paperstack
by Aldrin-Joan
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| S2_API_KEY | No | Optional Semantic Scholar API key for higher rate limits | |
| MAX_RETRIES | No | Maximum number of retries for HTTP requests | 3 |
| GITHUB_TOKEN | No | Optional GitHub token for higher API rate limits | |
| HTTP_TIMEOUT | No | Timeout in seconds for HTTP requests | 60 |
| OLLAMA_MODEL | No | Ollama model name | mistral |
| ARXIV_DB_PATH | No | Path to the SQLite workflow database | ${ARXIV_DOWNLOAD_DIR}/arxiv_mcp.db |
| DIFF_CACHE_TTL | No | TTL in seconds for diff cache (default 24 hours) | 86400 |
| LINK_CACHE_TTL | No | TTL in seconds for code link cache (default 48 hours) | 172800 |
| ARXIV_CACHE_DIR | No | Directory for caching downloaded PDFs | ./downloads |
| ARXIV_CACHE_TTL | No | TTL in seconds for cache entries (default 7 days) | 604800 |
| ARXIV_KEEP_PDFS | No | Whether to keep PDFs after parsing | false |
| EMBEDDING_MODEL | No | Embedding model for semantic similarity | sentence-transformers/all-MiniLM-L6-v2 |
| OLLAMA_BASE_URL | No | Base URL for Ollama server | http://localhost:11434 |
| REPRO_CACHE_TTL | No | TTL in seconds for reproducibility cache (default 7 days) | 604800 |
| ARXIV_RATE_LIMIT | No | Rate limit for arXiv API requests per second | 1 |
| GITHUB_MAX_FILES | No | Maximum number of files to analyze from a GitHub repository | 20 |
| CHUNK_SIZE_TOKENS | No | Token chunk size for context building | 800 |
| ARXIV_DOWNLOAD_DIR | No | Directory for downloaded PDFs (used in MCP config) | ${workspaceFolder}/downloads |
| CITATION_CACHE_TTL | No | TTL in seconds for citation cache (default 24 hours) | 86400 |
| SEMANTIC_INDEX_DIR | No | Directory for semantic index storage | ${ARXIV_DOWNLOAD_DIR}/semantic_index |
| CHUNK_OVERLAP_TOKENS | No | Token overlap between chunks | 100 |
| ARXIV_RATE_LIMIT_DELAY | No | Delay in seconds between arXiv API calls | 3.0 |
| CONTRIBUTION_CACHE_TTL | No | TTL in seconds for contribution cache (default 7 days) | 604800 |
| GITHUB_MAX_FILE_SIZE_KB | No | Maximum file size in KB for GitHub file analysis | 50 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Aldrin-Joan/paperstack'
If you have feedback or need assistance with the MCP directory API, please join our Discord server