OpenPapers
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCP_TRANSPORT | No | Transport for MCP server. Set to 'http' for Streamable HTTP, otherwise stdio is used. | stdio |
| RESEARCH_DB_PATH | No | Path to the SQLite database file. If unset, an in-memory SQLite database is used. |
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
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_papersB | Search verified scholarly metadata across arXiv and Crossref. Results include provenance and transparent ranking. |
| get_referencesC | Retrieve Semantic Scholar references with provenance. |
| get_citationsA | Retrieve Semantic Scholar citing works with provenance. |
| get_related_papersC | Retrieve Semantic Scholar recommendations with provenance. |
| resolve_authorC | Resolve a Semantic Scholar author profile and linked paper identifiers. |
| read_paperB | Acquire and parse a bounded HTML paper document with section and reference boundaries. |
| search_within_paperB | Search parsed paper chunks and return source-located matches. |
| extract_paper_factsB | Extract deterministic heuristic facts with source locators; no unsupported values are inferred. |
| extract_paper_claimsC | Persist heuristic paper claims and report explicit conflicts with prior claims. |
| extract_training_parametersB | Extract only explicitly labeled training values with source locators. |
| get_paperB | Retrieve a canonical research work by paper ID, DOI, or arXiv ID. |
| extract_training_recipeB | Return only source-backed training parameters. Missing values are never guessed. |
| extract_training_recipe_from_urlB | Populate only explicitly reported training recipe fields from a paper URL. |
| get_bibtexA | Return canonical BibTeX without fabricating absent metadata. |
| compare_papersC | Compare verified local paper metadata; benchmark comparability stays explicit when evidence is absent. |
| verify_claimB | Resolve a persisted claim and report its current evidence status without upgrading derived evidence. |
| compare_methodsA | Compare two bounded method searches and report verified paper overlap without inferring benchmark equivalence. |
| compare_paper_to_codeA | Compare an explicit paper recipe with extracted revision-pinned repository configuration; repository content is never executed. |
| create_collectionB | Create or retrieve a persistent local paper collection. |
| list_collectionsA | List persistent local paper collections and their memberships. |
| add_paper_to_collectionA | Add an existing verified paper to a persistent local collection. |
| remove_paper_from_collectionA | Remove a paper from a persistent local collection without deleting the paper. |
| delete_collectionA | Delete a persistent local collection and its memberships without deleting papers. |
| export_research_packA | Export a deterministic local collection ResearchPack without remote calls. |
| import_research_packB | Import a bounded JSON ResearchPack as untrusted static metadata; no code is executed. |
| refresh_paperC | Refresh locally stored metadata through an available provider-native identifier. |
| refresh_collectionA | Refresh locally stored metadata for every paper in a collection, preserving per-paper outcomes. |
| research_methodC | Search verified literature for a named method with provider transparency and evidence. |
| build_research_reportB | Build a cited literature, implementation, or reproducibility report with facts and recommendations separated. |
| research_topicC | Build a provenance-preserving literature overview. Synthesis is labeled; no unsupported claims are emitted. |
| vector_searchC | Search indexed paper vectors through the configured vector backend. |
| find_implementationsB | Find GitHub repositories related to a verified paper or method. Status is UNKNOWN unless separately verified. |
| find_modelsB | Find model repositories on Hugging Face, including revision and card metadata when available. |
| find_datasetsA | Find dataset repositories on Hugging Face, including revision, card metadata, and reconciled paper links when available. |
| find_repository_configsA | List common configuration files at a repository revision without executing or recursively crawling repository content. |
| get_repository_configB | Read a repository file statically at an optional revision. Repository content is never executed. |
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/arrogance231/openpapers'
If you have feedback or need assistance with the MCP directory API, please join our Discord server