Schema | paper-mcp

paper-mcp

Describes the environment variables required to run the server.

Name	Required	Description	Default
`PAPER_MCP_CACHE_DIR`	No	Where PDFs and markdown are cached	%LOCALAPPDATA%\paper-mcp\Cache
`PAPER_MCP_LOG_LEVEL`	No	Log level (logs go to stderr)	INFO
`PAPER_MCP_MAX_CACHE_BYTES`	No	Cache size budget (oldest files evicted first)	2 GiB

Features and capabilities supported by this server

Capability	Details
`tools`	{ "listChanged": true }
`logging`	{}
`prompts`	{ "listChanged": false }
`resources`	{ "subscribe": false, "listChanged": false }
`extensions`	{ "io.modelcontextprotocol/ui": {} }
`experimental`	{}

Functions exposed to the LLM to take actions

Name	Description
search_papersA	Search arXiv for papers matching a query, optionally filtered by category.
get_paperA	Fetch full metadata and the abstract of a single arXiv paper.
read_paperA	Download an arXiv paper, convert it to markdown, and return its text (paginated). Also returns markdown_path: the cached file holding the FULL text, which can be Read/Grep'd directly instead of paging.
list_categoriesA	List known arXiv category codes and their display names.
cache_infoA	Show the location and size of the local PDF/markdown cache.
clear_cacheA	Delete cached files for one paper, or the entire cache.

Interactive templates invoked by user choice

Name	Description
`summarize-paper`	Summarize an arXiv paper at a chosen length and audience level
`ask-paper`	Answer a question about an arXiv paper, grounded in its full text

Contextual data attached and managed by the client

Name	Description
No resources

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Friedemann12/paper-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server