Backstory: search your data exports locally
v1.1.0
MCP ServerMCP Registry
io.github.magna-nz/backstory
Search your Google, Telegram, Spotify and Instagram exports locally. Fully offline.
stdionugetregistry 收录
io.github.nirholas/brain-mcp · v0.1.0
List LLM providers and run chat completions through the three.ws multi-provider router.
three.ws Brain 是一个MCP Server，收录自 官方 MCP Registry。支持 stdio 传输。本页提供 Cursor、Claude Code 等客户端的安装配置片段。
选择你的平台查看安装方式
{
"mcpServers": {
"brain-mcp": {
"command": "npx",
"args": [
"-y",
"@three-ws/brain-mcp"
]
}
}
}THREE_WS_BASE可选Base URL of the three.ws API that fronts the LLM router (/api/brain/chat). Override only when self-hosting or targeting a preview deployment.
THREE_WS_API_KEY可选secretOptional three.ws API key (sk_live_… / sk_test_…) or OAuth access token, sent as a Bearer token. Required only to use paid first-party flagships (Claude, GPT-4o, o3, Qwen Plus, DeepSeek). Free open-weight tiers (GPT-OSS 120B, NVIDIA NIM models) work with no key. Create one at https://three.ws/account.
THREE_WS_TIMEOUT_MS可选Per-request timeout in milliseconds. Chat completions stream server-side and are collapsed into a single reply, so this is generous by default to ride out a long flagship answer.
v1.1.0
io.github.magna-nz/backstory
Search your Google, Telegram, Spotify and Instagram exports locally. Fully offline.
v1.30.5
com.astranl/mcp
NL coordination protocol — 1% fee, agent-native, real Dutch merchant pricing. Open brain.
v3.0.319
com.local-mcp/local-mcp
180 local tools from ChatGPT, Claude.ai & desktop AIs: Mail, iMessage, Teams, files. Local, free.
v1.37.5
io.github.zoharbabin/web-researcher-mcp
Your AI research assistant that cites real sources and stays honest
v1.31.8
io.github.vuluu2k/webcake-storefront-mcp
Build pages and manage products, orders, and content on the WebCake/StoreCake storefront builder.
v1.4.53
io.github.HrRodan/agent-workspace-mcp
A sandboxed, agentic workspace providing secure filesystem, bash, and uv-powered Python execution.
{
"id": "io.github.nirholas/brain-mcp",
"type": "mcp-server",
"version": "0.1.0",
"displayName": "three.ws Brain",
"description": "List LLM providers and run chat completions through the three.ws multi-provider router.",
"repository": {
"url": "https://github.com/nirholas/three.ws",
"source": "github",
"subfolder": "packages/brain-mcp"
},
"homepage": "https://three.ws",
"distribution": {
"packages": [
{
"registryType": "npm",
"identifier": "@three-ws/brain-mcp",
"version": "0.1.0",
"runtimeHint": "npx",
"transport": "stdio",
"environmentVariables": [
{
"name": "THREE_WS_BASE",
"description": "Base URL of the three.ws API that fronts the LLM router (/api/brain/chat). Override only when self-hosting or targeting a preview deployment."
},
{
"name": "THREE_WS_API_KEY",
"description": "Optional three.ws API key (sk_live_… / sk_test_…) or OAuth access token, sent as a Bearer token. Required only to use paid first-party flagships (Claude, GPT-4o, o3, Qwen Plus, DeepSeek). Free open-weight tiers (GPT-OSS 120B, NVIDIA NIM models) work with no key. Create one at https://three.ws/account.",
"isSecret": true
},
{
"name": "THREE_WS_TIMEOUT_MS",
"description": "Per-request timeout in milliseconds. Chat completions stream server-side and are collapsed into a single reply, so this is generous by default to ride out a long flagship answer."
}
]
}
],
"remotes": []
},
"dependencies": [],
"installTargets": [
"claude-code",
"claude-desktop",
"cursor",
"vscode"
],
"keywords": [],
"provenance": {
"origin": "official-mcp-registry",
"originalId": "io.github.nirholas/brain-mcp",
"originalUrl": "https://registry.modelcontextprotocol.io/v0.1/servers/io.github.nirholas%2Fbrain-mcp/versions/latest",
"isOfficial": true,
"status": "active"
}
}