Modular MCP - Modular tool access for reducing context overhead
Connect Modular to Claude, Cursor or any other MCP client and it stops being a tab you switch to. Modular MCP - Modular tool access for reducing context overhead. The modular mcp server is what makes that connection.
A Model Context Protocol (MCP) proxy server that enables efficient management of large tool collections across multiple MCP servers by grouping them and loading tool schemas on-demand.
Because this one is hosted, setup is mostly authentication — you point your client at the endpoint and approve access. Nothing runs on your machine, so there is no runtime to keep patched.
The toolset is worth reading before you wire it up, because it tells you what the integration is really for:
get-modular-tools — Retrieves tool name and schemas for a specific groupcall-modular-tool — Executes a tool from a specific groupcontext7 — Use when you need to search library documentationplaywright — Use when you need to control or automate web browsersConfiguration is passed through the environment: API_KEY, LOG_DIR, MY_API_KEY. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.
Among the browser automation options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Modular's toolset — get-modular-tools, call-modular-tool, context7 and 1 more — is a fair guide to whether it matches your workflow. It is maintained by kimuson; worth a glance at recent repository activity before you build anything load-bearing on it.
SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.
| Tool | What it does |
|---|---|
| get-modular-tools | Retrieves tool name and schemas for a specific group |
| call-modular-tool | Executes a tool from a specific group |
| context7 | Use when you need to search library documentation. |
| playwright | Use when you need to control or automate web browsers. |
{
"mcpServers": {
"modular-server": {
"command": "npx",
"args": ["-y", "@kimuson/modular-mcp"],
"env": {
"API_KEY": "your-value",
"LOG_DIR": "your-value",
"MY_API_KEY": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| API_KEY | Credential the server authenticates with. | Yes |
| LOG_DIR | Filesystem location the server is allowed to use. | Optional |
| MY_API_KEY | Credential the server authenticates with. | Yes |
Microsoft's official browser automation server — drive a real browser through the accessibility tree, no screenshots needed.
Industrial-strength web extraction — render, scrape, crawl and search entire sites into clean markdown.
The original Chromium automation reference server — simple, screenshot-driven browser control.
Give your coding agent the full DevTools toolbox: traces, network, console, heap snapshots and Lighthouse.
Puppeteer-powered browser control that drives pages from the accessibility tree instead of pixels.
Cloud browsers for AI agents — automation sessions that run in Browserbase's fleet, not on your machine.