# ArcKnowledge (Custom RAG)

> Use this tool when you need to integrate custom knowledge bases with AI assistants, enabling retrieval-augmented generation capabilities for text and image queries. It solves problems of accessing specialized knowledge repositories and multi-source information retrieval, providing a configurable interface for managing multiple knowledge sources and handling API authentication. Ideal for applications requiring custom RAG implementations or visual context support.

Canonical page: https://skillsregistry.net/skills/arcknowledge-custom-rag  
JSON: https://api.skillsregistry.net/v1/skills/arcknowledge-custom-rag

## Description

ArcKnowledge is a FastMCP server that bridges AI assistants to custom knowledge base API webhooks, enabling retrieval-augmented generation (RAG) capabilities. Built with Python using the FastMCP framework, it manages multiple knowledge sources through a configurable JSON structure, supports both text and image queries, and handles API authentication. The implementation provides tools for querying knowledge bases, managing document sources, and processing images, making it particularly useful for applications requiring access to specialized knowledge repositories, custom RAG implementations, or multi-source information retrieval with visual context support.

## 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:** media
- **Updated:** 2026-04-25

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/arcknowledge-custom-rag)
- **Repository:** <https://github.com/dragonjump/mcp-arcknowledge>

## 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": "arcknowledge-custom-rag"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/arcknowledge-custom-rag` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/arcknowledge-custom-rag/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