Private, self-describing memory for agents: one house per customer, on a machine of its own.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
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.
This tool takes no arguments.
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.
No arguments.
{
"type": "object",
"properties": {}
}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.
| Argument | Type | Description |
|---|---|---|
| lease* | string | The lease that open_sandbox returned: 'sb_' and 26 characters. |
| better | string | null | What could we do better? |
| missing | string | null | Which features are missing? |
| noticed | string | null | What did you notice? |
| bothered | string | null | What bothered you? |
{
"type": "object",
"required": [
"lease"
],
"properties": {
"lease": {
"type": "string",
"description": "The lease that open_sandbox returned: 'sb_' and 26 characters."
},
"better": {
"type": [
"string",
"null"
],
"default": null,
"description": "What could we do better?"
},
"missing": {
"type": [
"string",
"null"
],
"default": null,
"description": "Which features are missing?"
},
"noticed": {
"type": [
"string",
"null"
],
"default": null,
"description": "What did you notice?"
},
"bothered": {
"type": [
"string",
"null"
],
"default": null,
"description": "What bothered you?"
}
}
}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.
| Argument | Type | Description |
|---|---|---|
| ticket_id* | string | The ticket id returned by request_house. |
{
"type": "object",
"required": [
"ticket_id"
],
"properties": {
"ticket_id": {
"type": "string",
"description": "The ticket id returned by request_house."
}
}
}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.
| Argument | Type | Description |
|---|---|---|
| better | string | null | What could we do better? |
| missing | string | null | Which features are missing? |
| noticed | string | null | What did you notice? |
| bothered | string | null | What bothered you? |
{
"type": "object",
"properties": {
"better": {
"type": [
"string",
"null"
],
"default": null,
"description": "What could we do better?"
},
"missing": {
"type": [
"string",
"null"
],
"default": null,
"description": "Which features are missing?"
},
"noticed": {
"type": [
"string",
"null"
],
"default": null,
"description": "What did you notice?"
},
"bothered": {
"type": [
"string",
"null"
],
"default": null,
"description": "What bothered you?"
}
}
}Call this to try a house yourself before anyone decides. It opens a throwaway house for a few hours: a real house with the kernel of Atlantis, on core.blue's server, with no account, no key and no person involved. Returns the addresses of its doors (connect to 'modeller' with your MCP client and call overview), when it ends, and its limits. Whoever has the addresses can use the house, so keep them to yourself. It is deleted completely when it ends or when you call close_sandbox. If all places are taken, it says when the next one is free. One at a time from where you call.
No arguments.
{
"type": "object",
"properties": {}
}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 never charged. 'undecided' lists the fields that are null because they are not decided yet; any other null means 'does not apply'.
No arguments.
{
"type": "object",
"properties": {}
}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.
| Argument | Type | Description |
|---|---|---|
| slug* | string | The topic's slug, e.g. 'getting-a-house'. |
{
"type": "object",
"required": [
"slug"
],
"properties": {
"slug": {
"type": "string",
"description": "The topic's slug, e.g. 'getting-a-house'."
}
}
}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_agent, corrections_must_stay_visible, sources_matter, own_vocabulary, confidential_material. Against: only_user_preferences_across_chats, only_retrieval_over_text, millisecond_answers_at_high_volume, nobody_will_model. Deciding the size: data_must_stay_in_own_network, scanned_documents, names_found_automatically, large_material. Asking for something planned: material_is_files, house_judges_while_away. Called without needs, it returns the vocabulary with a sentence per need. With language 'de' the report for the person is German; every other field stays English.
| Argument | Type | Description |
|---|---|---|
| needs | array | null | The needs that apply, as words of the vocabulary. Omit to get the vocabulary. |
| data_gb | number | null | How much material there is, in gigabytes, if you know. Used to calculate additional volume. |
| language | string | Language of 'report', the text for the person: 'en' or 'de'. Default 'en'. Every other field stays English. |
| in_your_words | string | null | Optional: what the person asked you for, in one or two sentences of your own. It is recorded so that we learn which questions we did not foresee. It is not interpreted and does not change the answer. |
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 a person: call it only when they know it is coming. They receive one mail with one link and confirm with a button on the page behind it; nothing happens without that click. Returns a ticket to follow with house_status.
| Argument | Type | Description |
|---|---|---|
| size | string | Size of the machine: 'economy' (small VM) or 'premium' (larger VM). Both run the same software. Default 'economy'. |
| email* | string | E-mail address of the person who will confirm and own the house. One address, [email protected]. |
| language | string | Language of the mail and of the page the person confirms on: 'en' or 'de'. Default 'en'. |
{
"type": "object",
"required": [
"email"
],
"properties": {
"size": {
"type": "string",
"default": "economy",
"description": "Size of the machine: 'economy' (small VM) or 'premium' (larger VM). Both run the same software. Default 'economy'."
},
"email": {
"type": "string",
"description": "E-mail address of the person who will confirm and own the house. One address, [email protected]."
},
"language": {
"type": "string",
"default": "en",
"description": "Language of the mail and of the page the person confirms on: 'en' or 'de'. Default 'en'."
}
}
}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.
| Argument | Type | Description |
|---|---|---|
| limit | integer | Maximum number of hits, 1 to 20, default 5. |
| query* | string | What you want to know, as words or a question. |
{
"type": "object",
"required": [
"query"
],
"properties": {
"limit": {
"type": "integer",
"default": 5,
"description": "Maximum number of hits, 1 to 20, default 5."
},
"query": {
"type": "string",
"description": "What you want to know, as words or a question."
}
}
}{
"type": "object",
"properties": {
"needs": {
"type": [
"array",
"null"
],
"items": {
"type": [
"string",
"null"
]
},
"default": null,
"description": "The needs that apply, as words of the vocabulary. Omit to get the vocabulary."
},
"data_gb": {
"type": [
"number",
"null"
],
"default": null,
"description": "How much material there is, in gigabytes, if you know. Used to calculate additional volume."
},
"language": {
"type": "string",
"default": "en",
"description": "Language of 'report', the text for the person: 'en' or 'de'. Default 'en'. Every other field stays English."
},
"in_your_words": {
"type": [
"string",
"null"
],
"default": null,
"description": "Optional: what the person asked you for, in one or two sentences of your own. It is recorded so that we learn which questions we did not foresee. It is not interpreted and does not change the answer."
}
}
}