# SciTrace MCP Server

> SciTrace MCP Server — mobai-read-scitrace. Use this tool when you need to record and query complex reasoning steps, offloading trace data for efficient memory management and persistent cross-session access. It solves problems of data overload and limited context window capacity, enabling AI agents to retrieve and analyze reasoning steps stored in SQLite. Ideal for use cases requiring transparent and explainable AI decision-making, with support for Directed Acyclic Graphs (DAGs) and scalable data storage.

Canonical page: https://skillsregistry.net/skills/mobai-read-scitrace  
JSON: https://api.skillsregistry.net/v1/skills/mobai-read-scitrace

## Description

Enables AI agents to record and query reasoning steps in SQLite, offloading trace data from the context window, with DAG support and persistent cross-session memory.

## Trust

- **Trust score (0–1):** 0.68
- **Verification tier:** scanned
- **Last scanned:** 2026-08-29

## Facts

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

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/dbuyuro3w6)
- **Repository:** <https://github.com/Mobai-read/scitrace>

## 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": "mobai-read-scitrace"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/mobai-read-scitrace` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/mobai-read-scitrace/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