Skip to main content

CKS MCP Server — Canonical Knowledge Structure for LLMs

Project description

CKS MCP Server

Model Context Protocol server for Canonical Knowledge Structure.

Python License Tests

cks-mcp is an MCP (Model Context Protocol) server that provides LLMs with structured, verifiable knowledge operations through the CKS ecosystem. It exposes six tools—validate, query, compare, evolve, derive, and construct—each backed by the deterministic, immutable semantics of cks-core.


Why cks-mcp?

LLMs generate plausible but unverified statements. cks-mcp gives them a canonical knowledge backbone: every piece of information must be explicitly structured, validated against formal constraints, and traceable to its origin. This minimises hallucinations and makes AI‑ generated knowledge auditable.


Installation

pip install cks-mcp

The server requires cks-core (installed automatically as a dependency).


Quick Start

Launch the server:

cks-mcp

An MCP client (Claude Desktop, any MCP-compatible LLM) can then connect and call tools.


Available Tools

Tool Description
validate_knowledge Validate a Knowledge Structure and return diagnostics.
query_relations Find all relations for a given entity.
compare_structures Check semantic equivalence of two structures.
evolve_knowledge Apply Genesis/Decay operators to evolve a structure.
derive_knowledge Derive a new Knowledge Object from existing premises.
construct_knowledge Parse and construct a Knowledge Structure (coming soon).

Usage Example

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "validate_knowledge",
    "arguments": {
      "json_data": "{\"objects\":[{\"identity\":{\"id\":\"obj-1\",\"type\":\"Definition\",\"name\":\"Test\"},\"structure\":{}}]}"
    }
  }
}

Response:

{
  "jsonrpc": "2.0",
  "id": 1,
  "result": "{\"valid\": true, \"error_count\": 0, \"warning_count\": 0, \"diagnostics\": []}"
}

Testing

python -m pytest -v

20 tests, all passing.


Ecosystem

  • cks-core — the canonical knowledge engine (repo)
  • CKS Specifications — formal theory behind the system (DOI)

License

MIT

Project details


Download files

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

Source Distribution

cks_mcp-0.1.1.tar.gz (9.9 kB view details)

Uploaded Source

Built Distribution

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

cks_mcp-0.1.1-py3-none-any.whl (9.7 kB view details)

Uploaded Python 3

File details

Details for the file cks_mcp-0.1.1.tar.gz.

File metadata

  • Download URL: cks_mcp-0.1.1.tar.gz
  • Upload date:
  • Size: 9.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.13

File hashes

Hashes for cks_mcp-0.1.1.tar.gz
Algorithm Hash digest
SHA256 bd541e0fa7e1b71c71abeb29d89a3dd55f4763c256460fa1b9504916f8d01e48
MD5 b8db330b8ddb5c4dcd3bd60cb2c4149d
BLAKE2b-256 153d8b7b77dc0153f6f06a5c338b74a887a8d3d23c5b4bc0d63fee77db763500

See more details on using hashes here.

File details

Details for the file cks_mcp-0.1.1-py3-none-any.whl.

File metadata

  • Download URL: cks_mcp-0.1.1-py3-none-any.whl
  • Upload date:
  • Size: 9.7 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.13

File hashes

Hashes for cks_mcp-0.1.1-py3-none-any.whl
Algorithm Hash digest
SHA256 45b605cebde03599ab5572afec8e21d638185b35debce09dfd71e19d78f99ab1
MD5 185de279aecd18b978ebc3c1278f24b7
BLAKE2b-256 be22d3d7f6c4db0ca94baf9e7aabaa4f020937ca1c9e72da215bf8064e4a7b08

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