SaANN MCP
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
SaANN MCP
A standalone, local Model Context Protocol server that exposes the SaANN machine-learning library over MCP stdio. It trains and evaluates models on the machine running the client; it requires no Docker, FastAPI service, or external backend.
Requirements and installation
Python 3.11 or newer
From the repository root, synchronize the project environment:
uv syncThis installs the MCP server, SaANN, and the development/test dependencies.
SaANN is installed from its upstream Git repository as declared in
pyproject.toml.
Related MCP server: tool-mcp-bridge
Run and test
Start the MCP server over stdio:
uv run saann-mcpRun the test suite:
uv run pytest -vThe tests use temporary CSVs and image folders. Training checkpoints are
written under saann_models/ in the server's current working directory.
MCP tools
inspect_dataset(file_path): Inspect a CSV or an image directory organized into one subdirectory per class.train_model(dataset_path, model_type="mlp", epochs=20, lr=0.01, batch_size=32): Train an MLP from a CSV or a CNN from a class-folder image directory.evaluate_model(model_path, test_data_path): Evaluate a checkpoint created by this server. The corresponding.saann.jsonmetadata file must remain beside the checkpoint. Evaluation reports SaANN's native loss and, for classification, its micro-F1 score (equivalent to single-label accuracy).
For MLP datasets, use numeric feature columns and a target in the final column.
Integer targets with up to 20 distinct values and non-numeric targets are
treated as classification; other numeric targets are treated as regression.
For CNN datasets, include at least two class subdirectories containing BMP,
JPEG, PNG, TIFF, or WebP images. Evaluation data must use the same features or
classes used during training. SaANN uses the part of each class-directory name
before the first underscore as its class label (for example, green_area is
treated as green), so these normalized class names must be unique.
Configure an MCP client
Replace the example path with the absolute path to this repository.
Claude Desktop (claude_desktop_config.json)
{
"mcpServers": {
"saann": {
"command": "uv",
"args": [
"run",
"--directory",
"C:\\path\\to\\saann-mcp",
"saann-mcp"
]
}
}
}Cursor (.cursor/mcp.json)
{
"mcpServers": {
"saann": {
"command": "uvx",
"args": [
"--from",
"C:\\path\\to\\saann-mcp",
"saann-mcp"
]
}
}
}Both configurations run the local project. uv run synchronizes the
repository's project environment; uvx --from runs the project command from
the specified local source.
License
This project is licensed under the MIT License - see the LICENSE file for details.
Author
Alessio Branda - GitHub Profile
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
MCP server providing access to the Scorecard API to evaluate and optimize LLM systems.
An MCP server for search and retrieval over a local LanceDB database
Remote MCP server for supportsheep: run AI interviews and manage support content for your blog.
Related MCP Servers
- AlicenseAqualityBmaintenanceEnables local file search, packing into LLM-ready context, and inspection via an MCP server on stdio.1450 PyPI2MIT
- AlicenseNot gradedqualityCmaintenanceEnables locally configured MCP servers to be called over stdio and mixed with xAI server-side tools, without relying on hosted xAI MCP.MIT
- AlicenseAqualityBmaintenanceEnables MCP-capable AI clients to control a local computer over stdio with filesystem operations, ripgrep search, shell command execution, and persistent process sessions.14MIT
- FlicenseNot gradedqualityAmaintenanceEnables AI agents and MCP clients to query and debug traces, sessions, observations, and exceptions, plus access prompts, datasets, annotation queues, scores, and metrics from a local server.-