Log inSubmit server
Crabeye MCP Bridge logo

Crabeye MCP Bridge

Consolidates multiple MCP servers behind one connection with searchable tools and configurable execution policies.

InstallRepository
Full README Compare alternatives Embed widget Claim this listing

Install Crabeye MCP Bridge

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "crabeye-mcp-bridge": {
      "command": "npx",
      "args": [
        "-y",
        "@crabeye-ai/crabeye-mcp-bridge"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Install not yet sandbox-tested— we haven't run this command through our automated sandbox yet. Not a red flag; we're working through the catalog.

Overview

crabeye-mcp-bridge MCP server places a single STDIO endpoint between an AI assistant and multiple upstream MCP servers. It exposes only `search_tools` and `run_tool`, keeping upstream schemas out of the context window until a tool search is performed. Upstreams can use STDIO, HTTP, or SSE, with namespacing, fuzzy discovery, credentials, and per-tool execution policies. Reach for it when many MCP connections create excessive tool-schema context or when centralized execution controls are needed.

Use cases

  • Consolidate many MCP servers behind one assistant connection
  • Search a large tool catalog before loading tool schemas
  • Require approval for selected upstream tools
  • Store upstream credentials outside plain-text configuration
  • Reuse STDIO upstream processes across bridge instances

Key features

  • Single STDIO interface for multiple upstream MCP servers
  • Fuzzy tool discovery with `search_tools` and `run_tool`
  • STDIO, HTTP, and SSE upstream support
  • Global, server, and tool execution policies
  • Encrypted credentials with template references
  • CLI initialization, restoration, validation, and daemon commands

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 1d ago

Recent health check succeeded.

4/4 checks healthy over the last 34d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 5d ago via OSV.dev · @crabeye-ai/crabeye-mcp-bridge (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars18Stargazers on the source repository.
npm downloads208Package downloads in the last 30 days.
Last commit2d agoMost recent push to the default branch.
Directory activity1 viewsConfig copies, upvotes, and views on AllMCPs.

How Crabeye MCP Bridge works

What crabeye-mcp-bridge does

crabeye-mcp-bridge combines tools from multiple upstream MCP servers behind one MCP connection. Instead of presenting every upstream tool directly to the assistant, it exposes two bridge-level tools: search_tools for discovery and run_tool for execution.

The bridge discovers and indexes configured upstream tools when the assistant connects. Search results can then identify the relevant namespace and schema, allowing the assistant to run a selected tool without loading all available tool definitions into the context window at startup. This design is intended for environments where many connected servers would otherwise contribute a large number of tool schemas.

How it works

The assistant connects to the bridge over STDIO. The bridge fans requests out to configured upstream MCP servers, which may communicate over STDIO, HTTP, or SSE. Namespaces distinguish tools that come from different upstream servers.

Search uses fuzzy matching to locate available tools. Execution is governed by policies that can apply globally, per server, or per tool. Each policy can allow execution automatically, require approval, or block the tool. Rate limiting is also available.

STDIO upstreams are routed through a per-user manager process. Multiple bridge instances can therefore share one subprocess for an upstream server.

Setup and configuration

The quickest setup path is the init command:

Terminal
npx @crabeye-ai/crabeye-mcp-bridge init

It looks for MCP client configuration from Claude Desktop, Cursor, VS Code Copilot, Windsurf, Zed, Cline, Roo Code, opencode, and Continue.dev. The command lets you choose configurations and can add the bridge entry automatically. opencode and Continue.dev are detection-only in this flow and receive a manual configuration snippet instead of an automatic rewrite. restore reverses changes made by initialization.

Manual configurations can place upstream definitions under upstreamMcpServers. The bridge also reads upstreamServers, servers for VS Code Copilot, and context_servers for Zed. Existing mcpServers entries can also be used when the bridge excludes its own entry. Supplying --config points the bridge at a specific configuration file.

Credentials can be stored with the CLI credential command and referenced in configuration using ${credential:key} templates. HTTP upstreams can use the one-shot auth <server> OAuth flow. Claude Code can install the bridge through its marketplace and plugin commands.

Tools and capabilities

  • search_tools: searches the indexed tools exposed by configured upstream servers.
  • run_tool: invokes a selected upstream tool through the bridge.
  • Namespaces separate tools from different servers.
  • Policies support always, prompt, and never behavior at global, server, or tool scope.
  • The encrypted credential store uses an OS-keychain-backed master key.
  • CLI commands include init, restore, credential, daemon, and --validate.

The bridge automatically excludes itself from discovered upstream configuration, preventing recursive self-registration when the same file is used for both settings and the bridge entry.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Crabeye MCP Bridge

crabeye-mcp-bridge is an MCP server that connects an AI assistant to multiple upstream MCP servers through one STDIO connection. Its main tools, `search_tools` and `run_tool`, discover and execute namespaced upstream tools while keeping their schemas out of the context window until needed.

Run `npx @crabeye-ai/crabeye-mcp-bridge init` to discover supported client configurations and add the bridge, then start it with `npx @crabeye-ai/crabeye-mcp-bridge`. You can also configure the bridge manually with `--config` or install its Claude Code plugin.

crabeye-mcp-bridge supports STDIO, HTTP, and SSE upstream MCP servers. STDIO upstreams are routed through a per-user manager process so multiple bridge instances can share one upstream subprocess.

crabeye-mcp-bridge uses global, per-server, and per-tool policies with `always`, `prompt`, or `never` behavior. It also supports rate limiting, allowing selected tools to run automatically, request approval, or remain blocked.

Yes, crabeye-mcp-bridge can discover Cursor MCP configuration during `init`, and the bridge can be added to the client configuration. Cursor is one of the clients recognized by the initialization command.

Related MCP servers

All in Aggregators All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewCrabeye MCP Bridge AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/crabeye-mcp-bridge?style=directory)](https://allmcps.com/mcp/crabeye-mcp-bridge)
HTML Embed
<a href="https://allmcps.com/mcp/crabeye-mcp-bridge"><img src="https://allmcps.com/api/badge/crabeye-mcp-bridge?style=directory" alt="Crabeye MCP Bridge on AllMCPs" /></a>