosses 10K stars
  • Recruiter agents — find authors of trending repos in a target language for outbound recruiting

Quick Start

from apify_client import ApifyClient
client = ApifyClient("YOUR_APIFY_TOKEN")
run = client.actor("nexgendata/developer-tools-mcp-server").call(run_input={
    "tool": "search_github_repos",
    "params": {"query": "vector database", "language": "Rust", "min_stars": 500}
})
for item in client.dataset(run["defaultDatasetId"]).iterate_items():
    print(item)

Or connect from Claude Desktop with this MCP server URL — and Claude can call any of the tools above as part of a conversation.

Pricing

Pay-per-event — you only pay for tool calls that succeed:

  • Actor Start: ~$0.0002 per session
  • Tool call: $0.002 per call

A typical agent making 20-50 tool calls per task spends $0.04 - $0.10 — orders of magnitude cheaper than running a self-hosted aggregator across three rate-limited APIs.

Related NexGenData Actors

Use caseActor
Trending repos surfaced as a flat datasetGitHub Trending Repos
npm package download + dependents statsnpm Package Stats
PyPI package download + dependents statsPyPI Package Stats
Stack Overflow tag question + answer trendsStackOverflow Tag Trends
News data + media monitoring for AI agentsNews MCP Server
Academic / research data for AI agentsAcademic Research MCP Server
Finance + stock data for AI agentsFinance MCP Server
Real estate + property data for AI agentsReal Estate MCP Server

FAQ

Q: Does this need a GitHub token? No — the server uses Apify-managed rate limits. You only need your Apify API token.

Q: How do I connect Claude Desktop to this server? Apify exposes every actor as an MCP endpoint. Add https://api.apify.com/v2/acts/nexgendata~developer-tools-mcp-server/runs (with your token) to your Claude Desktop MCP config.

Q: Is the data live or cached? GitHub + npm + PyPI calls are made fresh on each request. Stack Overflow tag trends use the most recent indexed snapshot (rolled daily).

Q: Can I add this MCP server to Cursor or Cline? Yes — any MCP-compatible client works. Use the same endpoint URL.

Q: What if I hit a rate limit on a downstream API? The server transparently retries with backoff and rotates internal credentials. Tool calls that ultimately fail return a structured error — no charge for failed events.

Q: Is this safe for production agent workloads? Yes — runs on Apify's auto-scaled actor infrastructure with logging + monitoring built in.

Q: Can I add custom tools? The upstream tool set is fixed for this actor. For custom workflows, fork the actor or compose tools across the MCP cluster (this + finance-mcp-server + news-mcp-server etc.).

About NexGenData

NexGenData publishes 260+ buyer-intent actors plus a family of MCP servers (finance, news, sports, real-estate, developer tools, academic research, premium data) for AI agent workflows. All pay-per-result. Browse the full catalog at https://apify.com/nexgendata?fpr=2ayu9b


How NexGenData Pricing Works

Every NexGenData actor uses pay-per-event pricing — you only pay for results that actually land in your dataset. No monthly minimum, no seat fees, no surprise overage bills.

  • Actor Start: a single-event charge each time you spin the actor up (scaled to memory size)
  • Result: charged per item written to the default dataset
  • No charge for retries, internal proxy rotation, or failed sub-requests — those are absorbed by the platform

If you only need the data once a quarter, you only pay once a quarter. If you scale to millions of records, the unit cost stays the same.

Apify Platform Bonus

New to Apify? Sign up with the NexGenData referral link — you get free platform credits on signup (enough for several thousand free results) and you help fund the maintenance of this actor fleet.

Integration Surface

Every actor in the NexGenData catalog can be triggered from:

  • Apify console — point-and-click run
  • Apify API — REST + webhooks
  • Apify Python / JS SDKs — programmatic batch
  • Zapier, Make.com, n8n — official integrations
  • MCP — many actors are exposed as MCP tools for Claude / ChatGPT / Cursor agents
  • Schedules — built-in cron for daily / weekly / monthly runs
  • Webhooks — POST results to any HTTPS endpoint on dataset write

Support

NexGenData maintains 260+ Apify actors and ships updates regularly. Bug reports via the Apify console issues tab get a response within 24 hours. Roadmap requests are welcome — high-demand features ship in the next version.

🏠 Home: thenextgennexus.com 📦 Full catalog: apify.com/nexgendata

Actor input Schema

Actor input object example

{}

API

You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup.

JavaScript example

import { ApifyClient } from 'apify-client';

// Initialize the ApifyClient with your Apify API token
// Replace the '<YOUR_API_TOKEN>' with your token
const client = new ApifyClient({
    token: '<YOUR_API_TOKEN>',
});

// Prepare Actor input
const input = {};

// Run the Actor and wait for it to finish
const run = await client.actor("nexgendata/developer-tools-mcp-server").call(input);

// Fetch and print Actor results from the run's dataset (if any)
console.log('Results from dataset');
console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
items.forEach((item) => {
    console.dir(item);
});

// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs

Python example

from apify_client import ApifyClient

# Initialize the ApifyClient with your Apify API token
# Replace '<YOUR_API_TOKEN>' with your token.
client = ApifyClient("<YOUR_API_TOKEN>")

# Prepare the Actor input
run_input = {}

# Run the Actor and wait for it to finish
run = client.actor("nexgendata/developer-tools-mcp-server").call(run_input=run_input)

# Fetch and print Actor results from the run's dataset (if there are any)
print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")
for item in client.dataset(run.default_dataset_id).iterate_items():
    print(item)

# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start

CLI example

echo '{}' |
apify call nexgendata/developer-tools-mcp-server --silent --output-dataset

MCP server setup

{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,nexgendata/developer-tools-mcp-server"
        }
    }
}

The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an Authorization: Bearer <APIFY_API_TOKEN> header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations).

OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/actors/ZuY8xExrmZTJualCf/builds/Es7MUjt71JqAHmz5I/openapi.json