# TalBenAmii/llm-d-bench-mcp

Source: https://glimind.com/server/glama%2Ftalbenamii%2Fllm-d-bench-mcp
Registry id: `glama/talbenamii/llm-d-bench-mcp`
Status: unknown

## Tools (31)

- `advise_accelerators`: Advise on accelerators based on environment
- `aggregate_runs`: Aggregate runs
- `analyze_results`: Analyze results
- `cancel_run`: Cancel a run
- `check_capacity`: Check capacity
- `check_endpoint_readiness`: Check endpoint readiness
- `compare_harness_runs`: Compare harness runs
- `compare_reports`: Compare reports
- `discover_stack`: Discover the stack
- `ensure_repos`: Ensure repositories are set up
- `estimate_run_duration`: Estimate run duration
- `execute_llmdbenchmark`: Execute the llm-d benchmark
- `export_run_bundle`: Export a run bundle
- `fetch_key_docs`: Fetch key documentation
- `generate_doe_experiment`: Generate a design of experiments
- `list_catalog`: List the catalog of available items
- `locate_and_parse_report`: Locate and parse a benchmark report
- `manage_orchestrated_runs`: Manage orchestrated runs
- `observe_run_metrics`: Observe run metrics
- `orchestrate_benchmark_run`: Orchestrate a benchmark run
- `orchestrate_sweep`: Orchestrate a sweep
- `probe_environment`: Inspect the environment, GPUs, catalog, docs, knowledge
- `propose_session_plan`: Propose a session plan
- `provision_hf_secret`: Provision a Hugging Face secret
- `read_knowledge`: Read a knowledge file
- `read_repo_doc`: Read a repository document
- `reproduce_run`: Reproduce a run
- `result_history`: Get result history
- `run_setup`: Run setup
- `search_knowledge`: Search the knowledge base
- `write_and_validate_config`: Write and validate configuration

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.