Cortex

MCP文档知识

提供方 未标注

文档知识 HTTP · 远程 未标注 社区 / 第三方 ClaudeCursorVS CodeGemini CLI
查看接入方式

为AI助手提供持久化语义记忆——一个远程MCP服务器,具备服务端质量门控,可拒绝冗余写入(生产环境中约80%),并将矛盾追踪为一等对象。

一句话选型结论

按资料字段整理

Cortex 属于文档知识类 MCP 服务器,HTTP · 远程,鉴权方式未标注,可直接接入 Claude、Cursor、VS Code 等,有可直接复制的远程端点配置。接入前先确认权限范围;涉及写入、删除或付款的操作,建议先在测试环境验证。

分类文档知识 传输方式HTTP · 远程 鉴权未标注 部署方式远程部署
GitHub 星标 未标注 仓库热度,无公开仓库时显示未标注
工具数 未标注 暴露给模型的工具数量
资源 / 提示词 0 / 0 资源与提示词模板数量
维护方 社区 / 第三方 核验等级 仅资料核对

工具与能力

文档知识
数量来自来源目录的标注,具体工具清单以官方文档为准
工具数量未标注暴露给模型可调用的工具个数
资源数量0可读取的资源条目
提示词数量0内置提示词模板数量

能力标签

支持客户端

适用场景

记忆

安装与配置

HTTP · 远程 未标注
连远程 HTTPS 端点,通常为 Streamable HTTP
{ "mcpServers": { "cortex": { "command": "npx", "args": ["-y", "mcp-remote", "https://skynetlab-cortex-saas-mcp.cortex-320.workers.dev/mcp"] } } }

这条命令只是入口,具体启动参数请按官方文档补齐,不要直接照搬到别的服务器。

  1. 1
    准备运行环境

    确认你的客户端支持远程端点,并拿到服务地址。

  2. 2
    安装服务

    复制上面的安装命令执行;命令里带占位符的位置,换成自己的密钥或路径。

  3. 3
    写入客户端配置

    在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,让新配置生效。

  4. 4
    验证是否可用

    连接成功后随便调一个只读工具,确认能返回结果,再接入正式流程。

典型使用场景

3 类
按分类与标签整理的常见用法,具体以官方文档为准
文档检索问答

在你的文档库里按问题找答案。

知识库读写

把新资料写进知识库,随用随取。

内容整理

把零散资料归纳成结构化笔记。

选择建议

选之前先看这几条
按条目字段给出的判断,不替你决定用不用

值得选的地方

  • 有现成的安装命令,不用自己找入口,照着跑就能起服务。
  • 已适配 Claude、Cursor、VS Code,换客户端不用重新研究配置。

先想清楚的地方

  • 远程端点依赖网络与服务方可用性,注意密钥与调用额度。
  • 资料没标注工具数量,实际能力要装好后确认。
  • 版本更新与行为细节以官方仓库为准。

更适合

  • 需要在文档知识场景里让模型直接调用外部能力的人。
  • 已经在用 Claude、Cursor 的用户,接入路径最短。
  • 想先快速试一下、能接受在本地或自有环境跑服务的人。

不太适合

  • 需要厂商级 SLA 和技术支持的生产环境。

同类对比

6 个同类
同分类里挑最接近的几条,字段以各自详情页为准
MCP 服务器工具数传输方式部署方式安装命令最后核验
Cortex当前 未标注 HTTP · 远程 远程部署 有 未标注
dify 未标注 stdio · 本地进程 本地部署 有 2026-04-11
open-webui 未标注 stdio · 本地进程 本地部署 有 2026-04-11
JeecgBoot 未标注 stdio · 本地进程 本地部署 有 2026-04-11
Cherry Studio 未标注 未标注 未标注 无 2026-05-17
mempalace 未标注 stdio · 本地进程 本地部署 有 2026-04-11

服务器档案

文档知识
字段来自项目仓库与公开索引,中文说明由本站标注
提供方未标注上游标注的维护方 未标注
分类文档知识本站按上游分类展示
连接方式HTTP · 远程连远程 HTTPS 端点,通常为 Streamable HTTP
鉴权方式未标注远程服务建议用最小权限凭据
维护方社区 / 第三方核验等级 仅资料核对
包名 / 运行时未标注 · 未标注本地安装时用到的包标识与运行时
部署类型远程部署上游给出的部署形态
最近核验未标注上游最后核验时间

详细介绍

5.9 KB
来自项目仓库与上游目录的原文,未做删改

Cortex — Semantic Memory for AI Agents

> One external brain, model-agnostic, in production. Connect it to Claude in two minutes — free trial, no credit card.

Cortex is a patent-pending semantic memory infrastructure developed by SKYNETLAB (Bergamo, Italy). Connected to your AI assistant as a remote MCP connector, it lets your conversations save decisions, context and sources — and find them again in every later session. Your AI remembers, and can show why it remembers.

🌐 Website: skynetlab-cortex.com · 📄 Patent · 📊 Benchmark · 📚 Paper · 💶 Pricing

> 🇮🇹 Versione italiana: README.it.md


Why Cortex is not "just another memory plugin"

Most memory tools for AI agents record what the agent did and retrieve similar text later. Cortex models what is true and how reliable it is:

Capability What it means
Quality Gate on write Every memory passes a novelty/redundancy check before being stored. No junk accumulation.
Typed claims & conflict tracking Facts are extracted as claims; contradictions between memories are detected and tracked, not silently overwritten.
Knowledge graph Memories are linked by entities and typed relations, not just vector similarity.
Coherence metric (Ψ_C) Each memory carries a native coherence score — the system knows how well a memory fits what it already knows.
Memory consolidation ("REM") A continuous background cycle consolidates episodic memories into long-term knowledge.
Transparent evidence Answers can cite the memories and sources they come from.

Cortex runs on globally distributed edge infrastructure operated in the European Union. The memory engine is covered by Italian patent application UIBM 102026000014026 (filed 15 May 2026).

Quick start — Claude (web / desktop / mobile)

Requirements: a Claude plan that supports custom connectors (the "Connectors" entry appears in Settings). No Cortex account needed beforehand — it is created on first sign-in.

  1. In Claude open Settings → Connectors → Add custom connector
  2. Paste this URL and confirm:https://skynetlab-cortex-saas-mcp.cortex-320.workers.dev/mcp

  3. Authorize access on the Cortex consent page (Google or email sign-in). Your personal memory space is created automatically, isolated from every other user.

That's it. Talk to Claude as usual: "Remember that we chose supplier X", "what did we decide about the budget?", "show me the sources for this claim". Claude picks the right tool on its own.

Quick start — Claude Code```bash

claude mcp add --transport http cortex https://skynetlab-cortex-saas-mcp.cortex-320.workers.dev/mcp


Then authenticate when prompted (`/mcp` shows connection status).

## Quick start — other MCP clients (stdio bridge)

For MCP clients that don't support remote connectors natively, use the `mcp-remote` bridge. Example configuration (see `examples/`):```json
{
  "mcpServers": {
    "cortex": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://skynetlab-cortex-saas-mcp.cortex-320.workers.dev/mcp"]
    }
  }
}

Quick start — this repository as a local stdio server

This repository also ships a small stdio MCP server (server/) that exposes the Cortex tools locally and forwards every call to the hosted service. It is meant for MCP clients, registries and evaluators that need a local process: it starts, lists its seven tools and answers introspection with no configuration at all; tool calls are forwarded when an access token is set.```bash
git clone https://github.com/FilippoPilo/cortex-connector.git
cd cortex-connector
npm install
CORTEX_ACCESS_TOKEN=<your token> node server/index.js


Or with Docker:```bash
docker build -t cortex-connector .
docker run -i --rm -e CORTEX_ACCESS_TOKEN=&lt;your token&gt; cortex-connector
Variable Meaning
CORTEX_ACCESS_TOKEN Bearer token for the hosted connector (the OAuth access token issued at sign-in, for example the one mcp-remote stores). Optional: without it the server only lists tools.
CORTEX_MCP_URL Remote endpoint, defaults to the hosted Cortex connector.

npm test runs a self test (initialize, tools/list, one call without token).

The seven tools

Tool Type Description
Search memories read Semantic search across your memories
Fetch memory read Full detail of one memory, with its sources
Recall & synthesize read Narrative synthesis of what Cortex knows about a topic
Show conflicts read Tracked contradictions between memories
Save memory write Stores a memory — after a quality check against duplicates and redundancy
Write status read Outcome of a queued save: quality-gate verdict and any open conflicts
Forget memory destructive Deletes a memory — always with explicit confirmation

Data & privacy

Memories are personal: each user only sees their own. They are exportable and deletable on request, and the infrastructure operates in the European Union. Details: Privacy Policy.

To disconnect, simply remove the connector from your client's settings; your memories remain in your Cortex account until you request their deletion.

Is this open source?

The Cortex memory engine is a hosted, patent-pending service — its source code is not published. This repository contains the public documentation, the client-side configuration examples and a small stdio bridge (server/) for connecting to it. Everything in this repository is released under the MIT License.

Support

📧 info@skynetlab.net · Contact page


Cortex is a SKYNETLAB product — independent research lab & deeptech studio, Bergamo, Italy. Founder: Filippo Pilotta (ORCID 0009-0000-5002-4199).

Some content and product outputs are generated or assisted by artificial intelligence, pursuant to Art. 50 of Reg. (EU) 2024/1689. AI transparency.

常见问题

8 问
答案由本站依据条目字段整理,不引用上游原文
Cortex 怎么安装?

在客户端按下面的安装命令接入:{ "mcpServers": { "cortex": { "command": "npx", "args": ["-y", "mcp-remote", "https://skynetlab-cortex-saas-mcp.cortex-320.workers.dev/mcp"] } } }。装完在客户端配置里引用同一个包或端点。

Cortex 怎么在 Claude、Cursor、VS Code 里配置?

它的传输方式是HTTP · 远程,在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,配置才会生效。

Cortex 收费吗?

本站不代收费用,也没有标注具体价格。是否收费取决于服务本身和背后的接口额度,正式使用前按官方说明确认。

Cortex 需要 API Key 吗?

资料没有标注鉴权方式,是否需要密钥取决于服务本身,接入前按官方文档确认。

Cortex 支持哪些客户端?

资料标注支持 Claude、Cursor、VS Code、Gemini CLI、Codex、Zed;其他客户端只要能配置 MCP Server,也能用同样的命令或地址接入。

Cortex 能提供哪些能力?

资料显示能力标签包括 记忆。具体工具清单以官方文档为准。

Cortex 需要什么运行环境?

属于远程端点,不需要在本地装运行时。

Cortex 是本地还是远程?

它是远程端点,连服务地址即可。传输方式为HTTP · 远程。

热门专题

按标签挑服务器
全部专题 →

服务器信息以作者仓库与官方文档为准;分类、传输方式与鉴权方式的中文说明为中文整理,最近核验 未标注。