# mcp-context-engine

> mcp-context-engine — habaandrei-mcp-context-engine. Use this tool when you need to maintain persistent context for AI assistants across multiple sessions and tool calls. It solves the problem of state loss by tracking tasks, epics, and dependencies in a database, ensuring agents retain perfect state. The mcp-context-engine takes in task and dependency data as input and outputs a unified context, making it ideal for use cases requiring continuous workflow management.

Canonical page: https://skillsregistry.net/skills/habaandrei-mcp-context-engine  
JSON: https://api.skillsregistry.net/v1/skills/habaandrei-mcp-context-engine

## Description

MCP server that acts as a persistent context engine for AI assistants: task, epic and dependency tracking in SQLite/PostgreSQL so agents keep perfect state across tool calls and sessions

## Trust

- **Trust score (0–1):** 0.90
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** MIT
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/HabaAndrei/mcp-context-engine)

## 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": "habaandrei-mcp-context-engine"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/habaandrei-mcp-context-engine` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/habaandrei-mcp-context-engine/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