# AgentCortex MCP

> Use this tool when you need to manage multiple codebases with isolated knowledge retention, solving context-switching problems and enabling persistent memory across sessions. The AgentCortex MCP takes in codebase data as input and outputs isolated, persistent memory banks for each project, keeping knowledge separate and accessible. Ideal for use in multi-project development environments where context switching is frequent.

Canonical page: https://skillsregistry.net/skills/sage-hq-agentcortex-mcp  
JSON: https://api.skillsregistry.net/v1/skills/sage-hq-agentcortex-mcp

## Description

An AI memory system that creates isolated, persistent memory banks for each codebase, solving the context-switching problem by keeping project knowledge separate and accessible across sessions.

## Trust

- **Trust score (0–1):** 0.99
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** other
- **Updated:** 2026-09-19

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/qndhk32ax8)
- **Repository:** <https://github.com/sage-hq/agentcortex-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": "sage-hq-agentcortex-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/sage-hq-agentcortex-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/sage-hq-agentcortex-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