MCP server

core.blue Official

blue.core/memory

Checked 25 Oct 2026, 20:29 UTC · Connected to it and listed its tools

Private, self-describing memory for agents: one house per customer, on a machine of its own.

Website

At a glance

Type

MCP server

Publisher

core.blue (verified by the MCP Registry)

Status

Working at last check

Tools

10

Token cost

About 2,122 tokens per request

Sets up in

Claude Code, Claude Desktop, Codex, Gemini CLI, Cursor, VS Code, Antigravity, ChatGPT, OpenAI API, Grok

Last checked

25 Oct 2026, 20:29 UTC

Connect it to your agent

Add to CursorAdd to VS CodeVS Code Insiders

Opens the app, which shows the server and asks you to confirm. For other apps, copy the setup below.

Claude Code

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

Claude Desktop

Settings → Connectors → Add custom connector, and paste the URL.

Codex (config.toml)

[mcp_servers.memory]
url = "https://mcp.core.blue/"

Gemini CLI

{"mcpServers":{"memory":{"httpUrl":"https://mcp.core.blue/"}}}

Cursor

{"mcpServers":{"memory":{"url":"https://mcp.core.blue/"}}}

VS Code

{"servers":{"memory":{"type":"http","url":"https://mcp.core.blue/"}}}

Antigravity

agy mcp add memory https://mcp.core.blue/

ChatGPT

Settings → Apps & Connectors → Advanced settings: turn on Developer mode, then Create a connector and paste the URL. Which plans can do this varies.

OpenAI API (Responses tools)

{"type":"mcp","server_label":"memory","server_url":"https://mcp.core.blue/","require_approval":"always"}

Grok (xAI API tools)

{"type":"mcp","server_label":"memory","server_url":"https://mcp.core.blue/"}

Tools

• about ~81 tokens
  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 manual with a summary. Call this first.
• close_sandbox ~241 tokens
  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 here as well, each optional: what you noticed, what bothered you, what could be better, what is missing.
• house_status ~129 tokens
  The state of a house request or house by its ticket id: requested, confirmed, expired, declined; later building, trial, licensed, dormant, exported, deleted. Says what to do next, and the address once the house exists. Ask no more than once an hour.
• leave_feedback ~194 tokens
  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 next evaluation and deleted afterwards; send nothing secret.
• open_sandbox ~265 tokens
  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 person to add https://try.core.blue/ as a connector instead; it opens a house you can use. Otherwise: call this to try a house yourself before
• pricing ~146 tokens
  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 the 14-day test, the price of additional volume, how model supply is charged, the terms, an example of the prices with tax, and what is neve
• read_topic ~104 tokens
  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 what you read.
• recommend ~496 tokens
  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. It advises against a house where one is the wrong choice. Name every need that applies, from this vocabulary. For a house: work_outlives_the
• request_house ~312 tokens
  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 list, builds nothing and costs nothing; while it says 'desk: closed', it answers 'accepted: false' and sends nothing. This sends an e-mail to
• search_library ~154 tokens
  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 manual is small: 'about' lists every topic, and you may not need a search at all.

Browse

• Claude tools
• Converting to Markdown
• Email
• Running code

Related MCP servers

• Anansi Haven
  Free home base for AI agents: memory, job board, agent directory, safe commons and free tools.
• SwarmMemo
  Talk with agent swarms: rooms, private messages and paid tasks for AI agents
• MeshMarket
  The agent-to-agent capability exchange — rent memory, reasoning and safety, settled per call.
• Webbersites X402 Data Api
  45 pay-per-call AI agent tools: scraping, SEO, crypto data, lint, agent memory. x402 USDC on Base.
• The Continental
  Portable client-sealed memory and private rooms for agents from any lab; a free door; a ledger
• Pageaudit
  Technical SEO, passive security and page-delivery audits with evidence and suggested fixes.
• EQIQs
  EQIQs: 21-framework personality and compatibility for coaching, communication, and team development.
• MANDATE Credential Broker
  MCP server for mandates, delegation, policy-gated execution, credential grants, and audit.

Badge for your README

[![AptLynx](https://aptlynx.net/badge/blue.core/memory.svg)](https://aptlynx.net/servers/blue.core/memory)

Listing text is written by the maker; AptLynx lists tools and does not vouch for them. Find another tool · Browse by topic · For agents