sktime-mcp
MCP (Model Context Protocol) layer for sktime - Registry-Driven for LLMs
A semantic engine that exposes sktime's native registry and semantics to Large Language Models, enabling them to:
- 🔍 Discover valid estimators
- 🧠 Reason about estimator capabilities
- 🔗 Compose compatible estimators
- ⚡ Execute real sktime workflows on real data
🎯 Design Philosophy
This MCP is not just documentation or static code analysis. It is a semantic engine for programmatic model usage.
Key Principles
-
sktime as Source of Truth - No AST parsing, no repo indexing, no heuristics. All structure comes from
all_estimators, estimator tags, and sktime's API contracts. -
Registry-First - Instead of
File → Class → Infer Relationships, we doRegistry → Semantics → Safe Execution. -
Minimal MCP Surface - Exposes only what an LLM needs: Discovery, Description, Instantiation, Execution.
🛠️ Installation
# Install from source
pip install -e .
# With all optional dependencies
pip install -e ".[all]"
# Development installation
pip install -e ".[dev]"
🚀 Quick Start
Running the MCP Server
# Start the MCP server
sktime-mcp
# Or run directly
python -m sktime_mcp.server
Connecting from an LLM Client
The server uses stdio transport by default, compatible with Claude Desktop and other MCP clients.
Add to your Claude Desktop config (~/.config/claude/claude_desktop_config.json):
{
"mcpServers": {
"sktime": {
"command": "sktime-mcp"
}
}
}
📚 Available Tools
Discovery & Search
1. list_estimators
Discover estimators by task type and capability tags.
Arguments:
task(optional): Task type filter ("forecasting","classification","regression","transformation","clustering")tags(optional): Filter by capability tags (e.g.,{"capability:pred_int": true})limit(optional): Maximum results (default: 50)
Example:
{
"task": "forecasting",
"tags": {
"capability:pred_int": true
},
"limit": 10
}
Returns: List of matching estimators with name, task, and summary info.
2. search_estimators
Search estimators by name or description using text query.
Arguments:
query(required): Search string (case-insensitive)limit(optional): Maximum results (default: 20)
Example:
{
"query": "ARIMA",
"limit": 5
}
Returns: List of estimators matching the search query.
3. describe_estimator
Get detailed information about a specific estimator's capabilities.
Arguments:
estimator(required): Name of the estimator (e.g.,"ARIMA","NaiveForecaster")
Example:
{
"estimator": "ARIMA"
}
Returns: Full estimator details including tags, hyperparameters, docstring, and module path.
4. get_available_tags
List all queryable capability tags across all estimators.
Arguments: None
Returns: List of all available tags (e.g., ["capability:pred_int", "handles-missing-data", ...])
Instantiation
5. instantiate_estimator
Create a single estimator instance and return a handle.
Arguments:
estimator(required): Name of the estimator to instantiateparams(optional): Hyperparameters for the estimator
Example:
{
"estimator": "ARIMA",
"params": {
"order": [1, 1, 1],
"suppress_warnings": true
}
}
Returns: {"success": true, "handle": "est_abc123", "estimator": "ARIMA", "params": {...}}
6. instantiate_pipeline
Create a complete pipeline from a list of components (transformers → forecaster).
Arguments:
components(required): List of estimator names in pipeline orderparams_list(optional): List of parameter dicts for each component
Example:
{
"components": ["ConditionalDeseasonalizer", "Detrender", "ARIMA"],
"params_list": [{}, {}, {"order": [1, 1, 1]}]
}
Returns: {"success": true, "handle": "est_xyz789", "pipeline": "ConditionalDeseasonalizer → Detrender → ARIMA", ...}
Note: This solves the "steps problem" - you don't need to instantiate components separately!
📖 Documentation
Project documentation lives in docs/ and can be served locally with MkDocs:
pip install -e ".[dev]"
mkdocs serve
The MkDocs config is in mkdocs.yml.
Validation
7. validate_pipeline
Check if a proposed pipeline composition is valid before instantiation.
Arguments:
components(required): List of estimator names in pipeline order
Example:
{
"components": ["Detrender", "ARIMA"]
}
Returns: {"valid": true/false, "errors": [...], "warnings": [...], "suggestions": [...]}
Execution
8. fit_predict
Execute a complete workflow: load dataset, fit estimator, and generate predictions.
Arguments:
estimator_handle(required): Handle frominstantiate_estimatororinstantiate_pipelinedataset(required): Dataset name (e.g.,"airline","sunspots","lynx")horizon(optional): Forecast horizon (default: 12)
Example:
{
"estimator_handle": "est_abc123",
"dataset": "airline",
"horizon": 12
}
Returns: {"success": true, "predictions": {1: 450.2, 2: 455.1, ...}, "horizon": 12}
Datasets
9. list_datasets
List all available demo datasets for testing and experimentation.
Arguments: None
Returns: {"success": true, "datasets": ["airline", "sunspots", "lynx", "shampoo", ...]}
Handle Management
10. list_handles
List all active estimator handles and their status.
Arguments: None
Returns: List of active handles with metadata (estimator name, fitted status, creation time)
11. release_handle
Release an estimator handle and free memory.
Arguments:
handle(required): Handle ID to release
Example:
{
"handle": "est_abc123"
}
Returns: {"success": true, "message": "Handle released"}
🔄 Example LLM Flows
Flow 1: Simple Forecasting
User Prompt: "Forecast monthly airline passengers using a probabilistic model."
LLM Steps:
-
Discover Models
list_estimators(task="forecasting", tags={"capability:pred_int": true}) -
Inspect Choice
describe_estimator(estimator="ARIMA") -
Instantiate
instantiate_estimator(estimator="ARIMA", params={"order": [1,1,1]}) → Returns: {"handle": "est_abc123"} -
Execute
fit_predict(estimator_handle="est_abc123", dataset="airline", horizon=12) → Returns: {"predictions": {1: 450.2, 2: 455.1, ...}}
Flow 2: Pipeline Forecasting ⭐
User Prompt: "Forecast with deseasonalization and detrending preprocessing."
LLM Steps:
-
Validate Composition
validate_pipeline(components=["ConditionalDeseasonalizer", "Detrender", "ARIMA"]) → Returns: {"valid": true} -
Instantiate Pipeline (single call!)
instantiate_pipeline( components=["ConditionalDeseasonalizer", "Detrender", "ARIMA"], params_list=[{}, {}, {"order": [1,1,1]}] ) → Returns: {"handle": "est_xyz789", "pipeline": "ConditionalDeseasonalizer → Detrender → ARIMA"} -
Execute
fit_predict(estimator_handle="est_xyz789", dataset="airline", horizon=12) → Returns: {"predictions": {...}}
📁 Project Structure
sktime_mcp/
├── src/sktime_mcp/
│ ├── server.py # MCP server entry point
│ ├── registry/ # Registry interface & tag resolver
│ ├── composition/ # Pipeline composition validator
│ ├── runtime/ # Execution engine & handle management
│ └── tools/ # MCP tool implementations
├── examples/ # Usage examples
└── tests/ # Test suite
🧪 Running Tests
pytest tests/
Metadata
Release files for sktimecopilot 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 |
|---|---|---|---|---|
| sktimecopilot-0.1.0.tar.gz | 42.6 kB | Without provenance | Details for sktimecopilot-0.1.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| sktimecopilot-0.1.0-py3-none-any.whl | Python 3 | none | any | Details for sktimecopilot-0.1.0-py3-none-any.whl |
Total release size: 97.0 kB
Release files / sktimecopilot-0.1.0.tar.gz
| Download URL | sktimecopilot-0.1.0.tar.gz |
|---|---|
| Size | 42.6 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
91378da2cc59ff51e90256b55b386313a4d424af4386d7ba2c6f337a5bfa02ff
|
|
BLAKE2b-256 checksum How to use checksums |
26b8cfa6db4bc93f227c9c04ae0690919d9d19597f1a7fcffeb9f2c7cb58b720
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.3
|
Release files / sktimecopilot-0.1.0-py3-none-any.whl
| Download URL | sktimecopilot-0.1.0-py3-none-any.whl |
|---|---|
| Size | 54.3 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
987d13d0dcb0644a2e4b03d6f6555ae37bb2afc706df56df304b3564c908ef01
|
|
BLAKE2b-256 checksum How to use checksums |
3b69d470487af610ccc0274bb41c8afe3e9e6c05966e0da615264a05e7a5163e
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.3
|
Security for sktimecopilot 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.