search-arxiv
Search arxiv for articles related to the given keyword.
LABSCO SUMMARY
Two literature sources behind one keyword, with nothing to set up in between.
The whole surface is a pair of searches, each taking a single keyword — no date range, no author, no category. That makes it a first look rather than a research instrument: you find out which names keep appearing, then go elsewhere for the papers themselves. One caution the tool description states outright: arXiv returns best-effort matches for any query, so results coming back is not on its own evidence that prior work exists.
What it is
A small literature-search server: one keyword search against arXiv, one against Google Scholar, and an optional web search when a key for it is present.
What you get
- arXiv searched by keyword for related articles, with no key needed and an answer in about a second
- Google Scholar searched by keyword through the scholarly library and its free proxy pool — the same question, against reviewed literature
- A Google web search registered as a third tool when SERPBASE_API_KEY is set, and absent otherwise
- An empty keyword comes back as a tool error rather than an empty result set, so a failed search is never mistaken for "nothing has been published"
Requirements
uv on the machine and nothing else — no account or key for the two search tools. Both take a keyword and nothing more: there is no date range, author or category argument to narrow with. Allow more time for the Scholar side than the arXiv side; it goes through a free proxy pool and is far less predictable. MIT.
Setup effort
One command — uvx mcp-scholarly
USE CASES
01
Checking whether an idea is already in the literature
Put the same keyword to both sources in one turn: the preprint server for what is new, the citation index for what has been through review.
02
Finding the published version of a preprint
Search the title terms in the citation index to see whether the work has appeared somewhere citable since it was posted.
03
Getting a reading list started from a term you just learned
One keyword returns the arXiv papers that use it, which is usually enough to find the names and the phrasing the field actually uses.
2 tools
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
search-google-scholar
Search google scholar for articles related to the given keyword.
BEFORE YOU INSTALL
What to know first
Tools you get
2 tools when we connected; the project documents 3. search-google-web appears only when SERPBASE_API_KEY is set. An older section of the documentation says the server has one tool; that line is out of date.
Requires
uvx on PATH
INSTALLATION
Connect your client
Server setup
TERMINAL
uvx mcp-scholarlyMCP Clients
Claude Desktop — uvx
CLAUDE DESKTOP — UVX · JSON
{
"mcpServers": {
"mcp-scholarly": {
"command": "uvx",
"args": [
"mcp-scholarly"
]
}
}
}Claude Desktop — Docker
CLAUDE DESKTOP — DOCKER · JSON
{
"mcpServers": {
"mcp-scholarly": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"mcp/scholarly"
]
}
}
}Zorp
ZORP · JSON
{
"server": [
{
"name": "scholarly",
"transport": "stdio",
"command": "uv",
"args": [
"run",
"mcp-scholarly"
],
"trust": "sandbox",
"timeout_secs": 60
}
]
}
