mcp-pool
Pools multiple API keys for upstream MCP servers to distribute rate limits and provide automatic failover on rate limiting or errors.
README
mcp-pool
MCP Key Pool Proxy — pool multiple API keys across upstream MCP servers to distribute rate limits.
How it works
mcp-pool is itself an MCP server. You configure one or more "pools" — each pool represents one upstream MCP server type (e.g. Brave Search) with N API keys.
- 1 subprocess per pool at a time, not per key. No warm standby processes.
- On rate-limit or transport error, the current upstream is closed and a new one spawns with the next key (~1-2s failover).
- Tools are exposed with
{poolName}__prefix to avoid name collisions. - Route calls are serialized via a promise-chain mutex to prevent state races.
Config
pools:
brave-search:
command: bunx
args: ["-y", "@brave/brave-search-mcp-server"]
keys:
- {BRAVE_API_KEY: "sk-first"}
- {BRAVE_API_KEY: "sk-second"}
rateLimitPatterns:
- "rate_limit_exceeded"
- "too many requests"
| Field | Description |
|---|---|
command |
Executable to spawn (required) |
args |
CLI arguments |
keys |
Array of environment-variable objects, one per key (at least 1); values may be literal strings or ${NAME} references |
rateLimitPatterns |
Regex patterns matched against tool error text (required, at least 1 — safety gate) |
cooldownSeconds |
Seconds a rate-limited key is skipped; defaults to 300 |
cwd |
Working directory for the upstream process |
Config paths (first found wins): --config <path>, ./mcp-pool.yaml, ./.mcp-pool.yaml, ~/.config/mcp-pool/mcp-pool.yaml.
Values support ${VAR} expansion from environment variables. An undefined reference is a configuration error.
Usage
{
"mcpServers": {
"mcp-pool": {
"command": "bunx",
"args": ["mcp-pool@0.1.4", "--config", "/path/to/mcp-pool.yaml"]
}
}
}
Tool names are prefixed: brave-search__brave_web_search. The client calls the prefixed name; mcp-pool strips the prefix and routes to the correct upstream.
Pass --verbose for per-request trace logs.
Logging
All logs are JSON lines on stderr (stdout is reserved for MCP protocol):
{"ts":"...","level":"info","pool":"brave-search","event":"upstream_start","keyIndex":0}
{"ts":"...","level":"warn","pool":"brave-search","event":"rate_limited","upstream":0}
{"ts":"...","level":"error","pool":"brave-search","event":"upstream_error","upstream":0,"error":"..."}
Design
- Lazy failover: 1 process per pool. Rate-limited/crashed keys are closed and replaced with the next key on demand; rate-limited keys are skipped for
cooldownSeconds(300 seconds by default). - Serialized calls: promise-chain mutex prevents races on shared state across
awaitpoints. - Tool validation: each spawned upstream's tools are validated against the cached set (by name→schema map, order-independent).
rateLimitPatternsis required: without explicit patterns, allisErrorresults are terminal — no retries. Use[".*"]for blanket retry on read-only pools.- Stdio upstreams only: upstream MCP servers are spawned as subprocesses.
Development
bun install --frozen-lockfile
bun run typecheck
bun run test
bun run smoke
bun run build
bun run check:package
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。