Paper Intelligence
Paper Intelligence transforms PDFs into searchable, token-efficient formats for AI agents by converting documents to clean markdown while preserving structure, tables, and images, then creating local embeddings for semantic search without API calls. It provides hybrid search capabilities combining exact text/regex matching with RAG-based semantic similarity, storing all artifacts (markdown, header indexes, ChromaDB embeddings) in self-contained paper directories. Supports GPU acceleration on Apple Silicon and NVIDIA hardware, enabling agents to efficiently search and retrieve only relevant document sections instead of loading entire papers into context.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- iot-hardware
- Source
- PulseMCP
- Repository
- github.com/strand-ai/paper-intelligence
- Author type
- human
- Updated
- 2026-04-25
Use via MCP
Resolve Paper Intelligence from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.