Skip to main content

Bidirectional MCP proxy that translates between JSON and GCF. 50-92% fewer tokens. 100% comprehension on every frontier model. 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.

53-71% fewer input tokens. 63% fewer output tokens. 100% comprehension on every frontier model and 3 providers. 1,700+ 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-0.11.0-py3-none-win_arm64.whl (5.5 MB view details)

Uploaded Python 3Windows ARM64

gcf_proxy-0.11.0-py3-none-win_amd64.whl (3.1 MB view details)

Uploaded Python 3Windows x86-64

gcf_proxy-0.11.0-py3-none-manylinux2014_x86_64.whl (6.1 MB view details)

Uploaded Python 3

gcf_proxy-0.11.0-py3-none-manylinux2014_aarch64.whl (5.8 MB view details)

Uploaded Python 3

gcf_proxy-0.11.0-py3-none-macosx_11_0_arm64.whl (5.9 MB view details)

Uploaded Python 3macOS 11.0+ ARM64

gcf_proxy-0.11.0-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-0.11.0-py3-none-win_arm64.whl.

File metadata

  • Download URL: gcf_proxy-0.11.0-py3-none-win_arm64.whl
  • Upload date:
  • Size: 5.5 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-0.11.0-py3-none-win_arm64.whl
Algorithm Hash digest
SHA256 2f29a1819ce9074874e2122164ca20b9e7f7ead2a428616335d7d955e923ea27
MD5 37192196ec705a39acd58c8f0d795755
BLAKE2b-256 c984a6963fa495ff3dd7e7aab2b02d8c49df6d704c4a6496976c7d94687f0462

See more details on using hashes here.

File details

Details for the file gcf_proxy-0.11.0-py3-none-win_amd64.whl.

File metadata

  • Download URL: gcf_proxy-0.11.0-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-0.11.0-py3-none-win_amd64.whl
Algorithm Hash digest
SHA256 6518e44ab9881a4ebeeb6e5cd04bd7b5d8900030fe76350ec29d493820268916
MD5 314781e9b3a4c42e99a4e6d78c251af4
BLAKE2b-256 a41240cde3c70edc069f96ea7d8d8c7768eb34c005829b272f50b672bc3756ba

See more details on using hashes here.

File details

Details for the file gcf_proxy-0.11.0-py3-none-manylinux2014_x86_64.whl.

File metadata

File hashes

Hashes for gcf_proxy-0.11.0-py3-none-manylinux2014_x86_64.whl
Algorithm Hash digest
SHA256 e6075b0fcfb3fa08e655cc7c5bafdc74ccfc554c634ce1f02c11bb3ff18456d6
MD5 a12f6c9e08d85e1aa416b33d28d3ec62
BLAKE2b-256 3119c70dcaccf2f30e4ffb69fa3bcd57beadd53ea0409bc3fd095f138d5ad47b

See more details on using hashes here.

File details

Details for the file gcf_proxy-0.11.0-py3-none-manylinux2014_aarch64.whl.

File metadata

File hashes

Hashes for gcf_proxy-0.11.0-py3-none-manylinux2014_aarch64.whl
Algorithm Hash digest
SHA256 622c42280fc354ea1c6360c381858228f075afdfe1a2dc482007ccca9835bdd2
MD5 8ba1bc45a6ae94974de3238371339e11
BLAKE2b-256 c697dac21da5673d0e8fc3f57e466691126bb50ddb59a3957bd494de6673cf51

See more details on using hashes here.

File details

Details for the file gcf_proxy-0.11.0-py3-none-macosx_11_0_arm64.whl.

File metadata

File hashes

Hashes for gcf_proxy-0.11.0-py3-none-macosx_11_0_arm64.whl
Algorithm Hash digest
SHA256 2d6c9243fa9e0f4c44508bb6e77ea9632e8cfe811e9624eb54639bf2c0ea7742
MD5 c864c7b6f1baa902332bb83fd850f6d3
BLAKE2b-256 e27776d5cc50a8a4e5e0906878a69813e441f49c1712c72f25c1a8a1bc2ea584

See more details on using hashes here.

File details

Details for the file gcf_proxy-0.11.0-py3-none-macosx_10_12_x86_64.whl.

File metadata

File hashes

Hashes for gcf_proxy-0.11.0-py3-none-macosx_10_12_x86_64.whl
Algorithm Hash digest
SHA256 d3279cdf4ad516e4da455e69c7934266e11a6515641165afbc4d2e39a71a08d9
MD5 21b78adaf65f7b8c78a3575066af41b3
BLAKE2b-256 f88110f0d4f21fb52e93ebe484569e735ec59972a951d96f0d256d56a039aae0

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