Summary
Wraps the StackExchange API v2.3 to let Claude search and retrieve data from Stack Overflow and the broader StackExchange network. No authentication required for read operations, which keeps setup simple. Hosted by Pipeworx as a streamable HTTP endpoint, so you point your MCP client at their gateway URL and skip local server setup. The repo mentions an ask_pipeworx tool that interprets natural language questions and routes them to the right API calls automatically. Useful when you want Claude to pull programming solutions, troubleshooting threads, or technical discussions directly from StackExchange during a conversation. Part of a larger gateway offering 250+ data sources if you need broader coverage.
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →mcp-stackexchange
StackExchange MCP — wraps the StackExchange API v2.3 (free, no auth required for read)
Part of Pipeworx — an MCP gateway connecting AI agents to 1476+ live data sources.
Tools
| Tool | Description |
|---|---|
search_questions | Search for questions on StackOverflow or any StackExchange site. Returns title, body, score, answer count, tags, and link. |
get_answers | Get answers for a specific StackExchange question by ID. Returns answer body, score, and whether it is accepted. |
stack_get_user | Look up a StackExchange user by numeric ID. Returns display name, reputation, badges (gold/silver/bronze counts), location, website, account age, last access, and per-site activity counts (questions/answers). Works on any StackExchange site (default: stackoverflow). |
list_questions_by_tag | Browse questions by TAG, sorted by votes or recency — answers "top questions tagged ", "trending questions this week/month", "most-voted questions". Returns title, score, answer count, whether answered, view count, tags, and link (call get_answers with a returned question_id to read answers). Combine tags with ";" for AND (e.g. "kubernetes;helm"). Distinct from search_questions, which is keyword-based. |
stack_tags | List or search StackOverflow / StackExchange tags with question counts and synonym info — top tags by popularity, tags matching a name fragment, or stats for specific tags. Answers "most popular StackOverflow tags", "how many questions are tagged X", "which tags have more than N questions". Example: stack_tags({ sort: "popular", limit: 20 }) or stack_tags({ inname: "python" }) |
Quick Start
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"stackexchange": {
"url": "https://gateway.pipeworx.io/stackexchange/mcp"
}
}
}
What this endpoint actually serves
tools/list at https://gateway.pipeworx.io/stackexchange/mcp returns the tools in the table
above plus the shared Pipeworx meta-tools — ask_pipeworx,
discover_tools, search_within, remember/recall and the rest of the
gateway-wide set. So the tool count you see is larger than this table: a
single-pack endpoint currently lists roughly 30 shared tools alongside the
pack's own. The connection's initialize response states its exact scope, and
is the authoritative answer for a given day.
This is deliberate, not multiplexing by accident. The meta-tools are what let a
scoped connection answer a question this pack does not cover — via
ask_pipeworx, which routes across the whole catalog — without you adding a
second MCP server. There is currently no way to mount a pack endpoint without
them; if the extra schemas cost you more context than the routing is worth,
connect to the full gateway once rather than to several pack endpoints.
Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:
{
"mcpServers": {
"pipeworx": {
"url": "https://gateway.pipeworx.io/mcp"
}
}
}
Both URLs reach the same gateway and the same 1476+ data sources. The
only difference is which pack's tools are listed directly; ask_pipeworx
reaches all of them from either one.
Using with ask_pipeworx
Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:
ask_pipeworx({ question: "your question about Stackexchange data" })
The gateway picks the right tool and fills the arguments automatically.
More
License
MIT
Featured
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →