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.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。