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-0.9.0-py3-none-win_arm64.whl (5.4 MB view details)

Uploaded Python 3Windows ARM64

gcf_proxy-0.9.0-py3-none-win_amd64.whl (3.1 MB view details)

Uploaded Python 3Windows x86-64

gcf_proxy-0.9.0-py3-none-manylinux2014_x86_64.whl (6.1 MB view details)

Uploaded Python 3

gcf_proxy-0.9.0-py3-none-manylinux2014_aarch64.whl (5.8 MB view details)

Uploaded Python 3

gcf_proxy-0.9.0-py3-none-macosx_11_0_arm64.whl (5.8 MB view details)

Uploaded Python 3macOS 11.0+ ARM64

gcf_proxy-0.9.0-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-0.9.0-py3-none-win_arm64.whl.

File metadata

  • Download URL: gcf_proxy-0.9.0-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-0.9.0-py3-none-win_arm64.whl
Algorithm Hash digest
SHA256 10baf70e44055eda54fa632271f5cee769cd12a06b0c1531a3a2462a8de8ff32
MD5 1dd943e4f4c7d0a7a6763edc2b918d13
BLAKE2b-256 317fec12e5155a08ca59ce47adf02573075203b4d42fb774ad83162ba06ba5e7

See more details on using hashes here.

File details

Details for the file gcf_proxy-0.9.0-py3-none-win_amd64.whl.

File metadata

  • Download URL: gcf_proxy-0.9.0-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-0.9.0-py3-none-win_amd64.whl
Algorithm Hash digest
SHA256 2dcf1a0bd19af3e8c45d10f9e2e755c488ffbc70d69befb4fd0d5411f31d9769
MD5 08f92535c094abe2a340f56ae838577a
BLAKE2b-256 566185322668b2857dfe7fdfd7b1958966fe929505ee462570d0a20a8fdaac2f

See more details on using hashes here.

File details

Details for the file gcf_proxy-0.9.0-py3-none-manylinux2014_x86_64.whl.

File metadata

File hashes

Hashes for gcf_proxy-0.9.0-py3-none-manylinux2014_x86_64.whl
Algorithm Hash digest
SHA256 d0ba9d4366ea9883a66a1684a36170530f9651ccee8686d7a95573343468d1a7
MD5 469248bb6da4ec70fc41aae967cde405
BLAKE2b-256 7e7ac84ef22e862df3d78b266d1efc19526c45081cbd0dae94204f7033894f3a

See more details on using hashes here.

File details

Details for the file gcf_proxy-0.9.0-py3-none-manylinux2014_aarch64.whl.

File metadata

File hashes

Hashes for gcf_proxy-0.9.0-py3-none-manylinux2014_aarch64.whl
Algorithm Hash digest
SHA256 25266e207527cfac123bbc561f67fd67211e918677e445f4b80d7952bfbf95f0
MD5 78f6308ddedff0befce5fc788cf7fc1e
BLAKE2b-256 49854af3ecdb03733e801a21babe4f7062137a4c35bbf425b731d6335a00cd32

See more details on using hashes here.

File details

Details for the file gcf_proxy-0.9.0-py3-none-macosx_11_0_arm64.whl.

File metadata

File hashes

Hashes for gcf_proxy-0.9.0-py3-none-macosx_11_0_arm64.whl
Algorithm Hash digest
SHA256 92b4f0c5549a3c7afa161d88ffddaecf126ebf8fd42b52f3260caebe756ec54d
MD5 1f381e1e1df98783e966744364a9dd29
BLAKE2b-256 04edf11253d8d34ed1543a8d0207ff29cc04dd11ef889b769f4d90783686912c

See more details on using hashes here.

File details

Details for the file gcf_proxy-0.9.0-py3-none-macosx_10_12_x86_64.whl.

File metadata

File hashes

Hashes for gcf_proxy-0.9.0-py3-none-macosx_10_12_x86_64.whl
Algorithm Hash digest
SHA256 753496dead3fc631367464c0c97dce0b23c621fd1d44571f691ded48da123fa3
MD5 5709f7aedae0cc80e1146fe83ef5b0b1
BLAKE2b-256 7eb05ce2350127da99b6cefbdc74d667f4b59b492c0d700367d2322c8ab81c2f

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