Skip to main content

Bidirectional MCP proxy that translates between JSON and GCF. 79% fewer input tokens, 63% fewer output tokens. Zero code changes.

Project description

gcf-proxy

Bidirectional MCP proxy that translates between GCF and JSON. Drop-in, zero code changes to your server or client.

79% fewer input tokens. 63% fewer output tokens. 90.7% comprehension accuracy across 10 models and 3 providers. 1,300+ LLM evaluations. Zero training.

Docs: gcformat.com · Proxy Guide · Playground · GCF vs TOON

Install

pip install gcf-proxy

Setup (one line change)

Before:

{"mcpServers": {"yours": {"command": "your-mcp-server"}}}

After:

{"mcpServers": {"yours": {"command": "gcf-proxy", "args": ["your-mcp-server"]}}}

Works with Claude Code, Claude Desktop, VS Code, Cursor, and any MCP client.

What it does

Translates in both directions:

Responses:  Your Server (JSON) -> gcf-proxy encodes -> LLM reads GCF   (79% input savings)
Requests:   LLM writes GCF    -> gcf-proxy decodes -> Your Server (JSON) (63% output savings)
  • Responses: JSON tool results from the server are encoded as GCF
  • Requests: GCF strings in tool call arguments are decoded to JSON (4-byte prefix check, zero overhead)
  • Non-convertible content passes through unchanged in both directions
  • Neither the server nor the client needs to know about GCF

Savings

JSON   2,506 bytes  ~626 tokens
GCF      916 bytes  ~229 tokens   (63% fewer)

With session dedup (92.7% by 5th call) and delta encoding (81.2%), use the GCF libraries directly.

Benchmarks

Format Accuracy Tokens vs JSON
GCF 90.7% avg (10 models) 11,090 79% fewer
TOON 68.5% avg 16,378 69% fewer
JSON 53.6% avg 53,341 baseline

Also available on

  • npm: npm install -g @blackwell-systems/gcf-proxy
  • Go: go install github.com/blackwell-systems/gcf-proxy@latest

Links

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distributions

If you're not sure about the file name format, learn more about wheel file names.

gcf_proxy-0.10.1-py3-none-win_arm64.whl (5.4 MB view details)

Uploaded Python 3Windows ARM64

gcf_proxy-0.10.1-py3-none-win_amd64.whl (3.1 MB view details)

Uploaded Python 3Windows x86-64

gcf_proxy-0.10.1-py3-none-manylinux2014_x86_64.whl (6.1 MB view details)

Uploaded Python 3

gcf_proxy-0.10.1-py3-none-manylinux2014_aarch64.whl (5.8 MB view details)

Uploaded Python 3

gcf_proxy-0.10.1-py3-none-macosx_11_0_arm64.whl (5.8 MB view details)

Uploaded Python 3macOS 11.0+ ARM64

gcf_proxy-0.10.1-py3-none-macosx_10_12_x86_64.whl (6.1 MB view details)

Uploaded Python 3macOS 10.12+ x86-64

File details

Details for the file gcf_proxy-0.10.1-py3-none-win_arm64.whl.

File metadata

  • Download URL: gcf_proxy-0.10.1-py3-none-win_arm64.whl
  • Upload date:
  • Size: 5.4 MB
  • Tags: Python 3, Windows ARM64
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.13

File hashes

Hashes for gcf_proxy-0.10.1-py3-none-win_arm64.whl
Algorithm Hash digest
SHA256 5b106b91669649e56f937a141cad8b84b250216fa17d5b9f3ab397d4c43a8fd7
MD5 79dfeb89b3091124498b6a857d8ae8e6
BLAKE2b-256 82550f842c0131a664150530af6e1d20843161dfd1218f2df04b2e96e8deabc4

See more details on using hashes here.

File details

Details for the file gcf_proxy-0.10.1-py3-none-win_amd64.whl.

File metadata

  • Download URL: gcf_proxy-0.10.1-py3-none-win_amd64.whl
  • Upload date:
  • Size: 3.1 MB
  • Tags: Python 3, Windows x86-64
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.13

File hashes

Hashes for gcf_proxy-0.10.1-py3-none-win_amd64.whl
Algorithm Hash digest
SHA256 8ad3ac5e081d2bb0e3efabc434001f3e6bca8621e7e0d3ffe329cb694b1d251f
MD5 4d6e777a73aa03cd2b300b561f1a6713
BLAKE2b-256 7f368006592e56612268fd39b38c3f873888c579e77793b849770942f1c6542f

See more details on using hashes here.

File details

Details for the file gcf_proxy-0.10.1-py3-none-manylinux2014_x86_64.whl.

File metadata

File hashes

Hashes for gcf_proxy-0.10.1-py3-none-manylinux2014_x86_64.whl
Algorithm Hash digest
SHA256 18d9963ae335e3fbd7811382855be633105321df71a373b9e99523f324613f6a
MD5 4be83a800f3964d911b91f11d3b96423
BLAKE2b-256 852fbb97202c4295fcfe703d8a6052a529361c9bc07742958ba7df130d4af34d

See more details on using hashes here.

File details

Details for the file gcf_proxy-0.10.1-py3-none-manylinux2014_aarch64.whl.

File metadata

File hashes

Hashes for gcf_proxy-0.10.1-py3-none-manylinux2014_aarch64.whl
Algorithm Hash digest
SHA256 1b62d54148f881f5090998aaafafdf49d09653a9faa48b6ff368b83a01c83b48
MD5 dd2990b7e86a8da028ad2d844526c610
BLAKE2b-256 53ffdd1c2ad9548b2cd1da0445b30343bcbaf936765745e8fd9ab31d6dc88b5f

See more details on using hashes here.

File details

Details for the file gcf_proxy-0.10.1-py3-none-macosx_11_0_arm64.whl.

File metadata

File hashes

Hashes for gcf_proxy-0.10.1-py3-none-macosx_11_0_arm64.whl
Algorithm Hash digest
SHA256 c1551a5061ed2babc3ac3907d66d0b1b98fc80f0ca70344ff9daec0226f1181b
MD5 6cb67b35093d330350ed2f334c760064
BLAKE2b-256 7c543241c7a86e5f88fd37c7bed880c1f4998cb1edd7f7a730f7725d455c0599

See more details on using hashes here.

File details

Details for the file gcf_proxy-0.10.1-py3-none-macosx_10_12_x86_64.whl.

File metadata

File hashes

Hashes for gcf_proxy-0.10.1-py3-none-macosx_10_12_x86_64.whl
Algorithm Hash digest
SHA256 c31c7d4f969d92bd7fe91e6915d5dee2fba69f9e0b2d043f26c7093225449a79
MD5 5a4dada04d486f9db05c22d464d4b7c2
BLAKE2b-256 15c11180b264f87aa219a8928ff6a1d5c47bb2e8a0d55cf140c7e6860f6ff0d2

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page