Featured

Deploy OpenClaw in 60 seconds — 20% off logoDeploy OpenClaw in 60 seconds — 20% off

Launch OpenClaw on Hostinger in about 60 seconds and keep your agent live 24/7. Our referral link gives you 20% off, no coupon code needed.

Launch on Hostinger
Run your Hermes agent on Hostinger, fully managed logoRun your Hermes agent on Hostinger, fully managed

Launch Hermes on Hostinger in one click, fully managed, no VPS knowledge needed. Use code ZACAARON10 for 10% off.

Launch on Hostinger
Crawl and scrape any site into clean data, 10% off logoCrawl and scrape any site into clean data, 10% off

Firecrawl crawls and scrapes any site into clean markdown for your agent. Get 1,000 free credits, and new users get 10% off their first purchase.

Try Firecrawl free
Your own AI agent, running 24/7 with QwikClaw logoYour own AI agent, running 24/7 with QwikClaw

QwikClaw sets up and runs an always-on OpenClaw agent for you. One click, no config files, no server setup.

Deploy now
One API to scrape, enrich, and extract the internet. logoOne API to scrape, enrich, and extract the internet.

Context.dev gives your agents a single API to scrape, enrich, and extract live web data — no proxies, no parsers, no maintenance.

Start building free
SetupClaw: done-for-you OpenClaw for founders & exec teams logoSetupClaw: done-for-you OpenClaw for founders & exec teams

White-glove OpenClaw for founders and exec teams (4–50+ employees): we install, harden, integrate your tools, and maintain it — secured from day one.

Get it set up for you
SEO data APIs for your agent, $1 free credit logoSEO data APIs for your agent, $1 free credit

DataForSEO gives your agent live access to SERP results, keyword data, backlinks, and on-page SEO data through one API. New accounts get a $1 credit, good for up to 20,000 keyword or backlink lookups.

Try DataForSEO free
Reach 47,000+ AI builders

A flat monthly placement in front of developers actively installing AI tools. No lock-in, cancel anytime.

Advertise here

Works with

Claude CodeClaude DesktopCursorVS CodeClineCodex CLIOpenClaw+ any MCP client

Install to Claude Code

claude mcp add stackoverflow -- npx -y @gscalzo/stackoverflow-mcp

Summary

The Stack Overflow MCP server lets an agent search Stack Overflow for programming solutions directly from your MCP client.

Connect from your MCP client

One-click install

Add this server to your editor with a single click. Fill in any required credentials afterward.

Claude Code

Run this once and Claude Code registers the server for you:

claude mcp add stackoverflow -- npx -y @gscalzo/stackoverflow-mcp

Claude Desktop

Add this to claude_desktop_config.json under Settings → Developer → Edit Config:

{
  "mcpServers": {
    "stackoverflow": {
      "command": "npx",
      "args": [
        "-y",
        "@gscalzo/stackoverflow-mcp"
      ],
      "env": {
        "STACKOVERFLOW_API_KEY": "<STACKOVERFLOW_API_KEY>"
      }
    }
  }
}

Cursor

Add this to .cursor/mcp.json in your project (or ~/.cursor/mcp.json for all projects):

{
  "mcpServers": {
    "stackoverflow": {
      "command": "npx",
      "args": [
        "-y",
        "@gscalzo/stackoverflow-mcp"
      ],
      "env": {
        "STACKOVERFLOW_API_KEY": "<STACKOVERFLOW_API_KEY>"
      }
    }
  }
}

Cline and other MCP clients

Most MCP clients accept the standard mcpServers JSON block:

{
  "mcpServers": {
    "stackoverflow": {
      "command": "npx",
      "args": [
        "-y",
        "@gscalzo/stackoverflow-mcp"
      ],
      "env": {
        "STACKOVERFLOW_API_KEY": "<STACKOVERFLOW_API_KEY>"
      }
    }
  }
}

Codex CLI

Register the server with OpenAI's Codex CLI — run this once, or add the equivalent block to ~/.codex/config.toml:

codex mcp add stackoverflow --env STACKOVERFLOW_API_KEY=<STACKOVERFLOW_API_KEY> -- npx -y @gscalzo/stackoverflow-mcp

# or add to ~/.codex/config.toml:
[mcp_servers.stackoverflow]
command = "npx"
args = ["-y", "@gscalzo/stackoverflow-mcp"]
[mcp_servers.stackoverflow.env]
STACKOVERFLOW_API_KEY = "<STACKOVERFLOW_API_KEY>"

OpenClaw

OpenClaw reads MCP servers from the mcp.servers section of ~/.openclaw/openclaw.json (managed via `openclaw mcp add` or the mcporter skill):

{
  "mcp": {
    "servers": {
      "stackoverflow": {
        "command": "npx",
        "args": [
          "-y",
          "@gscalzo/stackoverflow-mcp"
        ],
        "env": {
          "STACKOVERFLOW_API_KEY": "<STACKOVERFLOW_API_KEY>"
        }
      }
    }
  }
}

Replace the <PLACEHOLDER> values with your own credentials — see the configuration table below.

Configuration

Stack Overflow MCP Server reads the following environment variable:

VariableRequired
STACKOVERFLOW_API_KEYOptional

README.md

Stackoverflow MCP Server

A Model Context Protocol server for querying Stack Overflow. This server helps AI models find solutions to programming problems by searching Stack Overflow questions and answers.

Features

  • Search by error messages
  • Search by programming language and technology tags
  • Stack trace analysis
  • Filter results by score/votes
  • Include question and answer comments
  • Output in JSON or Markdown format

Installation

You can run the server directly using npx:

npx -y @gscalzo/stackoverflow-mcp

Or install it globally:

npm install -g @gscalzo/stackoverflow-mcp

Configure the Server

Create or modify your MCP settings file:

  • For Claude.app: ~/Library/Application Support/Cursor/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
  • For Claude Desktop: ~/Library/Application Support/Claude/claude_desktop_config.json

Add the following configuration:

{
  "mcpServers": {
    "stackoverflow": {
      "command": "npx",
      "args": ["-y", "@gscalzo/stackoverflow-mcp"],
      "env": {
        "STACKOVERFLOW_API_KEY": "your-api-key-optional"
      },
      "disabled": false,
      "autoApprove": []
    }
  }
}

Optional: Stack Overflow API Authentication

The server works without authentication but has rate limits. To increase the rate limits:

  1. Get an API key from Stack Apps
  2. Add the API key to your MCP settings configuration

Usage

The server provides three main tools:

1. search_by_error

Searches Stack Overflow for error-related questions:

interface SearchByErrorInput {
  errorMessage: string;          // Required: Error message to search for
  language?: string;            // Optional: Programming language
  technologies?: string[];      // Optional: Related technologies
  minScore?: number;           // Optional: Minimum score threshold
  includeComments?: boolean;    // Optional: Include comments in results
  responseFormat?: "json" | "markdown"; // Optional: Response format
  limit?: number;              // Optional: Maximum number of results
}

2. search_by_tags

Searches Stack Overflow questions by tags:

interface SearchByTagsInput {
  tags: string[];              // Required: Tags to search for
  minScore?: number;          // Optional: Minimum score threshold
  includeComments?: boolean;   // Optional: Include comments in results
  responseFormat?: "json" | "markdown"; // Optional: Response format
  limit?: number;             // Optional: Maximum number of results
}

3. analyze_stack_trace

Analyzes stack traces to find relevant solutions:

interface StackTraceInput {
  stackTrace: string;          // Required: Stack trace to analyze
  language: string;           // Required: Programming language
  includeComments?: boolean;   // Optional: Include comments in results
  responseFormat?: "json" | "markdown"; // Optional: Response format
  limit?: number;             // Optional: Maximum number of results
}

Examples

Searching by Error Message

{
  "name": "search_by_error",
  "arguments": {
    "errorMessage": "TypeError: Cannot read property 'length' of undefined",
    "language": "javascript",
    "technologies": ["react"],
    "minScore": 5,
    "includeComments": true,
    "responseFormat": "markdown",
    "limit": 3
  }
}

Searching by Tags

{
  "name": "search_by_tags",
  "arguments": {
    "tags": ["python", "pandas", "dataframe"],
    "minScore": 10,
    "includeComments": true,
    "responseFormat": "json",
    "limit": 5
  }
}

Analyzing Stack Trace

{
  "name": "analyze_stack_trace",
  "arguments": {
    "stackTrace": "Error: ENOENT: no such file or directory, open 'config.json'\n    at Object.openSync (fs.js:476:3)\n    at Object.readFileSync (fs.js:377:35)",
    "language": "javascript",
    "includeComments": true,
    "responseFormat": "markdown",
    "limit": 3
  }
}

Response Format

JSON Output

Responses include:

  • Question details (title, body, score, tags, etc.)
  • Answers (sorted by votes)
  • Optional comments for both questions and answers
  • Links to the original Stack Overflow posts

Markdown Output

The markdown format provides a nicely formatted view with:

  • Question title and score
  • Question body
  • Comments (if requested)
  • Answers with acceptance status and score
  • Answer comments (if requested)
  • Links to the original posts

Development

  1. Build in watch mode:
npm run watch
  1. Run tests:
npm test

Contributing

  1. Fork the repository
  2. Create a feature branch
  3. Commit your changes
  4. Push to the branch
  5. Create a Pull Request

License

MIT

See related servers & alternatives →

Related MCP servers

Browse all →

Related guides

Hand-picked reading to help you choose and use Search servers.