Allows retrieving citation data in BibTeX format for DOIs via the CiteAs service
Enables searching Google Scholar and retrieving BibTeX-formatted citations with configurable result counts
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., "@cite-mcp get BibTeX for https://arxiv.org/abs/2303.08774"
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 Model Context Protocol server that provides BibTeX-formatted citation data from CiteAs and Google Scholar. Enhance your research workflow by integrating citation retrieval directly into your applications.
get_citeas_data - Retrieve BibTeX-formatted citation for the specified resource from the CiteAs
resource (string, required): DOI, URL, keyword
get_scholar_data - Retrieve BibTeX-formatted citations from the Google Scholar
query (string, required): Search query
results (integer, optional): Number of results (default: 2)
Related MCP server: bib-enrich-mcp
On MacOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json
On Windows: %APPDATA%/Claude/claude_desktop_config.json
Development/Unpublished Servers Configuration:
"mcpServers": {
"reference-mcp": {
"command": "uv",
"args": [
"--directory",
"/path/to/project/dir",
"run",
"reference-mcp"
]
}
}Published Servers Configuration:
"mcpServers": {
"reference-mcp": {
"command": "uvx",
"args": [
"reference-mcp"
]
}
}To install reference-mcp for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @ndchikin/reference-mcp --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 /path/to/project/dir run reference-mcpUpon launching, the Inspector will display a URL that you can access in your browser to begin debugging.
Retrieve BibTeX-formatted citation for the specified resource (e.g., DOI, URL, keyword) from the CiteAs
| Name | Required | Description | Default |
|---|---|---|---|
| resource | 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. It states the tool retrieves data, implying a read-only operation, but doesn't cover important aspects like error handling, rate limits, authentication needs, or response format details beyond 'BibTeX-formatted'.
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 clearly states the tool's purpose and parameter usage. It's appropriately sized for a simple tool with one parameter, though it could be slightly more structured with separate usage guidance.
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 and output schema, the description is incomplete for a tool that presumably returns structured citation data. It doesn't explain what happens with invalid inputs, the format of returned BibTeX, or how this differs from the sibling tool's functionality.
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 description adds meaningful context by explaining that the 'resource' parameter can be a DOI, URL, or keyword, which goes beyond the schema's generic 'string' type. However, with 0% schema description coverage and only one parameter, this provides adequate but not comprehensive semantic information.
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 verb 'Retrieve' and the resource 'BibTeX-formatted citation', specifying it's from the CiteAs service. It distinguishes from the sibling tool 'get_scholar_data' by focusing on citation formatting rather than scholarly data, though the distinction could be more explicit.
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 minimal guidance by mentioning the resource parameter can be a DOI, URL, or keyword, but offers no explicit advice on when to use this tool versus the sibling 'get_scholar_data'. It lacks context on alternatives or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Retrieve results BibTeX-formatted citations for publications matching the query from the Google Scholar
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | ||
| results | No |
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. It mentions the retrieval action and output format but lacks details on rate limits, authentication needs, error handling, or what happens if no results are found. This is a significant gap for a tool that likely interacts with an external API.
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 with no wasted words. It front-loads the key action and resource, making it easy to scan and understand 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 complexity of querying an external service like Google Scholar, no annotations, no output schema, and low schema coverage, the description is incomplete. It lacks crucial details such as response format beyond 'BibTeX-formatted', error cases, or usage constraints, leaving significant gaps for an AI agent.
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?
Schema description coverage is 0%, so the schema provides no parameter descriptions. The description adds some semantics by explaining that 'query' matches publications and 'results' retrieves citations, but it doesn't specify query syntax, result limits, or default behavior beyond the schema's default value. It partially compensates but not fully.
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 verb ('Retrieve') and resource ('BibTeX-formatted citations for publications'), specifying the format and source (Google Scholar). It doesn't explicitly differentiate from the sibling tool 'get_citeas_data', but the purpose is well-defined and not tautological.
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?
No guidance is provided on when to use this tool versus the sibling 'get_citeas_data', nor any context about prerequisites, alternatives, or exclusions. The description only states what it does, not when it should be used.
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: get_citeas_data retrieves a citation for a specific resource (DOI, URL, keyword), while get_scholar_data searches for multiple publications matching a query. There is no overlap in functionality, making tool selection unambiguous.
Both tools follow a consistent verb_noun pattern (get_citeas_data and get_scholar_data), using the same verb 'get' and a descriptive noun indicating the data source. The naming is predictable and uniform throughout the set.
With only two tools, the server feels thin for a citation management domain. While the tools cover basic retrieval from two sources, there are no operations for managing citations (e.g., save, update, delete) or handling metadata, which limits functionality for typical agent workflows.
The tool set is severely incomplete for citation management. It only provides retrieval from two sources, lacking essential operations like creating, updating, deleting, or organizing citations. There are no tools for formatting, exporting, or integrating with reference managers, leaving significant gaps in the domain coverage.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Federated search of books and papers, BibTeX/RIS citations, open-access retrieval and reading.
Search papers, format citations in 60 styles, and verify bibliographies against scholarly sources.
Catch AI-fabricated citations (real DOI + fake title). Retraction, open-access, 10,000+ CSL styles.
ArXiv preprints + Google Scholar papers, with citation counts in one query.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/ndchikin/reference-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
