The MCP Scholarly Server allows you to search for academic articles across multiple scholarly platforms:
Search arXiv for articles using keywords
Search Google Scholar for articles using keywords
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@MCP Scholarly Server search for recent papers about quantum computing algorithms"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A MCP server to search for accurate academic articles. More scholarly vendors will be added soon.
search-arxiv — arXiv search (no key needed)
search-google-scholar — Google Scholar via the scholarly library (free proxy pool)
search-google-web — Google web search via the SerpBase API. Optional; only registered when SERPBASE_API_KEY is set. Get a key at https://serpbase.dev/dashboard/api-keys (free tier available).
Related MCP server: arXiv MCP Server
The server implements one tool:
search-arxiv: Search arxiv for articles related to the given keyword.
Takes "keyword" as required string arguments
On MacOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json
On Windows: %APPDATA%/Claude/claude_desktop_config.json
or if you are using Docker
To install mcp-scholarly for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install mcp-scholarly --client claudeTo prepare the package for distribution:
Sync dependencies and update lockfile:
uv syncBuild package distributions:
uv buildThis will create source and wheel distributions in the dist/ directory.
Publish to PyPI:
uv publishNote: You'll need to set PyPI credentials via environment variables or command flags:
Token: --token or UV_PUBLISH_TOKEN
Or username/password: --username/UV_PUBLISH_USERNAME and --password/UV_PUBLISH_PASSWORD
Since MCP servers run over stdio, debugging can be challenging. For the best debugging experience, we strongly recommend using the MCP Inspector.
You can launch the MCP Inspector via npm with this command:
npx @modelcontextprotocol/inspector uv --directory /Users/adityakarnam/PycharmProjects/mcp-scholarly/mcp-scholarly run mcp-scholarlyUpon launching, the Inspector will display a URL that you can access in your browser to begin debugging.
zorp needs a search-capable MCP tool
before validate will run. This server satisfies that check, because zorp
matches on a search verb in the tool name and these tools are called
search-arxiv and search-google-scholar.
zorp-agent --yes \
--mcp "stdio:scholarly:uv:run:mcp-scholarly" \
validate "<your research question>"Or configure it once, so every run picks it up:
# .zorp/mcp.toml
[[server]]
name = "scholarly"
transport = "stdio"
command = "uv"
args = ["run", "mcp-scholarly"]
trust = "sandbox"
timeout_secs = 60Notes measured against zorp's transport, not assumed:
search-arxiv answers in about 1 second. zorp's default stdio read
budget is 30 seconds, so the default is comfortable. timeout_secs = 60
above is headroom for search-google-scholar, which goes through
scholarly and a free proxy pool and is far less predictable.
Logging goes to stderr. Nothing but JSON-RPC reaches stdout, which is what zorp's newline-delimited framing requires.
An empty keyword comes back as an MCP tool error rather than an empty result set. zorp cares about that distinction: a failed search that looks like "no prior work" would put a wrong novelty score into an evidence record.
arxiv returns best-effort matches for any query, including nonsense, so a non-empty result set is not by itself evidence that prior work exists. The tool description says so, since that is the text the model reads.
Search arxiv for articles related to the given keyword.
| Name | Required | Description | Default |
|---|---|---|---|
| keyword | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure but offers minimal information. It mentions searching but doesn't cover aspects like rate limits, authentication needs, result formats, pagination, or error handling, which are critical for a search tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that gets straight to the point without unnecessary words. It's appropriately sized for a simple tool, though it could be slightly more informative without losing conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (a search function with one parameter) and the lack of annotations and output schema, the description is incomplete. It doesn't address behavioral traits, parameter details, or expected outputs, making it inadequate for effective agent use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 0% description coverage, so the description must compensate but adds little beyond the schema. It implies 'keyword' is used for searching but doesn't explain its semantics, such as how it's matched (e.g., title, abstract, full-text) or any constraints, leaving the parameter poorly defined.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose with a specific verb ('search') and resource ('arxiv for articles'), making it immediately understandable. However, it doesn't differentiate from its sibling tool 'search-google-scholar' beyond mentioning the platform, which prevents a perfect score.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus its sibling 'search-google-scholar' or any alternatives. It lacks context about use cases, exclusions, or prerequisites, leaving the agent without direction for tool selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search google scholar for articles related to the given keyword.
| Name | Required | Description | Default |
|---|---|---|---|
| keyword | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It only states the basic action of searching, without mentioning rate limits, authentication needs, result formats, pagination, or potential side effects. This is inadequate for a search tool with zero annotation coverage.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that directly states the tool's function without unnecessary words. It is appropriately sized and front-loaded, making it easy to parse quickly.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of annotations, no output schema, and low schema description coverage, the description is incomplete. It doesn't address behavioral aspects like result handling or limitations, nor does it provide enough context for effective use in a multi-tool environment with a sibling tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema description coverage is 0%, and the description adds minimal value beyond the schema. It mentions 'keyword' as the input but doesn't explain what constitutes a valid keyword, how it's used in the search, or any constraints. With one undocumented parameter, the description fails to compensate for the coverage gap.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose as searching Google Scholar for articles related to a keyword, providing a specific verb ('search') and resource ('Google Scholar articles'). However, it doesn't explicitly differentiate from its sibling tool 'search-arxiv', which likely searches a different academic database, so it doesn't reach the highest score.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. It doesn't mention the sibling tool 'search-arxiv' or any other search options, nor does it specify contexts where Google Scholar is preferred over other databases. This leaves the agent with minimal usage direction.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
The two tools have clearly distinct purposes: one searches ArXiv specifically, while the other searches Google Scholar. There is no overlap in their functionality, and an agent can easily choose the appropriate tool based on the desired academic database.
Both tools follow a consistent verb_noun pattern with 'search' as the verb and the database name as the noun (arxiv, google-scholar). The naming is uniform and predictable across the set.
With only 2 tools, the server feels thin for a 'Scholarly Server' that might be expected to handle broader academic tasks. While search is a core function, typical scholarly workflows could benefit from additional tools like fetching article details, citations, or managing references.
The server is severely incomplete for a scholarly domain, as it only provides search functionality without any tools for retrieving full articles, accessing metadata, or performing follow-up actions like citation analysis. This leaves significant gaps that could hinder agent workflows.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Academic research search across PubMed and arXiv
Academic paper search, scientific literature, citation analysis, arXiv & semantic related-work.
Search arXiv/Semantic Scholar/OpenAlex + medical evidence (PubMed/Europe PMC) + LaTeX/PDF tools.
Find academic papers across major sources like arXiv, PubMed, bioRxiv, and more. Download PDFs whe…
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/adityak74/mcp-scholarly'
If you have feedback or need assistance with the MCP directory API, please join our Discord server