# Seahorse RAG MCP

> Use this tool when you need to enable high-precision, offline search and memory for AI agents, connecting related facts across passages with graph-backed retrieval. It solves problems of knowledge retrieval and memory for edge devices, providing a local memory server for efficient information access. Ideal for use cases requiring offline capability and high-accuracy search, with input of natural language queries and output of relevant, context-specific information.

Canonical page: https://skillsregistry.net/skills/pch8286-seahorse-rag-mcp  
JSON: https://api.skillsregistry.net/v1/skills/pch8286-seahorse-rag-mcp

## Description

A local MCP memory server for edge devices that uses graph-backed retrieval to connect related facts across passages, enabling high-precision, offline capable search and memory for agents.

## Trust

- **Trust score (0–1):** 0.23
- **Verification tier:** scanned
- **Last scanned:** 2026-08-31

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-08-31

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/ctl4b9vmbo)
- **Repository:** <https://github.com/pch8286/seahorse-rag-mcp>

## 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": "pch8286-seahorse-rag-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/pch8286-seahorse-rag-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/pch8286-seahorse-rag-mcp/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