CortexPlus
Personal memory layer: files, notes, messages, tasks and email, semantically indexed.
使うべきか
品質と安全性
検出事項(1)
- LOWfetch 内
ツール定義とプロトコルへの準拠に関する自動分析に基づいています。
コンテキストコスト
これは、サーバーのツールがモデルのコンテキストに読み込まれるたびに消費されるおおよそのトークン数です。数が多いほど、ほかのタスクに使える注意が減ります。
インストール
ワンクリックインストール
これを `claude_desktop_config.json` ファイルに追加してください:
{
"mcpServers": {
"cortexplus": {
"url": "https://mcp.cortexplus.io/mcp"
}
}
}リモートエンドポイント
https://mcp.cortexplus.io/mcpstreamable-httpできること
ツール一覧
ツール(11)
🟢search(query, limit)
Search the user's CortexPlus memory and return ranked matches. Use this to find what the user has stored before answering from memory.
入力スキーマ
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "What to look for, in natural language."
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 50,
"default": 10
}
},
"required": [
"query"
],
"additionalProperties": false
}出力スキーマ
{
"type": "object",
"properties": {
"results": {
"type": "array",
"items": {
"type": "object",
"properties": {
"id": {
"type": "string"
},
"title": {
"type": "string"
},
"url": {
"type": "string"
},
"text": {
"type": "string"
}
},
"required": [
"id",
"title",
"url"
]
}
}
},
"required": [
"results"
]
}🟢fetch(id)
Retrieve the full content of one CortexPlus memory item by id, as returned by search.
入力スキーマ
{
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "Item id from a search result."
}
},
"required": [
"id"
],
"additionalProperties": false
}出力スキーマ
{
"type": "object",
"properties": {
"id": {
"type": "string"
},
"title": {
"type": "string"
},
"text": {
"type": "string"
},
"url": {
"type": "string"
},
"metadata": {
"type": "object"
}
},
"required": [
"id",
"title",
"text",
"url"
]
}🟢recall(query, limit, depth, maxChars)
Build a context block from the user's CortexPlus memory: the passages that answer a question plus their graph neighbours, already formatted as text. Prefer this over search when you intend to answer from the user's memory.
入力スキーマ
{
"type": "object",
"properties": {
"query": {
"type": "string"
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 50,
"default": 10
},
"depth": {
"type": "integer",
"minimum": 0,
"maximum": 3,
"default": 1
},
"maxChars": {
"type": "integer",
"minimum": 500,
"maximum": 20000,
"default": 6000
}
},
"required": [
"query"
],
"additionalProperties": false
}出力スキーマ
{
"type": "object",
"properties": {
"text": {
"type": "string"
},
"matches": {
"type": "integer"
}
},
"required": [
"text",
"matches"
]
}⚪remember(title, content, tags, type, parentId)
Store a note in the user's CortexPlus memory so future conversations can recall it.
入力スキーマ
{
"type": "object",
"properties": {
"title": {
"type": "string"
},
"content": {
"type": "string"
},
"tags": {
"type": "array",
"items": {
"type": "string"
}
},
"type": {
"type": "string",
"default": "note",
"description": "Node type, e.g. note or meeting-note."
},
"parentId": {
"type": "string",
"description": "Optional id of an existing memory to nest this one under."
}
},
"required": [
"content"
],
"additionalProperties": false
}出力スキーマ
{
"type": "object",
"properties": {
"id": {
"type": "string"
},
"title": {
"type": "string"
}
},
"required": [
"id"
]
}🟡memory(text, tags)
Save a memory in CortexPlus. CortexPlus decides whether it is a note, task, or reminder and extracts the client.
入力スキーマ
{
"type": "object",
"properties": {
"text": {
"type": "string",
"description": "Text to classify and save."
},
"tags": {
"type": "array",
"items": {
"type": "string"
}
}
},
"required": [
"text"
],
"additionalProperties": false
}出力スキーマ
{
"type": "object",
"properties": {
"id": {
"type": "string"
},
"type": {
"type": "string"
},
"title": {
"type": "string"
},
"client": {
"type": [
"string",
"null"
]
},
"status": {
"type": [
"string",
"null"
]
},
"memory": {
"type": [
"string",
"null"
]
},
"review": {
"type": [
"string",
"null"
]
},
"resolved": {
"type": [
"boolean",
"null"
]
},
"url": {
"type": "string"
}
},
"required": [
"id",
"type",
"title",
"client",
"status",
"memory",
"review",
"resolved",
"url"
]
}🟢tasks(status, client, limit)
List open CortexPlus tasks and reminders, optionally filtered by client.
入力スキーマ
{
"type": "object",
"properties": {
"status": {
"type": "string",
"default": "open"
},
"client": {
"type": "string"
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 50,
"default": 20
}
},
"additionalProperties": false
}出力スキーマ
{
"type": "object",
"properties": {
"tasks": {
"type": "array",
"items": {
"type": "object",
"required": [
"id",
"title",
"client",
"status",
"dueAt",
"url"
],
"properties": {
"id": {
"type": "string"
},
"title": {
"type": "string"
},
"client": {
"type": [
"string",
"null"
]
},
"status": {
"type": [
"string",
"null"
]
},
"dueAt": {
"type": [
"string",
"null"
]
},
"url": {
"type": "string"
}
}
}
}
},
"required": [
"tasks"
]
}🟡save_context(content, platform, key, title, model, ...)
Save a handoff summary of this conversation to the user's CortexPlus memory so it can be resumed later in another AI platform. Write the summary yourself, in Markdown, covering: objective, decisions taken, current state, artifacts, next steps and constraints. Do not paste the raw transcript. Never include passwords, API keys or tokens.
入力スキーマ
{
"type": "object",
"properties": {
"content": {
"type": "string",
"description": "Handoff summary in Markdown."
},
"platform": {
"type": "string",
"description": "The AI platform you are running on, e.g. ChatGPT, Claude, Gemini, Cursor."
},
"key": {
"type": "string",
"description": "Short stable slug for the topic, e.g. context-pack-design. Sending the same key again updates the pack instead of creating another."
},
"title": {
"type": "string"
},
"model": {
"type": "string"
},
"messageCount": {
"type": "integer",
"minimum": 0,
"maximum": 100000
},
"tags": {
"type": "array",
"items": {
"type": "string"
}
}
},
"required": [
"content",
"platform",
"key"
],
"additionalProperties": false
}出力スキーマ
{
"type": "object",
"properties": {
"id": {
"type": "string"
},
"title": {
"type": "string"
},
"url": {
"type": "string"
},
"created": {
"type": "boolean"
},
"redactions": {
"type": "array",
"items": {
"type": "object",
"required": [
"kind",
"placeholder",
"count"
],
"properties": {
"kind": {
"type": "string"
},
"placeholder": {
"type": "string"
},
"count": {
"type": "integer"
}
}
}
}
},
"required": [
"id",
"title",
"url",
"created",
"redactions"
]
}🟢resume(query, id, maxChars)
Load a previously saved CortexPlus context pack to resume work started in another AI conversation.
入力スキーマ
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Topic to find the pack by, in natural language."
},
"id": {
"type": "string",
"description": "Pack id, as returned by context_packs."
},
"maxChars": {
"type": "integer",
"minimum": 500,
"maximum": 20000,
"default": 6000
}
},
"additionalProperties": false
}出力スキーマ
{
"type": "object",
"properties": {
"text": {
"type": "string"
},
"pack": {
"type": [
"object",
"null"
],
"properties": {
"id": {
"type": "string"
},
"title": {
"type": "string"
},
"url": {
"type": "string"
}
}
},
"matches": {
"type": "integer"
}
},
"required": [
"text",
"pack",
"matches"
]
}🟢context_packs(platform, limit)
List saved CortexPlus context packs, optionally filtered by AI platform.
入力スキーマ
{
"type": "object",
"properties": {
"platform": {
"type": "string",
"description": "Platform filter, e.g. chatgpt or claude."
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 50,
"default": 20
}
},
"additionalProperties": false
}出力スキーマ
{
"type": "object",
"properties": {
"packs": {
"type": "array",
"items": {
"type": "object",
"required": [
"id",
"title",
"platform",
"url",
"savedAt"
],
"properties": {
"id": {
"type": "string"
},
"title": {
"type": "string"
},
"platform": {
"type": [
"string",
"null"
]
},
"url": {
"type": "string"
},
"savedAt": {
"type": [
"string",
"null"
]
}
}
}
}
},
"required": [
"packs"
]
}🟡signup(email, name, client)
Create a CortexPlus account, or begin signing in to an existing one, so this conversation can use CortexPlus as the user's long-term memory and knowledge base. Ask the user for their email address, and for their name if you do not already have it, then call this tool. CortexPlus sends them a short authentication key by email; ask the user for that key and call connect with it. Never guess or invent the email address.
入力スキーマ
{
"type": "object",
"properties": {
"email": {
"type": "string",
"description": "The user's email address. Ask the user; never guess or invent it."
},
"name": {
"type": "string",
"description": "The user's name, if it is not already known."
},
"client": {
"type": "string",
"description": "The name of the AI platform you are running on, e.g. ChatGPT, Claude, Cursor."
}
},
"required": [
"email"
],
"additionalProperties": false
}出力スキーマ
{
"type": "object",
"properties": {
"sent": {
"type": "boolean"
}
},
"required": [
"sent"
]
}🟡connect(key, client)
Complete the CortexPlus connection with the short authentication key the user received by email after signup. Ask the user to paste the key, then call this tool; never guess or invent the key. The response includes an API key that the AI platform should save in its CortexPlus connector configuration.
入力スキーマ
{
"type": "object",
"properties": {
"key": {
"type": "string",
"description": "The authentication key pasted by the user from their CortexPlus email."
},
"client": {
"type": "string",
"description": "The name of the AI platform you are running on, e.g. ChatGPT, Claude, Cursor."
}
},
"required": [
"key"
],
"additionalProperties": false
}出力スキーマ
{
"type": "object",
"properties": {
"apiKey": {
"type": "string"
},
"email": {
"type": "string"
},
"name": {
"type": "string"
}
},
"required": [
"apiKey",
"email",
"name"
]
}コミュニティ
エビデンス