benchmarks_list — AILANG Executor MCP Tool
benchmarks_list
(benchmarks list) is one of 29 tools on the
AILANG Executor
MCP server. Connect the server and your client discovers it on the handshake.
by client
How to call benchmarks_list from your client
- Claude Code AILANG Executor benchmarks_list run in your project directory
- Claude Desktop AILANG Executor benchmarks_list ~/Library/Application Support/Claude/claude_desktop_config.json
- Cursor AILANG Executor benchmarks_list ~/.cursor/mcp.json
- VS Code AILANG Executor benchmarks_list .vscode/mcp.json
- Zed AILANG Executor benchmarks_list ~/.config/zed/settings.json
- Windsurf AILANG Executor benchmarks_list ~/.codeium/windsurf/mcp_config.json
- Cline AILANG Executor benchmarks_list ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
- Gemini CLI AILANG Executor benchmarks_list ~/.gemini/settings.json
- Grok AILANG Executor benchmarks_list .mcp.json (in your project root)
- ChatGPT AILANG Executor benchmarks_list Settings → Connectors → Advanced → Developer mode
- Claude.ai AILANG Executor benchmarks_list Settings → Connectors → Add custom connector
- LangChain AILANG Executor benchmarks_list pip install langchain-mcp-adapters
Fastest route
claude mcp add --transport http ailang-executor https://executor.ailang.sunholo.com/mcp/connect/Other tools on this server
- ailang_builtins
- ailang_check
- ailang_eval
- ailang_prompt
- ailang_run
- ailang_versions
- benchmark_run
- benchmarks_compare
- benchmarks_for_model
- changelog_for_version
- design_doc
- design_docs_list
- docs_nav
- docs_search
- effects_catalog
- example_for_concept
- example_get
- examples_list
- executor_whoami
- install_guide
- limitations_list
- onboarding_guide
- prompt_get
- roadmap
- stdlib_module
- stdlib_modules
- stdlib_search
- submit_feedback
This list was read from the server itself, by connecting to it and calling tools/list on 14 November 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.