F
licenseNot graded
qualityD
maintenanceEnables querying machine-learning experiments in natural language. Supports listing, inspecting, ranking, and comparing experiment runs.
-
exp-agent
Related Servers
Alternatives to exp-agent
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityDmaintenanceExposes TensorBoard experiment data through a standardized MCP API, enabling AI coding agents to query and analyze scalars, tensors, histograms, distributions, and images from ML experiment logs.MIT
- AlicenseNot gradedqualityCmaintenanceEnables MCP clients to query bundled synthetic logs, service metrics, and traces through three bounded read-only tools for evidence-first incident investigation.MIT
- AlicenseNot gradedqualityAmaintenanceEnables external agents to monitor and control ML training runs via 35 MCP tools. Covers training status, checkpoints, experiments, recovery, and dashboard configuration.2MIT
- AlicenseNot gradedqualityAmaintenanceEnables MCP clients to list and inspect evaluation tasks, score model answers, run the full benchmark, and retrieve provenance information.266 npmMIT
- AlicenseNot gradedqualityCmaintenanceEnables MCP-compatible clients to semantically search, retrieve, and list engineering runbooks, providing relevant runbooks in response to natural language queries.MIT
TDQS
A4/5.0
Scored across 6 tools
Disambiguation5/5
Each tool has a clearly distinct purpose: listing runs, reading config, reading final metrics, comparing runs, reading one metric curve, and diagnosing failures. The only apparent overlap between get_final_metrics and compare_runs is resolved by their descriptions: one reads a single run's metrics, the other ranks multiple runs.
Naming Consistency5/5
All tools follow a consistent snake_case verb_noun pattern: list_runs, get_run_config, get_final_metrics, compare_runs, get_metric_curve, diagnose_run. There are no mixed conventions or vague names.
Tool Count5/5
Six tools is well-scoped for inspecting and analyzing training runs. Each tool covers a distinct analysis need, and none feels redundant or extraneous.
Completeness4/5
The set covers the core lifecycle of run inspection: listing, configuration, final metrics, curve inspection, comparison, and diagnosis. Minor gaps remain, such as filtering runs or comparing metric curves across runs, but agents can work around these with the existing tools.
Maintenance
ActivityMaintained
ResponsivenessNo issues