cdes-mcp-server
Exposes Cannabis Data Exchange Standard (CDES) v1 JSON schemas, reference data libraries, and validation tools to AI agents and MCP-compatible clients.
README
CDES MCP Server
Cannabis Data Exchange Standard — Model Context Protocol Server
A public MCP server that exposes the Cannabis Data Exchange Standard (CDES) v1 JSON schemas, reference data libraries, and validation tools to AI agents and MCP-compatible clients.
What is CDES?
The Cannabis Data Exchange Standard is an open-source data standard for the cannabis industry, providing:
- 7 JSON Schemas — Strain, Terpene Profile, Cannabinoid Profile, Terpene, Certificate of Analysis (COA), Rating, Rating Aggregate
- 3 Reference Data Sets — Terpene Library (10 terpenes), Cannabinoid Library (9 cannabinoids), Terpene Color Palette (30 WCAG 2.1 AA colors)
- Validation Tools — Validate any cannabis data object against CDES schemas
Quick Start
Option 1: Use the Public Server (Recommended)
The CDES MCP Server is hosted publicly at https://mcp.cdes.world — no installation needed.
Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"cdes": {
"url": "https://mcp.cdes.world/sse"
}
}
}
VS Code (GitHub Copilot)
Add to .vscode/mcp.json in your project:
{
"mcpServers": {
"cdes": {
"type": "sse",
"url": "https://mcp.cdes.world/sse"
}
}
}
Cursor / Windsurf
{
"mcpServers": {
"cdes": {
"url": "https://mcp.cdes.world/sse"
}
}
}
Health Check
curl https://mcp.cdes.world/health
Option 2: Run Locally (stdio)
Install from source for local/offline use:
git clone https://github.com/Acidni-LLC/cdes-mcp-server.git
cd cdes-mcp-server
pip install -e .
cdes-mcp-server
For local stdio transport, configure your MCP client:
{
"mcpServers": {
"cdes": {
"command": "cdes-mcp-server",
"args": []
}
}
}
Available Tools
| Tool | Description |
|---|---|
list_schemas |
List all CDES v1 schemas with titles, descriptions, and required fields |
get_schema |
Get the full JSON Schema document by name |
validate_data |
Validate a data object against any CDES schema |
get_terpene_info |
Look up detailed terpene information by ID or name |
get_cannabinoid_info |
Look up detailed cannabinoid information by ID or name |
lookup_terpene_color |
Get standardized WCAG 2.1 AA color for a terpene |
list_terpenes |
List all terpenes with summary data |
list_cannabinoids |
List all cannabinoids with summary data |
search_reference_data |
Full-text search across all reference data |
get_cdes_overview |
Comprehensive CDES standard overview |
Available Resources
| URI | Description |
|---|---|
cdes://schemas/v1/strain |
Strain schema |
cdes://schemas/v1/terpene-profile |
Terpene Profile schema |
cdes://schemas/v1/cannabinoid-profile |
Cannabinoid Profile schema |
cdes://schemas/v1/terpene |
Terpene definition schema |
cdes://schemas/v1/coa |
Certificate of Analysis schema |
cdes://schemas/v1/rating |
User Rating schema (CX extension) |
cdes://schemas/v1/rating-aggregate |
Rating Aggregate schema |
cdes://reference/terpene-library |
Terpene reference library (10 terpenes) |
cdes://reference/cannabinoid-library |
Cannabinoid reference library (9 cannabinoids) |
cdes://reference/terpene-colors |
Terpene color palette (30 colors) |
Example Interactions
List all schemas
> Use the CDES server to list all available schemas
The CDES standard includes 7 schemas:
1. Strain — cannabis strain definition with type, effects, flavors
2. Terpene Profile — 21 named terpene measurements
3. Cannabinoid Profile — 13 cannabinoid measurements with computed totals
4. Terpene — individual terpene definition with CAS number, effects
5. COA — Certificate of Analysis with lab info, safety tests
6. Rating — user rating/review (CX extension)
7. Rating Aggregate — aggregated rating statistics
Validate data
> Validate this strain data against the CDES schema:
> {"id": "strain-001", "name": "Blue Dream", "type": "hybrid"}
✅ Valid! The data conforms to the CDES v1 strain schema.
Look up a terpene
> What is Myrcene? Use the CDES terpene library.
Myrcene (CAS: 123-35-3) is a monoterpene with an earthy, musky, herbal
aroma. It's the most common terpene in cannabis (~40% of strains).
Boiling point: 168°C. Key effects: relaxing, sedating, anti-inflammatory.
Found in mango, hops, lemongrass, and thyme.
Schema Structure
All schemas follow JSON Schema Draft 2020-12 with base URI:
https://schemas.terprint.com/cdes/v1/
Schema Relationships
strain.json
├── $ref → terpene-profile.json
├── $ref → cannabinoid-profile.json
└── enums: type, effects, flavors, difficulty
coa.json
├── $ref → terpene-profile.json
├── $ref → cannabinoid-profile.json
└── safetyTests: microbials, pesticides, heavyMetals, ...
terpene-profile.json
└── $defs/terpeneValue: number | {value, loq, lod, ...}
rating.json → rating-aggregate.json (computed)
Reference Data Licensing
| Data Set | License | Description |
|---|---|---|
| Terpene Library | CC0-1.0 | 10 common cannabis terpenes with full metadata |
| Cannabinoid Library | CC0-1.0 | 9 cannabinoids with colors, effects, CAS numbers |
| Terpene Colors | CC0-1.0 | 30 WCAG 2.1 AA-compliant visualization colors |
Development
# Install with dev dependencies
pip install -e ".[dev]"
# Run tests
pytest
# Lint
ruff check src/
ruff format src/
Related Projects
| Project | Description |
|---|---|
| cdes-spec | CDES specification and JSON schemas |
| cdes-sdk-python | Python SDK for CDES (Pydantic models) |
| cdes-reference-data | Reference data (terpenes, cannabinoids) |
| cdes.world | CDES documentation website |
License
- Code: Apache 2.0
- Schemas: CC BY 4.0
- Reference Data: CC0 1.0
Built by Acidni LLC — Powering the cannabis data ecosystem.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.