From trace-mcp
Routes code intelligence queries to a framework-aware MCP server. Use instead of Read/Grep/Glob for source code exploration, impact analysis, and debugging.
How this skill is triggered — by the user, by Claude, or both
Slash command
/trace-mcp:trace-mcpThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
trace-mcp is a framework-aware code intelligence MCP server. It exposes 120+ tools that return semantic, structured results over a cross-language dependency graph. When trace-mcp is available, it is almost always cheaper and more accurate than native file tools.
trace-mcp is a framework-aware code intelligence MCP server. It exposes 120+ tools that return semantic, structured results over a cross-language dependency graph. When trace-mcp is available, it is almost always cheaper and more accurate than native file tools.
Activate this skill whenever you need to:
Do not use Read, Grep, Glob, or shell ls/find/cat/head/tail for exploring source code (.ts, .js, .py, .php, .go, .rb, .java, etc.). Use trace-mcp tools instead. Native tools stay allowed only for non-code files (.md, .json, .yaml, configs) or immediately before an Edit on a known file.
get_project_map with summary_only=true — orient yourself to the project structureget_task_context with task: "<natural-language description>" — gather all relevant code in a single call instead of chaining search → get_symbol → Read| Task | trace-mcp tool | Instead of |
|---|---|---|
| Find a symbol by name | search | Grep |
| Understand a file before editing | get_outline | Read (full file) |
| Read one symbol's source | get_symbol | Read (full file) |
| Multiple symbols + shared imports | get_context_bundle | chained get_symbol |
| What breaks if I change X | get_change_impact | guessing |
| Who calls this / what does it call | get_call_graph | Grep |
| All usages of a symbol | find_usages | Grep |
| Implementations of an interface | get_type_hierarchy | Grep / ls |
| Classes implementing X | search with implements filter | Grep |
| Tests for a symbol or file | get_tests_for | Glob + Grep |
| Project overview | get_project_map (summary_only) | Bash ls/find |
| Context for a task | get_task_context / get_feature_context | reading many files |
| HTTP request flow | get_request_flow | reading route + controller files |
| DB model relationships | get_model_context | reading model + migrations |
| Component tree | get_component_tree | reading component files |
| Circular dependencies | get_circular_imports | manual tracing |
| Dead code / dead exports | get_dead_code / get_dead_exports | Grep for unused |
| Project health / coverage gaps | self_audit | manual inspection |
| Complexity / hotspots | get_complexity_report / get_risk_hotspots | guessing |
batch when you need 2+ independent tool calls:
batch({ calls: [
{ tool: "get_outline", args: { path: "src/foo.ts" } },
{ tool: "get_outline", args: { path: "src/bar.ts" } },
{ tool: "search", args: { query: "handleRequest", kind: "function" } }
]})
get_outline once, then get_symbol for specific pieces.get_context_bundle over chained get_symbol calls — it deduplicates shared imports.Read a file to edit it:
get_outline first to find the line range of the target symbol.offset + limit. Never read a 500-line file to edit 5 lines.register_edit with the edited file_path to reindex just that file and invalidate caches. This is much lighter than a full reindex and keeps subsequent queries accurate._duplication_warnings, review the referenced symbols — you may be duplicating existing logic.Edit tool already confirmed success.check_duplication with { name, kind } to verify no similar symbol exists. Prevents reinventing existing logic.audit_config — stale references in CLAUDE.md / settingsself_audit — dead exports, untested code, hotspotsget_tech_debt — per-module tech-debt gradesget_optimization_report — detects repeated reads, Bash grep usage, missed trace-mcp opportunitiestrace-mcp-refactoring — safe refactoring workflow (risk assessment → rename → impact check)trace-mcp-codemod — bulk mechanical changes via apply_codemodtrace-mcp-pre-commit — security, quality-gate, and antipattern checks before commitnpx claudepluginhub nikolai-vysotskyi/trace-mcp --plugin trace-mcpQueries codebase knowledge graphs to search functions, trace callers/callees, list file entities, analyze impact, and run SurrealQL. Use for code structure, dependencies, and relationships.
Provides token-efficient codebase analysis via MCP: call graphs, semantic search, impact analysis, dataflow, program slicing, and dead code detection. Use before refactoring or reading large files.
Routes code research queries to ChunkHound for architecture, data flows, design patterns, and semantic analysis; native grep/glob for simple string/file searches. For onboarding and understanding codebases.