Y
YawLabs/mcp
MCP orchestrator, one install, all your MCP servers
View on GitHub ↗Link checked 2026-11-14 · HTTP 200 · opens the vendor's own site
Install & config
Client config (built from the install command this repo gives)
{
"mcpServers": {
"yawlabs-mcp": {
"command": "npx",
"args": ["-y", "@yawlabs/mcp@latest"]
}
}
}Parsed from the README we fetched on 2026-11-12; we have not executed it.
command/args come from the install command the repository states. When it is ambiguous, the project README wins.
VS Code (.vscode/mcp.json - the key is servers)
{
"servers": {
"yawlabs-mcp": {
"command": "npx",
"args": ["-y", "@yawlabs/mcp@latest"]
}
}
}Same server, but VS Code keeps it under <code>servers</code>.
Claude Code (command line)
claude mcp add --transport stdio yawlabs-mcp -- npx -y @yawlabs/mcp@latest
Claude Code does not read a config file; add the server with this command.
Key names differ by client: Clients & CLI
- Star count
- 1 ★ · YawLabs/mcp · read from the GitHub search API · (checked 2026-11-13 20:00:50)
- Source
- read directly from its GitHub page · type: open-source project
- Harvest history
- first seen 2026-11-13 · last seen 2026-11-14 · seen 2× · listed by 2 sources
- Score
- score 203 · 1 ★ · 2 sources · repo
- Install
npx -y @yawlabs/mcp@latest
FAQ (answers come from our records)
How do I install it?
The repository provides this install command:
npx -y @yawlabs/mcp@latest. It comes from the repository itself; we cannot guarantee it runs as-is in your client.Who is it for?
We filed it under these tags: 开源项目. The tags come from the entry itself, not a taxonomy we imposed.
Who maintains it?
repository
YawLabs/mcp；first catalogued 2026-11-13；last seen 2026-11-14。There is no official certification or quality rating here — we record sources and dates only.# @yawlabs/mcp
以下摘录自该仓库的 README（片段） · 在 GitHub 读完整 README →
One install. Every MCP server. Managed from one place.
Yaw MCP (the yaw-mcp CLI) is an MCP server that fronts every other MCP server you use. Point each AI client (Claude Code, Claude Desktop, Cursor, VS Code) at it once, and your servers load lazily from a single connection instead of a hand-edited mcpServers block per client.
It runs entirely on your machine. No account, no sign-in, no telemetry -- your servers live in a local bundles.json and your credentials in a local encrypted vault. Running as an MCP server, its only outbound calls are two background npm checks: one for its own updates (YAW_MCP_AUTO_UPGRADE=0 to disable) and, if you have run yaw-mcp sidecars install, a once-a-day check that the managed sidecar packages are current (YAW_MCP_SIDECAR_REFRESH=0 to disable). One more is conditional: if a configured server launches through uv/uvx and uv is not on your PATH, yaw-mcp downloads Astral's uv release from GitHub once and caches it (see Runtime detection & uv bootstrap). yaw-mcp add, search and try fetch the public server catalog on demand. Nothing else leaves your machine.
It earns its keep when you hit any of these:
More than one client. Define a server once in bundles.json; every client on the machine picks it up. No copy-pasting the same JSON into four config files. (Sync bundles.json across machines with your dotfiles if you want it everywhere.)
Tool-context bloat. The dispatch meta-tool ranks your servers against the task and loads only the top match. A 30-server setup keeps a handful of tools in context at a time instead of hundreds.
Tokens you'd rather not leave in disk configs. Credentials live encrypted in a local vault and inject at spawn time. Rotate once; every client picks up the new value.
A trust signal before you activate. Every scored server shows an A-F compliance grade. Set YAW_MCP_MIN_COMPLIANCE=B to refuse anything below.
One client, a few servers? claude mcp add is fine -- yaw-mcp's value shows up when that setup stops scaling.
## How it works
Your MCP client (Claude Code, Cursor, ...)
| single stdio connection
@yawlabs/mcp --lazy load--> GitHub | Slack | Stripe | ... (your servers)
1. Add servers with yaw-mcp add (or edit ~/.yaw-mcp/bundles.json directly).
2. yaw-mcp reads that file on startup.
3. The model uses a handful of meta-tools to control which servers' tools are in context. Adding a server puts it on your list; loading it brings its tools into the session.
| Meta-tool | What it does |
| mcp_connect_dispatch | Describe a task in plain English; picks the best server, loads its tools, exposes them in one call. The fast path. |
| mcp_connect_discover | List available servers, optionally ranked by a context string. Auto-loads the top match when one clearly wins. Tool-name lists are capped at five per server; pass server for one server's full list. listOnly: true (for client UIs) returns the same listing with no side effects: no auto-load, no idle tick, no install suggestions. |
| mcp_connect_activate / deactivate | Load / unload specific servers by namespace. |
| mcp_connect_read_tool | Return one tool's schema without loading its server. |
| mcp_connect_find_tool | Search every installed server's tools by what they do, from cache: nothing is loaded and no server is contacted. A hit on a loaded server carries its full schema. |
Yaw MCP (the yaw-mcp CLI) is an MCP server that fronts every other MCP server you use. Point each AI client (Claude Code, Claude Desktop, Cursor, VS Code) at it once, and your servers load lazily from a single connection instead of a hand-edited mcpServers block per client.
It runs entirely on your machine. No account, no sign-in, no telemetry -- your servers live in a local bundles.json and your credentials in a local encrypted vault. Running as an MCP server, its only outbound calls are two background npm checks: one for its own updates (YAW_MCP_AUTO_UPGRADE=0 to disable) and, if you have run yaw-mcp sidecars install, a once-a-day check that the managed sidecar packages are current (YAW_MCP_SIDECAR_REFRESH=0 to disable). One more is conditional: if a configured server launches through uv/uvx and uv is not on your PATH, yaw-mcp downloads Astral's uv release from GitHub once and caches it (see Runtime detection & uv bootstrap). yaw-mcp add, search and try fetch the public server catalog on demand. Nothing else leaves your machine.
It earns its keep when you hit any of these:
More than one client. Define a server once in bundles.json; every client on the machine picks it up. No copy-pasting the same JSON into four config files. (Sync bundles.json across machines with your dotfiles if you want it everywhere.)
Tool-context bloat. The dispatch meta-tool ranks your servers against the task and loads only the top match. A 30-server setup keeps a handful of tools in context at a time instead of hundreds.
Tokens you'd rather not leave in disk configs. Credentials live encrypted in a local vault and inject at spawn time. Rotate once; every client picks up the new value.
A trust signal before you activate. Every scored server shows an A-F compliance grade. Set YAW_MCP_MIN_COMPLIANCE=B to refuse anything below.
One client, a few servers? claude mcp add is fine -- yaw-mcp's value shows up when that setup stops scaling.
## How it works
Your MCP client (Claude Code, Cursor, ...)
| single stdio connection
@yawlabs/mcp --lazy load--> GitHub | Slack | Stripe | ... (your servers)
1. Add servers with yaw-mcp add (or edit ~/.yaw-mcp/bundles.json directly).
2. yaw-mcp reads that file on startup.
3. The model uses a handful of meta-tools to control which servers' tools are in context. Adding a server puts it on your list; loading it brings its tools into the session.
| Meta-tool | What it does |
| mcp_connect_dispatch | Describe a task in plain English; picks the best server, loads its tools, exposes them in one call. The fast path. |
| mcp_connect_discover | List available servers, optionally ranked by a context string. Auto-loads the top match when one clearly wins. Tool-name lists are capped at five per server; pass server for one server's full list. listOnly: true (for client UIs) returns the same listing with no side effects: no auto-load, no idle tick, no install suggestions. |
| mcp_connect_activate / deactivate | Load / unload specific servers by namespace. |
| mcp_connect_read_tool | Return one tool's schema without loading its server. |
| mcp_connect_find_tool | Search every installed server's tools by what they do, from cache: nothing is loaded and no server is contacted. A hit on a loaded server carries its full schema. |
Listed badge (optional)
Copy this line into the README if you want the listing mark. Optional, and it does not affect being listed.
[](https://anclum.com/en/s/yawlabs-mcp/)
- Source
- github · https://github.com/YawLabs/mcp
- Browse by field
- Open source
- Traction
- 1 ★
- Listed by
- 2 independent sources
- added
- today
More like this
Filed under
Every tag opens the full list for that filter. Counts are the live catalogue figures.