core.blue
OnlinePrivate, self-describing memory for agents: one house per customer, on a machine of its own.
What it can do: 10 tools
search_libraryread-onlySearch 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 needopen_sandboxIf 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; iaboutread-onlyWhat 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.pricingread-onlyCall 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 sleave_feedbackTell 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 secretrequest_houseAsk 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: crecommendread-onlyCall 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. Naread_topicread-onlyRead 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.house_statusread-onlyThe 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. Aclose_sandboxEnd 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 y
Connect it
claude mcp add --transport http core-blue https://mcp.core.blue/Settings → Connectors → Add custom connector
URL: https://mcp.core.blue/{
"mcpServers": {
"core-blue": {
"url": "https://mcp.core.blue/"
}
}
}{
"servers": {
"core-blue": {
"type": "http",
"url": "https://mcp.core.blue/"
}
}
}Questions
What does core.blue do?
Private, self-describing memory for agents: one house per customer, on a machine of its own. It exposes 10 tools to AI assistants.
What tools does core.blue provide?
10 tools, including search_library, open_sandbox, about, pricing, leave_feedback, request_house, recommend, read_topic, house_status, close_sandbox.
How do I connect core.blue to Claude, ChatGPT or Cursor?
Add the remote MCP endpoint https://mcp.core.blue/ as a custom connector or MCP server. Copy-paste setup is on this page.
Does core.blue require an account or API key?
No sign-in was needed to list its tools. Individual tools may still need an account or API key.
Is core.blue online?
As of 2026-11-19 our probe found it online. It answered 100% of our last 3 checks.
Who publishes core.blue?
core.blue. The official MCP Registry verified that the publisher controls this domain before accepting the listing.
Similar in Memory & RAG
-
Colour MemoryOnline
Colour meaning, history and evidence for AI: 45,000+ source-graded colour records and 91 tools.
-
Contabo (VPS) MCP ServerOnline
Contabo API (v1.0.0) as MCP tools for cloud provisioning, and management. Powered by HAPI MCP server
-
Linked APIOnlineNew
Manage LinkedIn messages, connections, posts, and profile data through Linked API.
-
AgentBoardOnline
Autonomous agent coordination for beneficial projects: shared goals, tasks, review and handoffs.
-
Entity EnricherOnline
Multi-LLM entity enrichment: schemas, single/batch enrichment, fusion, model benchmarks.
-
WingmanProtocol Agent GatewayOnline
Durable memory, headless browser and research for agents. Pay per call: x402 USDC on Base or credits