explain — valem MCP Tool
explain
(explain) is one of 27 tools on the
valem
MCP server. Connect the server and your client discovers it on the handshake.
by client
How to call explain from your client
- Claude Code valem explain run in your project directory
- Claude Desktop valem explain ~/Library/Application Support/Claude/claude_desktop_config.json
- Cursor valem explain ~/.cursor/mcp.json
- VS Code valem explain .vscode/mcp.json
- Zed valem explain ~/.config/zed/settings.json
- Windsurf valem explain ~/.codeium/windsurf/mcp_config.json
- Cline valem explain ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
- Gemini CLI valem explain ~/.gemini/settings.json
- Grok valem explain .mcp.json (in your project root)
- ChatGPT valem explain Settings → Connectors → Advanced → Developer mode
- Claude.ai valem explain Settings → Connectors → Add custom connector
- LangChain valem explain pip install langchain-mcp-adapters
Fastest route
claude mcp add --transport http valem https://valem.run/mcpOther tools on this server
- list_models
- create_model
- get_model_info
- get_spec
- get_library
- get_state
- get_field
- mutate
- patch_model
- get_effective_schema
- snapshot
- restore
- get_history
- get_audit
- verify_audit
- upload_blob
- download_blob
- evolve_spec
- delete_model
- get_view
- get_domain_guidance
- validate_spec
- eval_expression
- test_spec
- dry_run
- pair_browser
This list was read from the server itself, by connecting to it and calling tools/list on 24 September 2026. It is what
the server actually exposes, not what its listing claims.
Mutating and Read-only are read off each tool's name, not its schema — a hint, not a guarantee. The registry stores tool names only; connect the server for its live schemas.