gcf-proxy MCP Server

Drop-in MCP proxy that losslessly re-encodes JSON tool responses as GCF. 71% fewer tokens, 100% comprehension across 1,700+ LLM evaluations. Zero code changes.

GitHub

Documentation

gcf-proxy

Bidirectional MCP proxy that translates between JSON and GCF. Drop-in, zero changes to your server or client. Works with any structured data format.

100% comprehension on every frontier model. 25.5% fewer tokens than TOON, 53% fewer than JSON (1,700+ evals, 10+ models, 3 providers). One line change in your MCP config.

Install

pip install gcf-proxy                                         # PyPI
npm install -g @blackwell-systems/gcf-proxy                   # npm
go install github.com/blackwell-systems/gcf-proxy@latest      # Go

Try it (30 seconds, no auth)

gcf-proxy --verbose uvx yfinance-mcp

Use it with any MCP client. When tools return structured JSON, the proxy re-encodes to GCF and logs savings to stderr:

gcf-proxy: get_price_history              54.0KB -> 28.1KB (48% saved)
gcf-proxy: get_ticker_info                10.0KB -> 7.4KB (26% saved)
gcf-proxy: get_price_history              53.8KB -> 27.9KB (48% saved)

--- gcf-proxy session stats ---
Tool calls rewritten:  3
JSON bytes in:         117.8KB
GCF bytes out:         63.4KB
Bytes saved:           54.4KB (46.2%)
Est. tokens saved:     ~13.6K
-------------------------------

Real live stock data from Yahoo Finance. 118KB of JSON reduced to 63KB. ~13,600 tokens saved in 3 tool calls.

Usage

Local server (stdio)

Add gcf-proxy in front of any MCP server command:

{
  "mcpServers": {
    "memory": {
      "command": "gcf-proxy",
      "args": ["npx", "-y", "@modelcontextprotocol/server-memory"]
    }
  }
}

Remote server (HTTP)

Point --upstream at any Streamable HTTP MCP server:

{
  "mcpServers": {
    "remote": {
      "command": "gcf-proxy",
      "args": ["--upstream", "http://host:3000/mcp"]
    }
  }
}

Supports JSON and SSE responses. Session ID tracking via Mcp-Session-Id is automatic.

Deploy as HTTP service

--http turns the proxy into a remote Streamable HTTP server:

gcf-proxy --http :9090 --session your-mcp-server

Any MCP client that supports HTTP transport connects directly. Health check at /health. Chains with --upstream for fully remote deployments.

Both modes are bidirectional: server responses are encoded to GCF, GCF in tool call arguments is decoded to JSON. Neither side needs to change.

Responses: Server (JSON) -> LLM (GCF)

Before: {"tool":"context_for_task","symbols":[{"qualified_name":"pkg.Auth","kind":"function","score":0.78,...},...]}
After:  GCF profile=graph tool=context_for_task budget=5000 tokens=1900 symbols=50 edges=20
        ## targets
        @0 fn pkg.Auth 0.78 lsp_resolved
        ...

53-71% fewer input tokens.

Requests: LLM (GCF) -> Server (JSON)

If the LLM produces GCF in a tool call argument (63% fewer output tokens), the proxy decodes it to JSON before forwarding:

LLM sends:    {"tool": "process", "arguments": {"data": "GCF profile=generic\nname=Alice\nage=30\n"}}
Server gets:  {"tool": "process", "arguments": {"data": {"name": "Alice", "age": 30}}}

Detection is a 4-byte prefix check (GCF ). Zero overhead. Non-GCF strings pass through untouched.

How it works

Spawns your MCP server as a subprocess
Proxies stdin/stdout between client and server
Responses: intercepts JSON-RPC responses, re-encodes structured JSON as GCF
Requests: scans tool call arguments for GCF strings, decodes to JSON
Passes everything else through unchanged in both directions

Why not modify the server?

Sometimes you can't. The server is a third-party binary, or it's maintained by another team, or you just don't want to add a dependency. gcf-proxy gives you the token savings without touching server code.

If you control the server, use the GCF libraries directly for better control over session deduplication and delta encoding.

Benchmarks

100% comprehension on standard workloads. 90.7% on code graphs (vs TOON 68.5%, JSON 53.6%). Wins 13/15 datasets on expanded token benchmark.

Format	Accuracy	Tokens	vs JSON
GCF	100% (frontier models)	11,090-24,000	53-71% fewer
TOON	68.5% avg	16,378	69% fewer
JSON	53.6% avg	53,341	baseline

Reproduce comprehension eval: git clone https://github.com/blackwell-systems/gcf-go && cd gcf-go/eval && GOWORK=off go test -run TestComprehension -v -timeout 0

Reproduce token benchmark: git clone https://github.com/blackwell-systems/toon && cd toon && git checkout gcf-comparison && cd benchmarks && pnpm install && pnpm benchmark:tokens

License

MIT - Dayna Blackwell / GCF