Skip to main content
Glama
nikolai-vysotskyi

trace-mcp

by nikolai-vysotskyi
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Related Servers

Alternatives to trace-mcp

No user-submitted related servers found.

    Related Servers

    • LAIN-mcp

      spuentesp
      A
      license
      Not graded
      quality
      A
      maintenance
      A persistent code-intelligence MCP server that builds a queryable knowledge graph of your codebase, enabling AI assistants to perform cross-file structural reasoning, dependency analysis, and blast radius detection.
      9
      MIT

    • LensPR

      kyrylopr
      A
      license
      Not graded
      quality
      C
      maintenance
      MCP server that builds a dependency graph of your codebase, giving AI agents structural understanding to analyze impact, find context, and make safe modifications across languages and infrastructure.
      MIT

    • Orihime

      srinivasan-sundaresan95
      A
      license
      A
      quality
      C
      maintenance
      Cross-repository code knowledge graph MCP server for Java, Kotlin, JavaScript, and TypeScript. Indexes source code into embedded KuzuDB via tree-sitter and exposes 30+ tools for call-flow tracing, multi-hop taint analysis (OWASP/CWE/PCI/STIG), entry-point reachability filtering, performance hotspot detection, and license compliance — without reading source files. 95% fewer tokens vs source-read
      33
      1
      MIT

    • code-atlas

      lusiem
      A
      license
      Not graded
      quality
      B
      maintenance
      Multi-language code intelligence MCP server providing structured code analysis including symbol search, references, hierarchies, and change impact. Supports 25 languages with persistent indexing and LSP integration.
      56 npm
      MIT

    • spider-map

      rofid-c
      A
      license
      Not graded
      quality
      B
      maintenance
      MCP server that analyzes codebases to provide dependency graphs, impact analysis, and file insights across 15+ programming languages, enabling AI assistants to understand project structure and navigate code efficiently.
      MIT
    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    A4/5.0

    Scored across 29 tools

    Disambiguation3/5

    Several clusters overlap heavily: get_task_context vs get_feature_context vs get_context_bundle vs plan_turn all deliver 'context', and get_session_analytics vs get_session_stats vs get_usage_trends vs get_real_savings vs get_optimization_report all report token/cost analytics. The descriptions mitigate this with explicit 'use X instead of Y' cross-references, but the boundaries remain genuinely fuzzy and require the agent to read carefully.

    Naming Consistency4/5

    Predominantly a consistent snake_case verb_noun pattern (get_symbol, search_text, query_decisions, find_usages, plan_turn), with a strong 'get_' convention for readers. A few single-word outliers (search, batch) break the pattern slightly, but overall it is predictable and readable.

    Tool Count3/5

    29 tools is on the heavy side for the apparent scope, with visible redundancy across the context and analytics clusters. The preset/load_tools deferral and batch mechanism soften this by allowing tools to be hidden, but the registered surface is still large enough to strain selection.

    Completeness4/5

    The surface is broad and largely self-contained: search (symbol + text), retrieval (outline, symbol, bundle, task/feature context), graph analysis (call graph, usages, change impact), diagnostics, decision-graph read/write/mine, and index/session management. Minor gaps remain (e.g. no explicit symbol rename/refactor or test-runner operation), but core code-intelligence workflows are covered.

    Maintenance

    ActivityActive
    ResponsivenessResponsive

    Resources