About stackexchange-mcp-server
An MCP server for people researching Stack Exchange sites, including Stack Overflow, that searches questions, retrieves full Q&A threads, and looks up tag FAQs and user profiles. Thread content is converted to markdown, with the accepted answer placed first.
Key features
- 01Search questions by text and tags
- 02Fetch Q&A threads as markdown
- 03Browse tag FAQ questions
- 04Retrieve user profiles and top tags
- 05List Stack Exchange sites
Use cases
- 01Find answers across Stack Exchange sites
- 02Read a question with its answers and comments
- 03Review highly voted answers for a tag
- 04Check a contributor’s profile and top tags
MCP support
Exposes five Stack Exchange search and lookup tools to MCP clients. It supports STDIO and Streamable HTTP, with a public hosted endpoint.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://stackexchange.caseyjhand.com/mcpclaude mcp add --transport http cyanheads-stackexchange https://stackexchange.caseyjhand.com/mcp{"mcpServers":{"cyanheads-stackexchange":{"type":"http","url":"https://stackexchange.caseyjhand.com/mcp"}}}Open in Cursor{"servers":{"cyanheads-stackexchange":{"type":"http","url":"https://stackexchange.caseyjhand.com/mcp"}}}Open in VS Code{"mcpServers":{"cyanheads-stackexchange":{"type":"http","url":"https://stackexchange.caseyjhand.com/mcp"}}}{"mcpServers":{"cyanheads-stackexchange":{"serverUrl":"https://stackexchange.caseyjhand.com/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
5| Parameter | Type | Required | Description |
|---|---|---|---|
| filter | string | No | Optional case-insensitive name filter — returns only sites whose name contains all provided tokens. Omit to return all sites. |
Details
From the project README@cyanheads/stackexchange-mcp-server
Search Stack Exchange questions, fetch complete Q&A threads as clean markdown, browse tag FAQs, and look up user profiles via MCP. STDIO or Streamable HTTP.
Public Hosted Server: https://stackexchange.caseyjhand.com/mcp
Overview
Stack Overflow and the rest of the Stack Exchange network, from Super User and Server Fault to Unix & Linux. Search questions, read complete Q&A threads as clean markdown, browse tag FAQs, and look up user profiles.
Tools
| Tool | Description |
|---|---|
stackexchange_search_questions | Search questions across a Stack Exchange site with full-text query, tag filters, score threshold, and sort order |
stackexchange_get_thread | Fetch a question and its answers as markdown, with a configurable answer limit and the accepted answer first |
stackexchange_get_tag_faq | Fetch the highest-voted answered questions for a tag — the canonical "best answers in X" list |
stackexchange_get_user | Fetch a user profile by ID: reputation, badge counts, top tags by answer score, and account metadata |
stackexchange_list_sites | Enumerate all Stack Exchange network sites and their api_site_parameter values |
Capability reference
stackexchange_search_questions tool
- Full-text query with optional tag filters, minimum score threshold, and accepted-only filter; sort by relevance (default), votes, activity, or newest
- Up to 30 results per page (default 10);
pagefor more — each page costs one API quota unit, and paging past 25 requiresSTACKEXCHANGE_API_KEY - Returns question ID, title, score, answer count, tags, and a ~300-character excerpt — IDs flow directly into
stackexchange_get_thread - Quota remaining and max surfaced via enrichment on every response
stackexchange_get_thread tool
- Accepts a numeric question ID or a full Stack Exchange question URL; fetches the question and a page of
maxAnswersanswers (1–100, default 10), adding the accepted answer if it falls outside that page - HTML→markdown normalization built in — code blocks, links, lists, headers, and blockquotes all converted
- Optional
includeCommentsfetches up to 20 comments per post, newest first, using two extra API calls (one when there are no answers);commentsTruncatedreports partial lists - Attribution (author name, profile link, score) on every answer per CC BY-SA 4.0
- Quota remaining and max surfaced via enrichment;
truncatedwhen more answers exist upstream thanmaxAnswersreturned
stackexchange_get_tag_faq tool
- Highest-voted answered questions for a tag — maps to
/tags/{tag}/faq, the canonical "best answers in X" list - Up to 30 results per page (default 10);
pagefor more — each page costs one API quota unit, and paging past 25 requiresSTACKEXCHANGE_API_KEY - Returns a question list without bodies; pipe any
questionIdintostackexchange_get_threadfor full content - Quota remaining and max surfaced via enrichment on every response
stackexchange_get_user tool
userIdmust be at most 2,147,483,647 (32-bit) — typically theauthorUserIdfromstackexchange_get_threadoutput- Fetches the profile and top tags in two upstream API calls
- Returns reputation, badge counts (gold/silver/bronze), location, website, answer/question counts, and up to 10 top tags by answer score (empty array for users with no answers)
- An unknown user ID returns a typed
user_not_founderror — Stack Exchange answers HTTP 200 with empty results rather than 404
stackexchange_list_sites tool
- Fetches every site in the Stack Exchange network, walking pages of 100 up to a 10-page cap; an enrichment notice flags a partial list if the network still has more
- Optional case-insensitive name filter matches against site name and
api_site_parameter, applied client-side after the fetch - Returns the
api_site_parametervalue (e.g.stackoverflow,superuser,serverfault) that every other tool'ssiteparameter accepts
Features
Built on @cyanheads/mcp-ts-core: stdio and Streamable HTTP transports, pluggable auth (none / jwt / oauth), swappable storage (in-memory, filesystem, Supabase, Cloudflare KV/R2/D1), structured logging with optional OpenTelemetry tracing.
Stack Exchange-specific:
- HTML→markdown conversion preserves code blocks, tables, links, images, and nested lists
- Shared upstream queue honors response backoff and HTTP 429 cooldowns; each operation has a 50-second budget covering queue time, backoff, requests, and retries
- Quota logging:
quota_remainingandquota_maxsurfaced 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, andupstream_unavailable - Optional
STACKEXCHANGE_API_KEYlifts 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
- The accepted answer appears first, followed by the remaining answers sorted by score
- Each answer includes attribution under CC BY-SA 4.0
- Typed
not_founderrors for missing questions and users (SE returns HTTP 200 with emptyitems[]rather than 404)
Getting started
Public Hosted Instance
A public instance is available at https://stackexchange.caseyjhand.com/mcp — no installation required. It serves Streamable HTTP; each client takes its own config shape.
For Claude Code:
claude mcp add --transport http stackexchange-mcp-server https://stackexchange.caseyjhand.com/mcp
For Cline (cline_mcp_settings.json):
{
"mcpServers": {
"stackexchange-mcp-server": {
"type": "streamableHttp",
"url": "https://stackexchange.caseyjhand.com/mcp"
}
}
}
For Cursor (mcp.json):
{
"mcpServers": {
"stackexchange-mcp-server": {
"url": "https://stackexchange.caseyjhand.com/mcp"
}
}
}
Claude Desktop adds remote servers under Settings → Connectors.
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 v1.4.0 or higher (or Node.js v24+)
- A
STACKEXCHANGE_API_KEYis optional but strongly recommended for any sustained use
Installation
- Clone the repository:
git clone https://github.com/cyanheads/stackexchange-mcp-server.git
- Navigate into the directory:
cd stackexchange-mcp-server
- Install dependencies:
bun install
- Configure environment:
cp .env.example .env
# edit .env and set STACKEXCHANGE_API_KEY if desired
Configuration
| Variable | Description | Default |
|---|---|---|
STACKEXCHANGE_API_KEY | Optional. Stack Exchange API key — lifts per-IP quota from ~300/day to ~10,000/day. | — |
MCP_TRANSPORT_TYPE | Transport: stdio or http. | stdio |
MCP_HTTP_PORT | Port for HTTP server. | 3010 |
MCP_HTTP_HOST | Host for HTTP server. | 127.0.0.1 |
MCP_SESSION_MODE | HTTP session mode: auto, stateful, or stateless. auto resolves to stateful. A meaningful env value overrides this server's stateless source default; blank or unsubstituted placeholders use the source default. | stateless |
MCP_AUTH_MODE | Auth mode: none, jwt, or oauth. | none |
MCP_LOG_LEVEL | Log level (RFC 5424). | info |
LOGS_DIR | Directory for log files (Node.js only). | <project-root>/logs |
LOG_TOOL_FAILURE_PAYLOADS | Log each failed tool call's arguments and result, redacted by key name and capped at LOG_TOOL_FAILURE_PAYLOAD_MAX_BYTES (default 16384). A secret inside a free-form value is not redacted. | false |
STORAGE_PROVIDER_TYPE | Storage backend. | in-memory |
OTEL_ENABLED | Enable OpenTelemetry instrumentation (spans, metrics, completion logs). | false |
OTEL_EXPORTER_OTLP_LOGS_ENDPOINT | Opt-in OTLP log export (e.g. http://localhost:4318/v1/logs); the base OTEL_EXPORTER_OTLP_ENDPOINT never enables it. | — |
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
| Path | Purpose |
|---|---|
src/index.ts | createApp() entry point — registers tools and inits services. |
src/config/ | Server-specific environment variable parsing with Zod (STACKEXCHANGE_API_KEY). |
src/mcp-server/tools/ | Tool definitions (*.tool.ts). |
src/services/stackexchange/ | Stack Exchange API v2.3 HTTP client, backoff tracking, quota logging, HTML→markdown normalizer. |
tests/ | Vitest unit and integration tests. |
docs/ | Design document and directory tree. |
Development guide
See CLAUDE.md/AGENTS.md for development guidelines and architectural rules. The short version:
- Handlers throw, framework catches — no
try/catchin tool logic - Use
ctx.logfor request-scoped logging,ctx.statefor 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 are welcome. Run checks and tests before submitting:
bun run devcheck
bun run test
License
Apache-2.0 — see LICENSE for details.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.