Alchemite MCP server

Read from the package source without running it. The installed server may list more.

• create_dataset_from_filewrite action

  Create a new dataset from a CSV file.

• create_model_from_filewrite action

  Create a new model from a CSV file and specified output columns.

• create_model_with_datasetwrite action

  Create a new model using a specified dataset ID.

• create_projectwrite action

  Create a new project

• design_new_experiments

  Design new experiments using a specific model ID and parameters for the experiment setup.

• get_all_suggested_experiments

  Get suggested experiments from a specific model using a model ID.

• get_all_suggested_initial_experiments

  Get suggested initial experiments, optionally selecting only

• get_column_names_from_file

  Get column names from a CSV or Excel file specified by file path.

• get_dataset_metadata

  Get metadata for a specific dataset

• get_documents
• get_model_importance

  Get feature importance for a specific model, for every output column. The output is a CSV string

• get_model_metadata

  Get metadata for a specific model

• get_model_predictions

  Get predictions from a specific model using a dataset ID

• get_model_predictions_with_data

  Get predictions from a specific model using provided data. The data should be a CSV string, including headers and row IDs.

• get_section_overview
• get_specific_suggested_experiment

  Get a specific suggested experiment from a specific model using a model ID and experiment ID.

• get_specific_suggested_initial_experiment

  Get a specific suggested initial experiment using an experiment ID.

• list_all_models

  List the metadata for models (paginated, max 100 at a time, default 20)

• list_all_models_in_a_project

  List the metadata for every model in a given project (paginated, max 100 at a time, default 20)

• list_all_projects

  List the metadata for every project

• list_documentation_structure
• list_section_documents
• search_documentation

• Code scan17 source files scanned25/25
• –Live reliabilityno gateway calls yet and no remote to proben/a
• –Tool poisoningtools not inspected (local package is not executed); not countedn/a
• Auth qualitylocal package, no credentials required12/15
• Maintenancerepository not readable: unknown3/15
• Maintainer identityverified namespace with website, no repo4/10

Safety score

68/100

higher than 33% of 4,460 AI and agents servers

Tools

23

the typical AI and agents server has 6

Tools that change things

17%

typical: 0%. Fewer write tools means less an agent can break

Downloads a week

81

more than 59% of 1,538 AI and agents servers with a package

Alchemite MCP: common questions

Is Alchemite MCP server safe?

With care: it is graded C, so read the findings first (68/100). Read the Alchemite MCP safety report

How do I install Alchemite MCP?

It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.

Does Alchemite MCP need an API key?

Not as far as the registry entry and our scan can tell: no credentials are declared or required.

Is Alchemite MCP maintained?

The latest release is v0.7.5.

What can I use instead of Alchemite MCP?

Servers from other publishers that do the same job: Figma Context MCP server, Agent-Native Design MCP server and Roast My Design System MCP server.

How does Alchemite MCP compare with other AI and agents MCP servers?

safety score 68/100 (higher than 33% of 4,460 AI and agents servers); tools 23 (the typical AI and agents server has 6); tools that change things 17% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.