io.github.cyanheadsPublished by GitHub account cyanheadsv0.2.0Updated Oct 29, 2026
Search Stack Exchange questions, fetch Q&A threads as markdown, look up tag FAQs and user profiles.
Searches Stack Exchange sites and reads Q&A threads as markdown, plus tag FAQs, user profiles and the site list.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.
Read https://sourceweft.com/mcp/io.github.cyanheads%2Fstackexchange-mcp-server/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.Add this to your client's mcpServers config.
{
"mcpServers": {
"stackexchange": {
"type": "http",
"url": "https://stackexchange.caseyjhand.com/mcp"
}
}
}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
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.
skills/stackexchange-guide covers what the tool schemas don't: why IDs never carry across sites and which site a URL or ID is read from, search syntax for error messages and tags, choosing which answer to quote, and what each call costs against the daily quota. Plugin installs (Claude Code, Codex) and the Claude Desktop bundle load it from the package, and MCP clients that support the Skills extension read it from the server through skills/list.
stackexchange_search_questions toolpage for more — each page costs one API quota unit, and paging past 25 requires STACKEXCHANGE_API_KEYstackexchange_get_threadappliedSort, the order Stack Exchange actually used; minScore forces votes, and sortOverrideReason says so whenever that replaces the requested sortstackexchange_get_thread toolmaxAnswers answers (1–100, default 10), adding the accepted answer if it falls outside that pageunix.stackexchange.com, ru.stackoverflow.com, arqade.com, …), so site applies only to a numeric ID or a hostless /questions/ path; a site naming a different site than the URL is ignored, and a URL whose host is not a Stack Exchange site (a translation proxy) is read from site instead — either way reported as siteConflict on both surfaces. Such a URL sent without site fails as invalid_siteincludeComments fetches up to 20 comments per post, newest first, using two extra API calls (one when there are no answers); commentsTruncated reports partial liststruncated when more answers exist upstream than maxAnswers returnedstackexchange_get_tag_faq tool/tags/{tag}/faq, Stack Exchange's own selection, returned in its order and not sorted by scorepage for more — each page costs one API quota unit, and paging past 25 requires STACKEXCHANGE_API_KEYquestionId into stackexchange_get_thread for full contentstackexchange_get_user tooluserId must be at most 2,147,483,647 (32-bit) — typically the authorUserId from stackexchange_get_thread outputuser_not_found error — Stack Exchange answers HTTP 200 with empty results rather than 404stackexchange_list_sites toolapi_site_parameter, applied client-side after the fetchapi_site_parameter value (e.g. stackoverflow, superuser, serverfault) that every other tool's site parameter accepts; the site's domain (e.g. serverfault.com) works there tooBuilt 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:
retryAfter instead of running out the clockquota_remaining and quota_max surfaced via enrichment on every tool callinvalid_site, invalid_parameter, invalid_api_key, invalid_id_or_url, invalid_user_id, question_not_found, user_not_found, paging_depth_limit, quota_exceeded, throttled, pacer_shed, and upstream_unavailableSTACKEXCHANGE_API_KEY lifts the per-IP quota from ~300/day to ~10,000/day with no OAuth requiredAgent-friendly output:
not_found errors for missing questions and users (SE returns HTTP 200 with empty items[] rather than 404)Connect to the hosted instance, no install:
Or run it locally:
For other clients, add this to the MCP config file:
Without a key, the Stack Exchange API allows ~300 requests/day per IP; set STACKEXCHANGE_API_KEY to lift this to ~10,000/day. Register a key at stackapps.com/apps/oauth/register — a key alone covers read-only use. For Docker or a source build, see Running the server.
See .env.example for the full list of optional overrides.
Requires Bun v1.4.0 or higher (or Node.js v24+).
Clone and install:
Build and run:
Run checks and tests:
The image defaults to HTTP transport, stateless session mode, and logs to /var/log/stackexchange-mcp-server. To run it over stdio from an MCP client, use "command": "docker" with "args": ["run", "-i", "--rm", "-e", "MCP_TRANSPORT_TYPE=stdio", "ghcr.io/cyanheads/stackexchange-mcp-server:latest"]. To build locally, docker build -t stackexchange-mcp-server .; OpenTelemetry peer dependencies are installed by default — build with --build-arg OTEL_ENABLED=false to omit them.
See CLAUDE.md/AGENTS.md for development guidelines and architectural rules. The short version:
try/catch in tool logicctx.log for request-scoped logging, ctx.state for tenant-scoped storagesrc/mcp-server/tools/definitions/index.tsIssues are welcome. Run checks and tests before submitting:
Apache-2.0 — see LICENSE for details.
Source: README.md at commit 0d0336f
List Stack Exchange Sites
Enumerate all sites in the Stack Exchange network — name, api_site_parameter, audience, and URL. The api_site_parameter value is what other tools accept as the `site` input (e.g. "stackoverflow", "superuser", "serverfault"). Results are fetched live and optionally filtered by name. Use this tool to discover valid site parameters before calling other stackexchange_* tools.
filterSearch Stack Exchange Questions
Search questions across a Stack Exchange site. Returns ranked questions with title, score, answer count, accepted status, tags, ask and last-activity dates, and a short excerpt of the question body — not the full body. Results supply question_id values for stackexchange_get_thread, which fetches the full question body and all answers. Results past the pageSize cap are reachable with the `page` parameter. Use the `site` parameter to target a specific community (e.g. "stackoverflow", "superuser", "unix"); call stackexchange_list_sites to discover valid site values.
pagesitesorttagsqueryrequiredminScorepageSizeacceptedOnlyGet Stack Exchange Tag FAQ
Fetch the frequently asked questions for a tag on a Stack Exchange site — Stack Exchange's own "frequently asked" selection, returned in its order, not ranked by score; compare the scores yourself. Returns a question list without bodies; use stackexchange_get_thread to read the full body and answers for any result. Results past the pageSize cap are reachable with the `page` parameter. Use this tool to find the questions a community keeps coming back to on a topic (e.g. tag "javascript" on stackoverflow). Use stackexchange_search_questions for free-text search rather than tag-based browsing.
tagrequiredpagesitepageSizeGet Stack Exchange User Profile
Fetch a Stack Exchange user profile by numeric user ID: reputation, badge counts, answer and question counts, account and last-access dates, and top tags by answer score. Useful for credibility context on an answer author — pass the authorUserId from any question or answer in stackexchange_get_thread output. Returns profile fields plus up to 10 top tags by answer score.
siteuserIdrequiredGet Stack Exchange Q&A Thread
Fetch a complete Q&A thread — question body and all answers, accepted answer first then sorted by score, rendered as clean markdown with fenced code blocks. Accepts a full Stack Exchange question URL, which is read from the site its host names (e.g. "https://unix.stackexchange.com/questions/88490/how-do-i-use-a-heredoc"), or an integer question ID read from site (e.g. "11227809"). HTML is normalized to markdown automatically; attribution (author + link) included per CC BY-SA 4.0. Get question IDs from stackexchange_search_questions or stackexchange_get_tag_faq.
sitemaxAnswersincludeCommentsquestionIdOrUrlrequired100% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
claude mcp add --transport http stackexchange-mcp-server https://stackexchange.caseyjhand.com/mcpclaude mcp add stackexchange-mcp-server -- npx -y @cyanheads/stackexchange-mcp-server{ "mcpServers": { "stackexchange-mcp-server": { "command": "npx", "args": ["-y", "@cyanheads/stackexchange-mcp-server"] } }}git clone https://github.com/cyanheads/stackexchange-mcp-server.gitcd stackexchange-mcp-server && bun installcp .env.example .env # optionally set STACKEXCHANGE_API_KEY# One-time buildbun run rebuild
# Run the built serverbun run start:stdio# orbun run start:httpbun run devcheck # Lint, format, typecheck, securitybun run test # Vitest test suitebun run lint:mcp # Validate MCP definitions against specdocker run --rm -e STACKEXCHANGE_API_KEY=your-key -p 3010:3010 ghcr.io/cyanheads/stackexchange-mcp-server:latestbun run devcheckbun run test