@cyanheads/stackexchange-mcp-server

Public Hosted Server: https://stackexchange.caseyjhand.com/mcp

Tools

Five tools for working with Stack Overflow and the wider Stack Exchange network:

stackexchange_search_questions

Search questions across any Stack Exchange site.

• Full-text search with optional tag filters, minimum score threshold, and accepted-only filter

• Sort by relevance, votes, activity, or newest

• Returns question ID, title, score, answer count, tags, and excerpt — IDs flow directly into stackexchange_get_thread

• Quota remaining surfaced on every response so agents can plan around rate limits

stackexchange_get_thread

Fetch a complete Q&A thread in one call — the server's primary value-add.

• Accepts a numeric question ID or a full Stack Exchange question URL

• Fetches question body + all answers in parallel (two upstream calls via Promise.all)

• HTML→markdown normalization baked in: <pre><code> → fenced code blocks, <p>, <a>, lists, headers, blockquotes all converted

• Accepted answer always first, then sorted by score descending

• Attribution (author display name + profile link + score) included on each answer per CC BY-SA 4.0

• Configurable maxAnswers (default 10, up to 100)

stackexchange_get_tag_faq

Browse the authoritative community answers on a topic.

• Maps to /tags/{tag}/faq — the highest-voted answered questions in a tag

• Returns question list without bodies; pipe any result into stackexchange_get_thread for full content

• Useful for "what are the canonical resources on Python async?" type queries

stackexchange_get_user

Credibility context for an answer author.

• Fetches profile + top tags in parallel (two upstream calls)

• Returns reputation, badge counts (gold/silver/bronze), location, website, post counts, and top 10 tags by answer score

• owner.user_id from stackexchange_get_thread output can be passed directly

stackexchange_list_sites

Discover api_site_parameter values for any Stack Exchange community.

• Fetches the full ~190-site network list live; optional case-insensitive name filter applied client-side

• The api_site_parameter value (e.g. stackoverflow, superuser, serverfault) is what every other tool's site parameter accepts

Related MCP server: StackOverflow MCP Server

Features

Built on @cyanheads/mcp-ts-core:

• Declarative tool definitions — single file per primitive, framework handles registration and validation

• Unified error handling — handlers throw, framework catches, classifies, and formats

• Pluggable auth: none, jwt, oauth

• Swappable storage backends: in-memory, filesystem, Supabase, Cloudflare KV/R2/D1

• Structured logging with optional OpenTelemetry tracing

• STDIO and Streamable HTTP transports

Stack Exchange-specific:

• Custom HTML→markdown normalizer covers the full SE post tag set with no external dependencies

• Backoff tracking: respects the backoff field in SE API responses to avoid throttling

• Quota logging: quota_remaining and quota_max surfaced via enrichment on every tool call

• Typed error contracts on every tool — invalid_site, invalid_parameter, invalid_api_key, invalid_id_or_url, invalid_user_id, question_not_found, user_not_found, paging_depth_limit, quota_exceeded, and upstream_unavailable

• Parallel upstream calls in get_thread and get_user via Promise.all

• Optional STACKEXCHANGE_API_KEY lifts the per-IP quota from ~300/day to ~10,000/day with no OAuth required

Agent-friendly output:

• Quota remaining on every response — agents can plan around rate limits without the server needing to fail

• Accepted-answer-first ordering is hardcoded — the community's explicit quality signal, not a preference

• Attribution on every answer per CC BY-SA 4.0 — provenance preserved without agent effort

• Typed not_found errors for missing questions and users (SE returns HTTP 200 with empty items[] — the server handles this correctly)

Getting started

Public Hosted Instance

A public instance is available at https://stackexchange.caseyjhand.com/mcp — no installation required. Point any MCP client at it via Streamable HTTP:

{
  "mcpServers": {
    "stackexchange-mcp-server": {
      "type": "streamable-http",
      "url": "https://stackexchange.caseyjhand.com/mcp"
    }
  }
}

Self-Hosted / Local

Add the following to your MCP client configuration file.

{
  "mcpServers": {
    "stackexchange": {
      "type": "stdio",
      "command": "bunx",
      "args": ["@cyanheads/stackexchange-mcp-server@latest"],
      "env": {
        "MCP_TRANSPORT_TYPE": "stdio",
        "MCP_LOG_LEVEL": "info"
      }
    }
  }
}

Or with npx (no Bun required):

{
  "mcpServers": {
    "stackexchange": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@cyanheads/stackexchange-mcp-server@latest"],
      "env": {
        "MCP_TRANSPORT_TYPE": "stdio",
        "MCP_LOG_LEVEL": "info"
      }
    }
  }
}

Or with Docker:

{
  "mcpServers": {
    "stackexchange": {
      "type": "stdio",
      "command": "docker",
      "args": [
        "run", "-i", "--rm",
        "-e", "MCP_TRANSPORT_TYPE=stdio",
        "ghcr.io/cyanheads/stackexchange-mcp-server:latest"
      ]
    }
  }
}

For Streamable HTTP, set the transport and start the server:

MCP_TRANSPORT_TYPE=http MCP_HTTP_PORT=3010 bun run start:http
# Server listens at http://localhost:3010/mcp

Rate limits: The Stack Exchange API allows ~300 requests/day per IP without a key. Set STACKEXCHANGE_API_KEY in env to lift this to ~10,000/day. Register a key at stackapps.com/apps/oauth/register (the OAuth flow is only required for write access — a key alone is sufficient for read-only use).

Prerequisites

• Bun v1.3.0 or higher (or Node.js v24+)

• A STACKEXCHANGE_API_KEY is optional but strongly recommended for any sustained use

Installation

1. Clone the repository:

git clone https://github.com/cyanheads/stackexchange-mcp-server.git

2. Navigate into the directory:

cd stackexchange-mcp-server

3. Install dependencies:

bun install

4. Configure environment:

cp .env.example .env
# edit .env and set STACKEXCHANGE_API_KEY if desired

Configuration

See .env.example for the full list of optional overrides.

Running the server

Local development

• Build and run:

  # One-time build
  bun run rebuild
  
  # Run the built server
  bun run start:stdio
  # or
  bun run start:http

• Run checks and tests:

  bun run devcheck   # Lint, format, typecheck, security
  bun run test       # Vitest test suite
  bun run lint:mcp   # Validate MCP definitions against spec

Docker

docker build -t stackexchange-mcp-server .
docker run --rm -e STACKEXCHANGE_API_KEY=your-key -p 3010:3010 stackexchange-mcp-server

The Dockerfile defaults to HTTP transport, stateless session mode, and logs to /var/log/stackexchange-mcp-server. OpenTelemetry peer dependencies are installed by default — build with --build-arg OTEL_ENABLED=false to omit them.

Project structure

Development guide

See CLAUDE.md/AGENTS.md for development guidelines and architectural rules. The short version:

• Handlers throw, framework catches — no try/catch in tool logic

• Use ctx.log for request-scoped logging, ctx.state for tenant-scoped storage

• Register new tools via the barrel in src/mcp-server/tools/definitions/index.ts

• Wrap external API calls: validate raw → normalize to domain type → return output schema; never fabricate missing fields

Contributing

Issues and pull requests are welcome. Run checks and tests before submitting:

bun run devcheck
bun run test

License

Apache-2.0 — see LICENSE for details.