MCP server for connecting to CodeMie Datasources
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"codemie-mcp-datasources","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# CodeMie Datasources MCP Server Python server implementing Model Context Protocol (MCP) for CodeMie Datasources operations. ## Features - List and filter datasources - Get datasource details - Create code datasources - Update datasources - Delete datasources - Monitor datasource processing status Note: The server requires authentication credentials via environment variables. ## API ### Tools #### list_datasources Get list of available datasources with filtering and pagination Inputs: - `page (integer, optional)`: Page number (default: 0) - `per_page (integer, optional)`: Items per page (default: 10) - `sort_key (string, optional)`: Sort by 'date' or 'update_date' (default: 'update_date') - `sort_order (string, optional)`: Sort order 'asc' or 'desc' (default: 'desc') - `datasource_types (array, optional)`: Filter by datasource types - `projects (array, optional)`: Filter by project names - `owner (string, optional)`: Filter by owner - `status (string, optional)`: Filter by status Returns list of datasources with their details #### get_datasource Get detailed information about a specific datasource Inputs: - `datasource_id (string)`: ID of the datasource to retrieve Returns complete datasource details including configuration #### create_code_datasource Create a new code datasource Inputs: - `name (string)`: Datasource name (lowercase letters and underscores only) - `description (string)`: Datasource description - `project_name (string)`: Project name - `repository_link (string)`: Git repository URL - `branch (string)`: Git branch name - `index_type (string, optional)`: Type of indexing - 'code', 'summary', or 'chunk-summary' (default: 'code') - `files_filter (string, optional)`: File patterns to include/exclude - `embeddings_model (string, optional)`: Model for embeddings generation - `shared_with_project (boolean, optional)`: Whether datasource is shared with project (default: false) Returns created datasource details #### update_code_datasource Update …
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.