marginalia
This server has a remotely hosted endpoint. Open its connector listing for connection details, authentication requirements, and setup instructions:
mcp-marginalia
Marginalia MCP — independent web search over a non-commercial, non-SEO index.
Part of Pipeworx — an MCP gateway connecting AI agents to 1865+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.
Tools
Tool | Description |
| Search the INDEPENDENT Marginalia web index — a separate crawler that favours text-heavy, ad-light, non-commercial pages: personal sites, technical writing, documentation, forums, academic and hobbyist pages. Use it when mainstream search results are dominated by SEO content, listicles, and marketing pages, or when you want a second opinion from an index that is NOT Google/Bing-derived (unlike serper_search / exa_search / serpapi). Especially good for programming and niche technical topics, obscure or historical subjects, and finding primary/hobbyist sources. Returns url, title, description, a quality score, and how many other results share the domain. Weak for breaking news, e-commerce, and mainstream/celebrity topics — use serper_search for those. Results are CC-BY-NC-SA 4.0 licensed; the licence is returned with every response. |
Related MCP server: keyless-web-search-mcp
Quick Start
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"marginalia": {
"url": "https://gateway.pipeworx.io/marginalia/mcp"
}
}
}What this endpoint actually serves
tools/list at https://gateway.pipeworx.io/marginalia/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 1865+ data sources. The
only difference is which pack's tools are listed directly; ask_pipeworx
reaches all of them from either one.
No MCP client? Call it over HTTP
curl -X POST https://gateway.pipeworx.io/v1/tools/marginalia_search \
-H 'Content-Type: application/json' \
-d '{"query":"rust async runtime internals"}'No account needed for the first calls. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/marginalia_search. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.
Run it from npm
@pipeworx/mcp-marginalia is a local stdio bridge to the Pipeworx gateway: your MCP client
starts it with npx, and it forwards every call to the same
https://gateway.pipeworx.io/marginalia/mcp endpoint shown above. It needs network access;
there is no offline mode.
{
"mcpServers": {
"marginalia": {
"command": "npx",
"args": ["-y", "@pipeworx/mcp-marginalia"]
}
}
}Without a key it calls anonymously, capped at 50 calls a day. A free account
raises that to 200 a day: get a key at https://pipeworx.io/signup and add
"env": { "PIPEWORX_API_KEY": "<your key>" } to the server entry.
The key is sent as a Bearer token, the same way a hosted connection sends it,
so calls are metered and billed exactly as they are there.
It lists only this pack's tools by default. Set PIPEWORX_META_TOOLS=1 to
also list ask_pipeworx and the other gateway-wide tools.
Behind an HTTPS proxy: Node's built-in fetch does not read HTTPS_PROXY by
default. Newer Node releases honour it when NODE_USE_ENV_PROXY=1 is set; check
your Node version's documentation.
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 Marginalia data" })The gateway picks the right tool and fills the arguments automatically.
More
License
MIT
Related MCP Connectors
Search independent software the big engines bury: indie apps, open-source repos, and dev tools.
Web search with quality scores; web pages are read on your computer by the local server.
Independent, EU, privacy-focused web search for AI agents. 25 free searches/day.
Full-text search over web pages published on IPFS. Free, no key.
Related MCP Servers
- AlicenseAqualityDmaintenanceEnables private web search and webpage content extraction using a local SearxNG instance, prioritizing user privacy and autonomy.22MIT
- FlicenseAqualityCmaintenanceEnables keyless web search across multiple engines with fallback and relevance ranking, plus anonymous HTTP(S) page fetching, all without API keys or vendor dependencies.21-
- FlicenseNot gradedqualityCmaintenanceProvides ad-filtered web search and full-page content reading, including multi-page and JavaScript-rendered pages, with source verification and configurable search providers.-
- AlicenseNot gradedqualityCmaintenanceEnables keyless local web search and page fetching through MCP, with domain-filtered queries, extractable original-text evidence, hashes, and snapshot cursors for verifiable, traceable results.16 npmMIT