@kireo/mcp-server
A shared long-term memory server for MCP clients, enabling you to persist and retrieve decisions, gotchas, and context across sessions with a web dashboard.
README
<p align="center"> <img src="./logo.png" alt="Kireo" width="120" height="120" /> </p>
@kireo/mcp-server
Kireo gives Claude Code, Cursor, and any MCP client a shared long-term memory — save decisions and gotchas as you work, recall them from any tool, and browse, edit, or delete everything in a web dashboard. Free beta.
Quickstart
- Get an API key at https://app.kireo.app/api-keys (
ki_sk_…). - Add this MCP server to your host. Claude Code — run:
claude mcp add kireo --env KIREO_API_KEY=ki_sk_xxx -- npx -y @kireo/mcp-server
Add --scope user to make it available in every project. Alternatively, check a project-scoped .mcp.json into your repo root with the same shape:
// .mcp.json (project root)
{
"mcpServers": {
"kireo": {
"command": "npx",
"args": ["-y", "@kireo/mcp-server"],
"env": { "KIREO_API_KEY": "ki_sk_xxx" }
}
}
}
- Restart the host. You now have 8 tools available to the AI:
| Tool | Purpose |
|---|---|
memory_save |
Persist a long-term memory |
memory_search |
Hybrid semantic + keyword search |
memory_recall |
Replay recent/important memories |
memory_get |
Fetch by id |
memory_update |
Patch fields |
memory_delete |
Soft/hard delete |
memory_list_namespaces |
Enumerate namespaces |
memory_health |
Probe service |
Client setup
The server config is identical everywhere — only the file (or UI) each client reads it from differs. Use your ki_sk_… key from https://app.kireo.app/api-keys.
Claude Code — run claude mcp add kireo --env KIREO_API_KEY=ki_sk_xxx -- npx -y @kireo/mcp-server (add --scope user for all projects), or check a project-scoped .mcp.json into your repo root (see the Quickstart block above).
Cursor — ~/.cursor/mcp.json (or <workspace>/.cursor/mcp.json for a single repo):
{
"mcpServers": {
"kireo": {
"command": "npx",
"args": ["-y", "@kireo/mcp-server"],
"env": { "KIREO_API_KEY": "ki_sk_xxx" }
}
}
}
Cline — open the MCP Servers panel → Configure MCP Servers, then add:
{
"mcpServers": {
"kireo": {
"command": "npx",
"args": ["-y", "@kireo/mcp-server"],
"env": { "KIREO_API_KEY": "ki_sk_xxx" }
}
}
}
Claude Desktop — claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\):
{
"mcpServers": {
"kireo": {
"command": "npx",
"args": ["-y", "@kireo/mcp-server"],
"env": { "KIREO_API_KEY": "ki_sk_xxx" }
}
}
}
Restart the client after editing. Any other MCP-compatible host (Windsurf, Zed, Continue …) uses the same command / args / env triple.
Configuration
Sources are merged in order: CLI args > env > ~/.kireo/config.json.
| ENV / CLI | Default | Description |
|---|---|---|
KIREO_API_KEY / --api-key |
required | Bearer token (ki_sk_…). |
KIREO_API_URL / --api-url |
https://api.kireo.app |
Override for self-host. |
KIREO_REQUEST_TIMEOUT_MS / --timeout |
60000 |
Per-request timeout in ms, max 300000 (env alias: KIREO_TIMEOUT_MS). |
KIREO_RETRY_MAX_ATTEMPTS |
3 |
5xx/429 retries (alias: KIREO_RETRY_MAX). |
KIREO_RETRY_BASE_MS |
200 |
Exponential backoff base. |
KIREO_TELEMETRY |
1 |
Set to 0 to disable device-id header. |
KIREO_LOG_LEVEL |
info |
debug / info / warn / error / silent. |
KIREO_PROXY_URL |
none | HTTP(S) proxy. |
KIREO_ACCEPT_LANGUAGE |
en |
Locale for error hints. |
Logs land in ~/.kireo/logs/ on all platforms (macOS, Linux, Windows).
Indexing local code
Index a repository's symbols (functions / classes / methods) into a
code-<repo> namespace so the AI can recall them via memory_search:
export KIREO_API_KEY=ki_sk_xxx
npx -y -p @kireo/mcp-server kireo index ./ --repo my-app
Indexing is incremental — only changed files are re-sent on subsequent runs.
| Flag | Default | Description |
|---|---|---|
--repo <name> |
directory basename | Repo name → code-<name> namespace. |
--batch-size <n> |
100 |
Symbols per upload batch (1..100). Lower it if a batch times out. |
--timeout <ms> |
60000 |
Per-request timeout (max 300000). |
--api-key / --api-url / --namespace / --log-level / --no-telemetry |
— | Same as the config table above; CLI flags override env. |
Run kireo --help for the full usage text. --help and --version never touch
the network or the filesystem and don't require an API key. If a batch upload
times out, re-running the same command is safe: the server dedupes identical
symbols, so retries won't create duplicates.
Host setup
Privacy
Set KIREO_TELEMETRY=0 to drop the X-Device-Id header. We never read your code; only the explicit content you pass to memory_save reaches the API.
Troubleshooting
AUTH_INVALID_KEY→ rotate your key at https://app.kireo.app/api-keys.QUOTA_EXCEEDED→ upgrade or wait for next billing cycle.- Tools missing in your host → run
npx @modelcontextprotocol/inspector node $(npm root -g)/@kireo/mcp-server/bin/kireo-mcp.cjsto verify locally.
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。