A
licenseA
qualityD
maintenanceAn MCP server that enables coding agents to autonomously test, evaluate, and tune other MCP servers by acting as a proxy and providing linting, trace recording, evaluation, comparison, and reporting tools.
7
MIT
profiler-mcp
by Stankye
Related Servers
Alternatives to profiler-mcp
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityCmaintenanceMCP servers for real-time development monitoring and interactive pair programming.1MIT
- AlicenseAqualityDmaintenanceAn MCP server that decodes V8 CPU profiles into token-efficient bottleneck summaries for AI agents, enabling them to analyze CPU consumption, call trees, GC pressure, and async bottlenecks.628 npmMIT
multivon-mcpofficial
AlicenseAqualityAmaintenanceMCP server that gives AI coding agents direct access to evaluation tools.23Apache 2.0- AlicenseNot gradedqualityBmaintenanceLocal MCP servers that give Claude Code access to other tools mid-session.GPL 3.0
- AlicenseNot gradedqualityBmaintenanceA local MCP server that provides tools for AI coding agents to execute, evaluate, and diff regression tests for LLM agents.2 npmMIT
TDQS
A4.3/5.0
Scored across 9 tools
Disambiguation4/5
Most tools have clearly distinct roles: check, collect, list, report, compare, timechart, system info. The three report variants (raw, summary, hotspots) are similar but their descriptions clarify the output formats, and check vs system_info have some overlap but remain distinguishable.
Naming Consistency3/5
All tools share the 'uprof_' prefix, but the suffix pattern is inconsistent: some are verbs (check, collect, compare), some are verb_noun (list_results), and some are nouns (timechart, system_info). The report_* subfamily is internally consistent, but overall the naming mixes conventions while remaining readable.
Tool Count5/5
With 9 tools, the set is well-scoped for a profiling server. Each tool covers a distinct part of the workflow (probe, collect, list, report, compare, system stats) without redundancy, and the count is comfortably within the ideal range.
Completeness4/5
The core profiling lifecycle is covered: environment check, collection, result listing, multiple report views, comparison, and time-series sampling. Minor gaps exist such as no explicit delete-result tool or a direct 'list available events' (though check includes available analyses), but agents can accomplish the main profiling tasks without dead ends.
Maintenance
ActivityStale
ResponsivenessNo issues