# picsense

> picsense — honlnk-picsense. Use this tool when you need to enhance single-modal base models with multi-modal vision capabilities, such as iterative image recognition and document image parsing. It provides a local MCP server with API access, allowing for seamless integration and multi-turn processing. Ideal for applications requiring advanced image analysis and understanding, such as document scanning, image classification, and object detection.

Canonical page: https://skillsregistry.net/skills/honlnk-picsense  
JSON: https://api.skillsregistry.net/v1/skills/honlnk-picsense

## Description

Local MCP server that provides multi-modal vision capabilities to single-modal base models via API, supporting multi-turn iterative image recognition and document image parsing.

## Trust

- **Trust score (0–1):** 0.69
- **Verification tier:** scanned
- **Last scanned:** 2026-08-29

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** media
- **Updated:** 2026-08-29

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/hkmca6pqpa)
- **Repository:** <https://github.com/honlnk/picsense>

## 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": "honlnk-picsense"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/honlnk-picsense` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/honlnk-picsense/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