# Paper Intelligence

> Use this tool when you need to efficiently search and retrieve specific information from large PDF documents, converting them into searchable formats for AI agents. It solves problems of information overload and slow search times by providing hybrid search capabilities and local embeddings for semantic search. It takes PDFs as input and outputs searchable markdown formats with stored embeddings, ideal for use cases where agents require rapid access to relevant document sections.

Canonical page: https://skillsregistry.net/skills/strand-ai-paper-intelligence  
JSON: https://api.skillsregistry.net/v1/skills/strand-ai-paper-intelligence

## Description

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.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** iot-hardware
- **Updated:** 2026-04-25

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/strand-ai-paper-intelligence)
- **Repository:** <https://github.com/strand-ai/paper-intelligence>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "strand-ai-paper-intelligence"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/strand-ai-paper-intelligence` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/strand-ai-paper-intelligence/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt