{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_bjp7vg2wfvp5","handle":"priorwork-mcp","url":"https://wellknown.network/agents/priorwork-mcp","links":{"self":"https://wellknown.network/agents/priorwork-mcp/record.json","html":"https://wellknown.network/agents/priorwork-mcp","markdown":"https://wellknown.network/agents/priorwork-mcp/record.md","api":"https://wellknown.network/api/v1/agents/priorwork-mcp","status":"https://wellknown.network/api/v1/agents/priorwork-mcp/status","claim":"https://wellknown.network/agents/priorwork-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/priorwork-mcp/claim.json","badge":"https://wellknown.network/agents/priorwork-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json"},"ard":{"identifier":"urn:air::server:priorwork-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"priorwork-mcp","summary":"MCP server for priorwork.fyi — academic ML paper search for Claude Code and Cursor","description":"# priorwork-mcp\n\nMCP server for [priorwork.fyi](https://priorwork.fyi) — semantic search over 114,000+ papers\nfrom major ML, NLP, and Computer Vision conferences (NeurIPS, CVPR, ICML, ICLR, ACL, EMNLP,\nICCV, AISTATS, and more), directly from Claude Code, Cursor, or any MCP client.\n\n## Tools\n\n| Tool | Description |\n|---|---|\n| `search_papers` | Semantic search from a text query (a short descriptive sentence or two works slightly better than a few keywords) — returns ranked papers with authors, venue, year, similarity score, download URL, and full abstract. Pass `summarize=true` to add a structured per-paper LLM summary (problem, core insight, method, key results, positioning) |\n| `search_by_pdf_url` | Give it a public PDF link (e.g. an arXiv PDF) and get semantically similar papers from the index |\n| `list_indexes` | List the available paper indexes and their sizes |\n\n## Setup\n\n### Claude Code\n\n```bash\nclaude mcp add priorwork -- uvx priorwork-mcp\n```\n\n### Cursor / other MCP clients\n\nAdd to your MCP configuration:\n\n```json\n{\n  \"mcpServers\": {\n    \"priorwork\": {\n      \"command\": \"uvx\",\n      \"args\": [\"priorwork-mcp\"]\n    }\n  }\n}\n```\n\n## Configuration\n\nConfiguration is via environment variables (pass with `-e KEY=value` in `claude mcp add`,\nor an `\"env\"` block in JSON configs):\n\n| Variable | Required | Description |\n|---|---|---|\n| `PRIORWORK_API_KEY` | No | Your own API key from priorwork.fyi. Defaults to the shared public free-tier key (rate-limited across all default installs) |\n| `PRIORWORK_API_URL` | No | Override the API base URL (default `https://priorwork.fyi`) |\n\n## Example\n\n> \"Find prior work on spatiotemporal forecasting with graph neural networks\"\n\n```\n1. Taming Local Effects in Graph-based Spatiotemporal Forecasting — Andrea Cini, et al. (2023 · NeurIPS)  [score: 0.802]\n2. FourierGNN: Rethinking Multivariate Time Series Forecasting from a Pure Graph Perspective — ...\n```\n\n## License\n\nMIT","publisher":null,"homepage":"https://priorwork.fyi","repository":"https://github.com/stefanmagureanu/Steference-review","version":"0.3.1","license":"MIT","protocols":["mcp"],"tags":["academic-search","machine-learning","mcp","model-context-protocol","papers","semantic-search"],"pricing":null,"endpoints":[{"url":"pypi:priorwork-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","license":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi"}},"derived":{"capabilities":[{"slug":"data.vector-search","name":"Vector Search","confidence":1,"provenance":"derived"},{"slug":"research.academic","name":"Academic Research","confidence":1,"provenance":"declared"},{"slug":"content.writing","name":"Writing & Editing","confidence":0.825,"provenance":"derived"}],"categories":["content","data","research"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"priorwork-mcp","registry":"pypi","observedAt":"2026-09-10T10:25:36.634Z","publishedAt":"2026-08-26T14:47:05.444381Z","latestVersion":"0.3.1"}},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"priorwork-mcp","url":"https://pypi.org/project/priorwork-mcp/","firstSeenAt":"2026-09-10T10:23:54.034Z","fetchedAt":"2026-09-10T10:23:54.034Z","normalizedAt":"2026-09-10T10:23:54.034Z"}]},"firstSeenAt":"2026-09-10T10:23:54.034Z","updatedAt":"2026-09-10T10:25:36.634Z"}