ckg-agent-protocols
Agent protocol stack as traversable knowledge graphs — 8 domains, 460 nodes, SHA-256 source provenance.
| Domain | Nodes | Coverage |
|---|---|---|
| a2a-protocol | 73 | A2A Protocol v1.0 — transport, Agent Card, task lifecycle, 10 RPC methods |
| x402-protocol | 55 | x402 Payment Protocol — HTTP 402, PAYMENT-REQUIRED, settlement schemes |
| a2a-x402-integration | 58 | A2A × x402 — Standalone/Embedded flows, signing patterns, 7 error codes |
| a2a-sdk-ecosystem | 52 | a2a-sdk · @a2a-js/sdk · Inspector · TCK · migration guides |
| google-adk-a2a | 48 | RemoteA2aAgent · to_a2a() · ADK 2.0 graph workflows (Experimental) |
| mcp-protocol | 56 | MCP 2026-07-28 — Streamable HTTP only, OAuth 2.1, Python/TS SDK v2 |
| erc8004-agent-trust | 46 | ERC-8004 — on-chain identity (ERC-721), reputation, validation registries |
| a2a-master | 72 | A2A Communication Master — full 7-step flow, cross-protocol constraint matrix |
Install
pip install ckg-agent-protocols
MCP server
uvx ckg-agent-protocols
Claude Desktop config:
{
"mcpServers": {
"agent-protocols": {
"command": "uvx",
"args": ["ckg-agent-protocols"]
}
}
}
HTTP server (x402 + A2A Agent Card)
pip install "ckg-agent-protocols[serve]"
python -m ckg_agent_protocols.serve
/.well-known/agent-card.json— A2A v1.0 Agent Card/.well-known/mcp/pricing.json— pricing tiers/mcp— MCP Streamable HTTP endpoint- Free: 10 calls/hr · x402: $0.010/call USDC Base L2 · Dev: $29/mo
Tools
list_domains()— list all 8 domainssearch_concepts(domain, query)— find concepts by keywordquery_ckg(domain, concept, depth)— traverse the graph from a conceptget_prerequisites(domain, concept)— full upstream prerequisite chainverify_source(domain, concept)— return source URL + SHA-256 hash
Provenance
Every node carries source_url and source_hash (SHA-256 of source bytes at extraction time).
curl -s <source_url> | sha256sum # compare to source_hash
By Graphify.md · patent-pending methodology · benchmark paper
Metadata
Release files for ckg-agent-protocols 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| ckg_agent_protocols-0.1.0.tar.gz | 21.7 kB | Without provenance | Details for ckg_agent_protocols-0.1.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| ckg_agent_protocols-0.1.0-py3-none-any.whl | Python 3 | none | any | Details for ckg_agent_protocols-0.1.0-py3-none-any.whl |
Total release size: 46.2 kB
Release files / ckg_agent_protocols-0.1.0.tar.gz
| Download URL | ckg_agent_protocols-0.1.0.tar.gz |
|---|---|
| Size | 21.7 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
1344fdbd9ffaf2b2cd3421f44d7a94194a7629c07331f10103bb3698defa4ed7
|
|
BLAKE2b-256 checksum How to use checksums |
53cc60edc5c9a24eacf57bc475a7e29c9782e591625e99c1c489ed573eb4845f
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.11.14
|
Release files / ckg_agent_protocols-0.1.0-py3-none-any.whl
| Download URL | ckg_agent_protocols-0.1.0-py3-none-any.whl |
|---|---|
| Size | 24.4 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
a1683c9b2018620f33079b660221c95ec322521ac2c45858360048a38af535b4
|
|
BLAKE2b-256 checksum How to use checksums |
62ab5554eaeae60d717c70e46ab9d66888f4c5ebe1c7ca16c376b5f81b79fd87
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.11.14
|
Security for ckg-agent-protocols 0.1.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.