Crabeye Mcp Bridge
If you're running more than a handful of MCP servers and watching your context window fill up with hundreds of tool definitions before the conversation even starts, this consolidates them all behind a single connection. It exposes just two tools: search_tools for fuzzy discovery and run_tool for execution. Everything else stays indexed but out of context until you actually need it. You also get namespacing, per-tool execution policies (always run, prompt first, or block), an encrypted credential store, and a shared STDIO manager so multiple bridge instances don't spawn duplicate upstream processes. Works with Linear, GitHub, Slack, and any other MCP server you point it at.
- GitHub stars
- 20
- tools
- 2
- transport
- STDIO
- last updated
- Nov 10, 2026
Tools
2 toolsPublic tool metadata for what this MCP can expose to an agent.
search_toolsSearches the indexed tools from all upstream servers so the assistant can find them without loading their schemas into the context window.
Searches the indexed tools from all upstream servers so the assistant can find them without loading their schemas into the context window.
No parameter schema in public metadata yet.
run_toolExecutes a tool discovered through the bridge, subject to the configured execution policies.
Executes a tool discovered through the bridge, subject to the configured execution policies.
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageReadme
Crabeye MCP Bridge
One MCP connection for all your tools — with discovery, namespacing, and execution policies.
Every MCP server you add to your AI assistant means another connection, another set of tool definitions injected into the context window, and no way to search or control them centrally. Wire up ten servers with a hundred tools each and your assistant is burning tokens on a thousand tool schemas before the conversation even starts — most of which it will never call.
crabeye-mcp-bridge consolidates all your upstream MCP servers behind a single STDIO interface and exposes exactly two tools to the assistant: search_tools and run_tool. Tools from every server are discovered, namespaced, and indexed as soon as your assistant connects, but none of them touch the context window until the assistant actually searches for them. You can have a thousand tools ready to go without bloating the context, with fuzzy search to find them and per-tool execution policies to control what runs freely, what needs approval, and what is blocked.
Details
- Repository
- github.com/crabeye-ai/crabeye-mcp-bridge
- Package
@crabeye-ai/crabeye-mcp-bridge- Transport
- STDIO
- Registry
- MCP registry, active