Context7
Up-to-date docs for AI agents
作者提供的说明(英文原文)
Cloud-persistent, semantic-search memory MCP — drop-in for server-memory, backed by ZeroDB.
这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
选择你使用的 AI 应用,然后复制设置。
你需要
你用的是哪个应用?
在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。
打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json
{
"mcpServers": {
"ainative-memory": {
"command": "npx",
"args": [
"-y",
"ainative-memory-mcp"
]
}
}
}在终端中运行这条命令
claude mcp add ainative-memory -- npx -y ainative-memory-mcp粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"ainative-memory": {
"command": "npx",
"args": [
"-y",
"ainative-memory-mcp"
]
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"ainative-memory": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"ainative-memory-mcp"
]
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
这个服务器在你的电脑上运行,而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。
你的选择通过 Cookie 保存在这台设备上,无需账户。
这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月7日
注册名称已通过 GitHub 账户 AINative-Studio 验证,该账户拥有此仓库
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
它在你的电脑上运行,没有互联网端点
在你的电脑上运行,改用本地设置
它在你的电脑上运行;我们只能读取互联网端点的工具列表
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。
它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。
GitHub 仓库最后更新于–,最新版本(1.0.1)于3个月前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Node.js。
同一分类中有:Context7, Codebase Memory, Exa
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
Up-to-date docs for AI agents
Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
Connect AI agents to Exa for web search, content fetching, and multi-step research.
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
Enhanced MCP knowledge graph memory server with cloud persistence and semantic search. Drop-in replacement for @modelcontextprotocol/server-memory.
| Feature | server-memory | ainative-memory-mcp |
|---|---|---|
| Storage | Local JSONL file | ZeroDB cloud |
| Persistence | Lost on machine wipe | Survives forever |
| Cross-device | No | Yes (same API key = same graph) |
| Semantic search | No (text match only) | Yes (vector similarity) |
| Setup | Manual file path | Auto-provisions on first run |
| Sharing | Copy files around | Share API key |
{
"mcpServers": { "memory": { "command": "npx", "args": ["-y", "ainative-memory-mcp"], "env": { "ZERODB_API_KEY": "ak_your_key" } } } }
No API key? Just omit it — a free ZeroDB instance is auto-provisioned on first run.
Same config in your .mcp.json:
{
"mcpServers": { "memory": { "command": "npx", "args": ["-y", "ainative-memory-mcp"], "env": { "ZERODB_API_KEY": "ak_your_key" } } } }
npx zerodb-cli init
Or sign up at ainative.studio.
All 9 original server-memory tools plus semantic search:
| Tool | Description |
|---|---|
create_entities | Create new entities with name, type, and observations |
create_relations | Create directed relations between entities |
add_observations | Add observations to existing entities |
delete_entities | Delete entities and their cascading relations |
delete_observations | Remove specific observations from entities |
delete_relations | Delete specific relations |
read_graph | Read the entire knowledge graph |
search_nodes | Search by text match (name, type, observations) |
open_nodes | Fetch specific entities by name with their relations |
| Tool | Description |
|---|---|
search_nodes_semantic | Vector similarity search — find entities by meaning, not just exact text |
The original search_nodes only finds exact text matches. search_nodes_semantic understands meaning:
search_nodes("ML frameworks") -> might find nothing
search_nodes_semantic("ML frameworks") -> finds "PyTorch", "TensorFlow", "JAX"
| Variable | Required | Description |
|---|---|---|
ZERODB_API_KEY | No* | ZeroDB API key (auto-provisions if missing) |
ZERODB_PROJECT_ID | No | ZeroDB project ID |
ZERODB_API_URL | No | API URL (default: https://api.ainative.studio) |
*If no credentials are provided, a free instance is automatically provisioned on first run.
On first run without credentials:
.mcp.json and .env in your projectInstead of writing to a local memory.jsonl file, this server:
kg_entities)kg_relations)@modelcontextprotocol/server-memory with ainative-memory-mcp in your MCP configZERODB_API_KEY to your env (or let it auto-provision)MIT
This package is part of the AINative ecosystem — the AI-native developer platform.
| Feature | ZeroDB | Others |
|---|---|---|
| Vector search | Built-in, free embeddings | Separate service (Pinecone, Qdrant) |
| Agent memory | Cognitive memory with decay + reflection | DIY or Mem0 ($$$) |
| File storage | S3-compatible, included | Separate S3 bucket |
| NoSQL tables | Instant, schema-free | MongoDB Atlas, DynamoDB |
| PostgreSQL | Managed, pgvector pre-installed | Neon, Supabase ($$$) |
| Serverless functions | DB-event triggered | Firebase/Supabase Edge |
| Pricing | Free tier, no credit card | Pay-per-query from day 1 |
npx zerodb-cli init # Auto-configures your IDE
Or sign up at [ainative.studio](https://ainative.studio) — free tier, no credit card required.
No account needed to start. On first run, this package automatically:
.env, .mcp.json)Your auto-provisioned instance is free for 72 hours. To keep your data permanently, visit the claim URL printed in your terminal.
If a coding agent (Claude Code, Cursor, Windsurf) installs this package:
.claude/CLAUDE.md instructs agents to surface the claim link to you.env or ~/.ainative/config.json for your project ID if you miss it