
4q Tokenz
If you're running Claude with a dozen MCP servers and watching your context window fill up with tool schemas on every turn, this proxy collapses them down to three tools: mcp_search, mcp_call, and mcp_schema. The LLM queries in natural language to find the right tool, then calls it on demand. The proxy sits between your client and upstream servers like Google Workspace or custom APIs, handling discovery with BM25 lexical search and lazy loading tools only when needed. Pure JavaScript, no native dependencies. Most helpful when you're juggling 50+ tools across multiple servers and token overhead is eating into your actual work. Works over stdio or HTTP, and the included systemd service keeps it running in the background.
- tools
- 3
- transport
- STDIO
- last updated
- May 8, 2026
Tools
3 toolsPublic tool metadata for what this MCP can expose to an agent.
mcp_searchSearch the tool catalog for matching tools.
Search the tool catalog for matching tools.
No parameter schema in public metadata yet.
mcp_callInvoke a tool through the proxy, with output shaping unless detail is set to true.
Invoke a tool through the proxy, with output shaping unless detail is set to true.
No parameter schema in public metadata yet.
mcp_schemaRetrieve the schema for a tool.
Retrieve the schema for a tool.
No parameter schema in public metadata yet.
Sponsors
Readme
MCP Proxy Gateway
A context-aware MCP proxy that reduces token usage by exposing only 3 tools (mcp_search, mcp_call, mcp_schema) to LLMs instead of the full catalog.
Why This Exists
When you connect multiple MCP servers to an LLM, every tool from every server is listed in the LLM's context window. For a typical workspace with 50-100 tools across multiple MCP servers, that's thousands of tokens of schema documentation on every request.
MCP Proxy Gateway sits between your LLM and your MCP servers, offering:
- JIT tool loading — tools from upstream servers are discovered once at startup, then tools are called on-demand. Clients never see the full catalog.
- Intelligent search — fast lexical (BM25) search to find the right tool for a query. Tool tokens are pre-computed at startup for zero-overhead per-query scoring.
- Token savings — LLMs only see 3 tool schemas (search, call, schema) instead of 50+. Typical savings: 20-40% per turn for tool-heavy workflows.
- Zero native dependencies — pure JavaScript, no native modules, no model downloads, no supply chain risk from ML packages.
Details
- Repository
- github.com/steveweltman/4q-tokens
- Category
- Search & Web Crawling
- Package
4q-tokenz- Transport
- STDIO
- Registry
- MCP registry, active