Skip to main content
Glama
stackexchange-mcp

stackexchange-mcp

by YashLimbani

stackexchange-mcp

An MCP server that lets your AI assistant search Stack Overflow and other Stack Exchange sites, read questions with their best answers, and ground its debugging help in real, voted answers instead of guessing.

  • Read-only: it never posts, votes or edits anything.

  • Model-friendly output: short summaries, Markdown instead of HTML, code blocks preserved, long posts truncated with a link.

  • Respects the API: optional API key, backoff handling, request spacing, retries, caching and quota tracking.

  • Clear errors: every failure tells the model what happened and what to try next.

Not affiliated with Stack Exchange, Inc. Content returned by the API is licensed CC BY-SA (3.0 or 4.0 depending on the post). The server returns the author, link and license so assistants can attribute it.

What it provides

[project] name = "mcp-server" version = "0.1.0" requires-python = ">=3.12" dependencies = [ "httpx>=0.28.1", "mcp[cli]>=1.0,<2", "pydantic>=2.14.2", ]

[dependency-groups] dev = [ "pytest>=9.2.0", ]

Tools

Tool

Use it to

search_questions

Find discussions about a topic. Filter by tags, site, sort order, accepted answers only.

get_question

Read one question with its best answers (accepted answer first).

search_by_error_message

Find threads for a pasted error or stack trace. File paths, line numbers and addresses are stripped before searching.

search_tags

Find exact tag names (so the assistant does not guess tags).

get_tag_overview

Get a technology's summary, question count and top-voted questions.

get_quota_status

See the remaining API quota and any active rate-limit wait.

Resources

URI

Contents

stackexchange://sites

Site slugs you can pass as site (cached for 24 hours).

stackexchange://help/search-tips

Guidance on effective searches.

stackexchange://quota

Live quota snapshot (JSON).

Prompts

Prompt

What it does

debug_error

Searches for your error, reads the best two threads, explains the likely fix with links.

compare_approaches

Compares two approaches using highly voted discussions.

tag_primer

Builds a beginner overview of a technology from its tag.

Related MCP server: Hivemind

Quick start

The server works without a key, but the anonymous quota is small: the API reported 300 requests per day without a key and 10,000 with one. Register an app on Stack Apps to get a key; you do not need OAuth for read-only use.

2. Install

You need uv. The server runs straight from PyPI:

uvx stackexchange-mcp

(That starts a stdio server and waits; you normally let your AI app launch it using one of the configs below.)

3. Connect your AI app

Use the full path to uvx if your app cannot find it (which uvx).

VS Code (GitHub Copilot, Agent mode) - .vscode/mcp.json:

{
  "servers": {
    "stackexchange": {
      "type": "stdio",
      "command": "uvx",
      "args": ["stackexchange-mcp"],
      "env": { "STACKEXCHANGE_KEY": "${input:se_key}" }
    }
  },
  "inputs": [
    {
      "type": "promptString",
      "id": "se_key",
      "description": "Stack Exchange API key",
      "password": true
    }
  ]
}

Antigravity CLI - .agents/mcp_config.json in your project (or ~/.gemini/config/mcp_config.json globally):

{
  "mcpServers": {
    "stackexchange": {
      "command": "uvx",
      "args": ["stackexchange-mcp"],
      "env": { "STACKEXCHANGE_KEY": "your-key" }
    }
  }
}

Start agy and run /mcp to confirm it is connected.

Claude Code:

claude mcp add --env STACKEXCHANGE_KEY=your-key stackexchange -- uvx stackexchange-mcp

Claude Desktop (macOS/Windows) and Cursor - same JSON shape as Antigravity (mcpServers), in claude_desktop_config.json or ~/.cursor/mcp.json.

Keep your key out of files you commit.

Configuration

Variable

Default

Purpose

STACKEXCHANGE_KEY

none

API key. Raises the daily quota.

SE_DEFAULT_SITE

stackoverflow

Site used when a tool call does not specify one.

SE_CACHE_TTL_SECONDS

300

How long identical requests are cached (0 disables caching).

SE_MAX_BODY_CHARS

2000

Maximum characters of any question or answer body returned.

Rate limits and errors

  • Identical requests within the cache window cost no quota.

  • If the API sends a backoff value, the server waits it out (up to 10 seconds) before the next call; longer waits are reported instead of blocking.

  • Requests are spaced at least 0.2 seconds apart.

  • Timeouts, network errors and 5xx responses are retried twice with exponential delay (0.5 s, then 1 s).

  • When the daily quota is exhausted the server stops calling the API until the next UTC day.

Situation

What the assistant is told

Invalid input (bad site, bad tag)

Which parameter is wrong and how to fix it.

Question or tag not found

It may be deleted or on another site; use search_tags.

No search results

Broaden the query, remove tags, or use search_tags.

Rate limited

How long to wait.

Quota exhausted

Set STACKEXCHANGE_KEY or wait for the daily reset.

Invalid API key

Check or unset STACKEXCHANGE_KEY.

Stack Exchange unavailable

Usually temporary; try again shortly.

The API key is never written to logs or error messages.

Example prompts

You do not need to name a tool. Things that should make the assistant use this server:

  • "What's the difference between asyncio.sleep and time.sleep? Check Stack Overflow."

  • "I get AttributeError: 'NoneType' object has no attribute 'foo' - find help on Stack Overflow." (paste the traceback)

  • "Is there a Stack Overflow tag for testing async code with pytest?"

  • "I'm new to python-asyncio. Give me an overview from Stack Overflow."

  • "Find recent discussions about Docker networking on Server Fault."

Tested with

Results for each prompt are in TESTING.md.

  • Antigravity CLI: connects and lists all 6 tools. In a 10-prompt run, the model picked the expected tool without being told its name in 9 of 10 prompts (one prompt still needs a re-run) and chose sensible arguments such as site, sort and accepted_only. It correctly used no tool for an unrelated question.

  • VS Code (Copilot Agent mode): the server starts and 6 tools are discovered; tool-call results are not recorded yet.

  • MCP Inspector: connects and lists the server's tools (re-check all resources and prompts before release).

Troubleshooting

  • Server "anonymous (low quota)" in the log: the key did not reach the server. Put STACKEXCHANGE_KEY in the env block of your client's config.

  • Command not found: use the absolute path of uvx in the config.

  • VS Code shows no tools: use a normal Copilot Agent mode chat session in a workspace that contains .vscode/mcp.json; some session types keep their own separate server list.

  • The assistant never calls a tool: ask it explicitly once ("search Stack Overflow for ...") and check the tool list in your client.

  • Logs: the server writes logs to stderr (never stdout, which carries the protocol). In VS Code, open the Output panel and choose the server.

Development

git clone https://github.com/YashLimbani/stackexchange-mcp
cd stackexchange-mcp
uv sync
uv run pytest -q
npx @modelcontextprotocol/inspector uv run stackexchange-mcp

Tests need no network: the API is mocked using real saved responses in samples/. See DESIGN.md for the design and CONTRIBUTING.md for how to help.

License

MIT for the code (see LICENSE). Stack Exchange content is CC BY-SA; attribute the author and link when you reuse it.

Available Tools

6 tools
get_questionA
Read-onlyIdempotent

Read one question in full, together with its best answers.

The question and answer bodies are returned as Markdown with code blocks preserved. Long posts are truncated and end with a link to the full text. Each item includes its author, link and license, so cite them when you use the content.

Inputs: question_id (required), site, max_answers. Returns: A question with its body and its best answers: the output of get_question.

get_quota_statusA
Read-onlyIdempotent

Show the remaining Stack Exchange API quota and any active rate-limit wait.

Call this if requests start failing, or before a large batch of searches.

Inputs: site. Returns: Output of get_quota_status.

get_tag_overviewA
Read-onlyIdempotent

Get a short description of a tag (a technology or topic) and its most-voted questions.

Use this to get oriented on an unfamiliar technology: it returns the tag's summary, how many questions use it, and the classic high-vote questions with links.

Inputs: tag (required), site, top_questions. Returns: Output of get_tag_overview.

search_by_error_messageA
Read-onlyIdempotent

Find Stack Overflow discussions that match an error message or stack trace.

Use this when the user pastes an error. The tool picks the most informative line and strips file paths, line numbers and memory addresses before searching; the query it actually used is returned as cleaned_query. Adding a language tag helps. Use get_question on a promising result to read the answers.

Inputs: error_message (required), site, tags, limit. Returns: Output of search_by_error_message: shows what was actually searched.

search_questionsA
Read-onlyIdempotent

Search Stack Overflow (or another Stack Exchange site) for questions about a topic.

Use this to find existing discussions and solutions. It returns short summaries (title, score, tags, link), not full text. To read a question and its answers, pass a question_id from the results to get_question.

Inputs: query (required), site, sort, tags, +2 more. Returns: note, results, has_more

search_tagsA
Read-onlyIdempotent

Find valid tag names containing some text, most popular first.

Use this before filtering other searches by tag, so you use tags that really exist instead of guessing (for example 'python-asyncio', not 'asyncio-python').

Inputs: query (required), site, limit. Returns: tags, has_more

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.1/5.0

    Scored across 6 tools

    Disambiguation4/5

    The set is mostly distinct: search_questions and search_by_error_message are the only close pair, but the error-specific input and cleaned_query output make the boundary clear. get_question, search_tags, get_tag_overview, and get_quota_status each serve a separate stage of discovery, retrieval, or runtime awareness.

    Naming Consistency5/5

    All tool names use snake_case with a consistent verb_noun shape such as search_questions, get_question, and get_tag_overview. search_by_error_message is slightly longer but still follows the same readable convention.

    Tool Count5/5

    Six tools is well scoped for a read-only Stack Exchange client. Each tool earns its place by covering a distinct workflow, and the set avoids unnecessary redundancy.

    Completeness4/5

    The surface covers discovery, full question and answer retrieval, tag lookup, and quota awareness. Minor gaps remain around explicit site discovery or fetching a single answer by ID, but get_question and search_tags cover the primary workflows.

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      Not graded
      quality
      D
      maintenance
      Provides instant access to a searchable knowledge base of 16,000+ community-driven troubleshooting solutions for common coding problems. Includes community feedback and smart ranking to help AI assistants find the most effective solutions.
      -
    • A
      license
      Not graded
      quality
      C
      maintenance
      Wraps the StackExchange API v2.3 to enable reading StackExchange data (questions, answers, etc.) without authentication. Allows AI agents to query StackExchange content through natural language or direct tool calls.
      286 npm
      1
      MIT