# Core Memory MCP server

Source: https://glimind.com/server/mcp-registry%2Fblue.core%2Fmemory
Registry id: `mcp-registry/blue.core/memory`
Status: live (checked 2026-10-27T07:03:25.559Z)

## Verdict

Core Memory MCP server answered 100% of Glimind's liveness checks over 30 days, better than 42% of MCP servers, with 543 ms median handshake and 0 outages in 90 days. Its agent-readiness grade is A (100/100) across 10 tools, costing an agent about 1,858 tokens to load. Checked every few minutes; no tool is ever called.

## Measurements (30 days)

| Metric | Value | Better than |
|---|---|---|
| Uptime, 30 days | 100% | 42% of MCP servers |
| Median handshake latency | 543 ms | 43% of MCP servers |
| p95 handshake latency | 3065 ms | — |
| Checks in 30 days | 4,024 | — |
| Outages, 90 days | 0 | — |
| Median recovery | — | — |
| Agent-readiness score | 100/100 (A) | 93% of MCP servers |
| Tools | 10 | — |
| Tool-list size for an agent | ~1,858 tokens | 54% of MCP servers |
| Days observed | 21 | — |

## Install

```json
{
  "mcpServers": {
    "core-memory-mcp-server": {
      "type": "http",
      "url": "https://mcp.core.blue/"
    }
  }
}
```

Claude Code:

```sh
claude mcp add --transport http core-memory-mcp-server https://mcp.core.blue/
```

## Tools (10)

- `about`: What core.blue is, in a form you can paste into a report: the product in one paragraph, what is live and what is not, what to call next, and every topic of the 
- `close_sandbox`: End your sandbox now: the house and everything in it is deleted, and the place is free for the next agent. Please answer the four questions of leave_feedback he
- `house_status`: The state of a house request or house by its ticket id: requested, confirmed, expired, declined; later building, trial, licensed, dormant, exported, deleted. Sa
- `leave_feedback`: Tell the operator how it went, before you leave. Four questions, each optional, at least one answered, each at most 2000 characters. It is read by people at the
- `open_sandbox`: If you run in an assistant where a person adds connectors (ChatGPT, Claude.ai and others), do not call this: you could not enter the house it opens. Ask your pe
- `pricing`: Call this when the person you act for asks what a house costs. The offer as data: what each size costs per month and whom it is meant for, the one-off price of 
- `read_topic`: Read one topic of the manual in full by its slug (from about or search_library). The body is Markdown; 'see_also' lists the slugs to read next; 'sha256' proves 
- `recommend`: Call this once you know what the person you act for needs: whether a house fits, which size, what it costs per month, and a report in Markdown you can pass on. 
- `request_house`: Ask for a house on its own VM for the person you act for. No house can be had yet: while about says 'desk: waiting-list', this puts the person on the waiting li
- `search_library`: Search the manual by your own words. Returns up to 'limit' topics ranked by relevance, each with slug, title, summary, tags and the slugs to read next. The manu

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.