trace-mcp
Installed, started with no arguments, no environment and no input, and listed its tools. Run 2026-11-16.
Needs to start: nothing
Returns a result when called with no setup: 2 of 5 tools tried
Contacts while installing and starting: www.google-analytics.com
What it contacted
www.google-analytics.com: usually analytics or error reporting
Hosts it looked up or connected to while installing and starting with no input, watched from outside its sandbox. The npm registry is left out. Says nothing about what its tools contact when called.
Starting it
npx -y -p trace-mcp@3.44.1 trace-mcp
Installing a package runs its code. Use a sandbox for anything you have not read.
Calling its tools
5 tools that take no input and look read-only were called once with nothing. 2 returned a result.
get_index_health | Returned a result under 0.1 s · 2,852 characters |
get_project_map | Returned a result under 0.1 s · 476 characters |
get_symbol | No usable answer tool reported an error: {"error":"Symbol not found (session root has empty index)","projectRoot":"/","indexFiles":0,"reason":"filesystem_root_session","message" |
get_change_impact | No usable answer tool reported an error: {"error":{"code":"VALIDATION_ERROR","message":"No file_path, symbol_id, fqn, or symbol_ids provided — specify at least one"}} |
get_context_bundle | No usable answer tool reported an error: {"error":{"code":"VALIDATION_ERROR","message":"Provide symbol_id, symbol_ids, or fqn"}} |
During the calls it contacted nothing it had not already contacted.
Only tools whose names read like looking something up, with no required input, are tried, five at most. Tools that need input, and anything that sounds like it changes or sends something, are not called.
What its tools tell an agent
In the tool descriptions, nothing that talks about the user, other tools or private files, or uses hidden characters.
Found by simple pattern rules in each tool's description (up to 3,000 characters), quoted as written. Parameter descriptions are not scanned. A clean result is not a safety review.
Tools
get_index_health
Get index status, statistics, health, and pipeline progress (indexing, summarization, embedding). Includes the session projectRoot; when the index is empty, next_steps names the empty root and points at list_projects + call_project_tool for other registered projects. Read-only, no side effects. Use to verify the index is ready before running queries. Returns JSON: { status, stats, projectRoot, next_steps?, config, warnings, pipelineProgress, embedding }.register_edit file_path
Notify trace-mcp that a file was edited. Reindexes the single file and invalidates search caches. Call after Edit/Write to keep index fresh — much lighter than full reindex. Also flags duplicate symbols — if `_duplication_warnings` appears, you may be recreating existing logic; review them. Each one is reported once per file, not on every edit; `check_duplication` re-asks. Mutates the index; idempotent. Returns JSON: { status, file, totalFiles, indexed, _duplication_warnings? }.get_project_map summary_only
Get project overview: detected frameworks, languages, file counts, structure. Read-only, no side effects. Call with summary_only=true at session start to orient yourself before diving into code. Use instead of manual ls/find. Returns JSON: { frameworks, languages, fileCount, symbolCount, structure }.search query, kind, language, file_pattern, implements, extends, decorator, fuzzy, fuzzy_threshold, max_edit_distance, semantic, semantic_weight, fusion, limit, offset, mode, drill_from, retriever, detail_level, output_format
Search symbols by name, kind, or text. Use instead of Grep for functions, classes, methods, variables. For raw text/comment search use search_text; for references to a known symbol use find_usages. Read-only. Returns JSON: { items: [{ symbol_id, name, kind, fqn, signature, file, line, score }], total, search_mode } — mode-specific shape when mode!=single. Supports `output_format: "toon"`.suggest_queries
Onboarding helper: shows top imported files, most connected symbols (PageRank), language stats, and example tool calls. Call this first when exploring an unfamiliar project. For a structured project map use get_project_map instead. Read-only. Returns JSON: { topFiles, topSymbols, languageStats, exampleQueries }.24 more tools
get_symbol symbol_id, fqn, max_lines, verify_against_git
Look up a symbol by symbol_id or FQN and return its source code. Use instead of Read when you need one specific function/class/method — returns only the symbol, not the whole file. For multiple symbols at once, prefer get_context_bundle. Read-only. Returns JSON: { symbol_id, name, kind, fqn, signature, file, line_start, line_end, source }.get_outline path, detail_level, nested, min_loc_for_nesting, output_format
Get all symbols for a file (signatures only, no bodies) — cheaper than Read for understanding a file before editing. Follow up with get_symbol to read one symbol's source. `nested: true` expands large top-level symbols (default ≥100 LOC) into inner declarations, each carrying `parentId` + `depth` (max 3). Accepts project-relative or absolute file paths. For files in other registered projects, use call_project_tool. Read-only. Returns JSON: { path, language, symbols: [{ symbolId, name, kind, signature, lineStart, lineEnd, parentId?, depth? }] }. Supports `output_format: "toon"`.get_change_impact file_path, symbol_id, fqn, symbol_ids, decorator_filter, depth, max_dependents, compact, bundle
Full change impact report: risk score + mitigations, breaking change detection, enriched dependents (complexity, coverage, exports), module groups, affected tests, co-change hidden couplings. Pass symbol_ids to scope to changed symbols. Use before modifying code. For a quick risk score alone use assess_change_risk; for who-calls-what use get_call_graph. compact pages results; bundle recalls. Read-only. Returns JSON: { risk, dependents, affectedTests, breakingChanges, totalAffected }.get_context_bundle symbol_id, symbol_ids, fqn, include_callers, token_budget, output_format
Get a symbol's source code + its import dependencies + optional callers, packed within a token budget. Supports batch queries with shared-import deduplication. Use instead of chaining get_symbol calls. For a single symbol without imports, use get_symbol — lighter. Read-only. Returns JSON: { primary: [{ symbol_id, file, source }], imports: [{ file, source }], token_usage }.get_feature_context description, token_budget, detail_level, output_format
Search code by keyword/topic → returns ranked source snippets within a token budget. Use when you need to READ actual code for a concept or feature. For structured task context with tests and entry points use get_task_context instead; for symbol metadata without source use search. Read-only. Returns JSON (default) or Markdown: { items: [{ symbol_id, name, file, source, score }], token_usage } | { content: "...markdown..." }. Supports `output_format: "toon"`. Capped by `memory.recall.timeoutMs` (default 5000ms); on timeout returns `{ items: [], token_usage, degraded: true }`.get_task_context task, token_budget, focus, include_tests, detail_level, output_format
All-in-one context for starting a dev task: execution paths, tests, entry points, adapted by task type. Use as your FIRST call when beginning any new task — replaces manual chaining of search → get_symbol → Read. For narrower feature-code lookup use get_feature_context instead. Read-only. Returns JSON (default) or Markdown.
find_usages symbol_id, fqn, file_path, detail_level, include_ambiguous_text_matched, limit
Find all references to a symbol or file (imports, calls, renders, dispatches). Use instead of Grep for symbol usages — semantic, not text matches. For raw text use search_text; for a bidirectional call graph use get_call_graph. Weakly-grounded `text_matched` edges into a name-colliding target are dropped by default (phantom god-node filter); `include_ambiguous_text_matched: true` keeps them. Read-only. Returns JSON: { references: [{ edge_type, resolution_tier, file, symbol }], total, truncated?, ambiguous_filtered? } — page caps at 50, `total` counts all.get_call_graph symbol_id, fqn, depth
Build a bidirectional call graph centered on a symbol (who calls it + what it calls). Each branch keeps its direction: depth 2 = callers of callers, callees of callees. Use to understand control flow through a function. For flat list of all references use find_usages instead. Read-only. Returns JSON: { root: { symbol_id, name, calls: [...], called_by: [...] } }.search_text query, is_regex, file_pattern, language, max_results, context_lines, case_sensitive, timeout_ms, grouping
Full-text search across all indexed files. Supports regex, glob file patterns, language filter. Use for finding strings, comments, TODOs, config values, error messages — anything not captured as a symbol. Skips .env files: secret values are never searched or returned, use get_env_vars for env keys. For symbol search (functions, classes) use search instead. Read-only. Returns JSON: { files: [{ file, language, hits: [{ line, column, match, context }] }], total_matches } — hits grouped per file, so a long path is paid once. Pass `grouping: "flat"` for the ungrouped matches[] shape.get_diagnostics file_path, checker, max_per_file, max_files, timeout_ms, reduce_output
Execute type-checker (tsc, mypy, pyright) and map errors to enclosing AST symbols. Read-only.
mine_sessions project_root, force, min_confidence, review_threshold, reject_threshold, strategy, incremental_cursor
Mine Claude Code / Claw Code session logs for architectural decisions, tech choices, bug root causes, and preferences. Strategies: "regex" (default, free, ~20-40% recall), "llm" (higher recall, costs tokens), "hybrid" (regex + LLM safety net). Skips already-mined sessions unless force=true. Mutates the decision store; idempotent. Returns JSON: { mined, decisions_extracted, sessions_processed, strategy?, llm_sessions?, llm_decisions_extracted? }.remember_decision title, content, type, service_name, symbol_id, file_path, tags, session_id, git_branch
Live agent write into the decision knowledge graph. Confidence-scores the input and routes it through the memoir review queue: high-confidence rows enter the active graph immediately, mid-confidence rows queue for human approval, low-confidence rows are dropped without persistence. Per-session dedup + rate-limit. Use during a session to capture decisions in real time. For manual high-confidence writes use add_decision; for post-hoc extraction from session logs use mine_sessions. Returns JSON: { id, review_status, confidence, deduplicated? }.query_decisions type, service_name, symbol_id, file_path, tag, search, as_of, include_invalidated, include_pending, review_status, git_branch, order_by, limit, verify, verification, index_only, output_format
Query the decision knowledge graph. Filter by type, subproject, code symbol, file path, tag, or time — answers "why was this architecture chosen?" with the actual decision record. Defaults to approved decisions; use include_pending or review_status for other tiers. Read-only. Returns JSON: { decisions: [{ id, title, type, content, tags, review_status, cluster_ids? }], clusters_summary?, total_results }. Supports `output_format: "toon"`.invalidate_decision id, valid_until
Mark a decision as no longer valid. The decision remains in the knowledge graph for historical queries but is excluded from active queries. Use when a decision is superseded or reversed. Mutates the decision store; idempotent. Returns JSON: { invalidated: { id, title, valid_until } }.get_preset_info
Show active tool preset, available presets, which tools are registered in this session, and which are deferred (loadable via load_tools). Read-only. Returns JSON: { active_preset, registered_tools, tool_names, available_presets, deferred_tools }.load_tools preset, tools
Load tools this session's preset deferred, by preset name and/or explicit tool names. Call with no arguments to list what is deferred. Emits notifications/tools/list_changed and returns the loaded tools' schemas, so they are usable even if your client ignores that notification (call them through `batch`). Returns JSON: { loaded, already_loaded, unknown, blocked, tools, hint }.get_session_analytics period, session_id
Analyze AI agent session logs: token usage, prompt-cache hit rate (blended and split by provider/model), cost breakdown by tool/server, top files, models used. Parses Claude Code JSONL logs automatically. Read-only. For waste detection use get_optimization_report; for cost trends use get_usage_trends. Returns JSON: { sessionsCount, totals, cacheHitRate: { blended, byModel, byProvider }, byToolServer, topTools, topFiles, modelsUsed }.get_optimization_report period
Detect token waste patterns in AI agent sessions: repeated file reads, Bash grep instead of search, large file reads, unused trace-mcp tools. Provides savings estimates. Read-only. For usage/cost overview use get_session_analytics; for A/B savings comparison use get_real_savings. Returns JSON: { patterns: [{ type, description, savings_estimate }], total_waste }.get_coverage_report
Technology profile of the project: detected frameworks/ORMs/UI libs from manifests (package.json, composer.json, etc.), which are covered by trace-mcp plugins, and coverage gaps. Read-only. Returns JSON: { detected, covered, gaps }.get_real_savings period
A/B comparison: how many tokens could be saved by using trace-mcp instead of raw Read/Bash file reads. Per-file breakdown. Read-only. For pattern-based waste detection use get_optimization_report instead. Returns JSON: { files: [{ file, raw_tokens, compact_tokens, savings }], total_savings }.get_usage_trends days
Daily token usage time-series: sessions, tokens, estimated cost, tool calls, prompt-cache hit rate per day. For spotting cost spikes. Read-only. For detailed session breakdown use get_session_analytics instead. Returns JSON: { days, daily: [{ date, sessions, tokens, cost_usd, tool_calls, cache_hit_rate, cache_hit_rate_by_provider }], totals }.get_session_stats
Token savings stats for this session: per-tool call counts, estimated token savings, reduction percentage, dedup savings, and per-tool latency (p50/p95/max/error_rate). Read-only. Returns JSON: { session: { ..., latency_per_tool }, cumulative, dedup_saved_tokens, report }.plan_turn task, intent, max_targets, skip_risk
Opening-move router for new tasks. Combines BM25/PageRank search + session journal (negative evidence + focus signals) + framework-aware insertion-point suggestions + change-risk + turn-budget advisor into ONE call. Returns verdict (exists/partial/missing/ambiguous), confidence, ranked targets with provenance, scaffold hints when missing, and recommended next tool calls. Call this FIRST on a new task to break the empty-result hallucination chain. Read-only. For broader task context with source code use get_task_context instead. Returns JSON: { verdict, confidence, targets, scaffoldHints, nextSteps }.batch calls
Execute multiple trace-mcp tools in a single MCP request. Dispatches any registered tool by name, including tools this session's preset defers — so a deferred tool is callable here without a load_tools round-trip (tools.exclude stays a hard restriction). Use to reduce round-trips when you need several independent queries (e.g., get_outline for 3 files, or search + get_symbol together). Read-only (delegates to other tools). Returns JSON: { batch_results: [{ tool, result }], total }.Descriptions are the package's own words, cut at 3,000 characters. Treat them as data.
Files it wrote
/tmp/ .trace/ activity.db /tmp/ .trace/ telemetry-state.json /tmp/ .trace/ daemon.log /tmp/ .trace/ decisions.db-shm /tmp/ .trace/ .config.json /tmp/ .trace/ state.db /tmp/ .trace/ decisions.db /tmp/ .trace/ state.db-wal /tmp/ .trace/ state.db-shm /tmp/ .trace/ index/ -8a5edab28263-session-702a2423.db /tmp/ .trace/ index/ -8a5edab28263-session-702a2423.db-shm /tmp/ .trace/ index/ -8a5edab28263-session-702a2423.db-wal /tmp/ .trace/ activity.db-shm /tmp/ .trace/ activity.db-wal /tmp/ .trace/ sessions/ 8a5edab28263-snapshot.json /tmp/ .trace/ decisions.db-wal /tmp/ .trace/ daemon.pid
Paths inside its sandbox, where its home folder is /tmp and its own folder cannot be written to.
Install facts
| License | MIT |
|---|---|
| Needs | node >=22.0.0 |
| Source | github.com/nikolai-vysotskyi/trace-mcp |
| Install scripts | @parcel/watcher, onnxruntime-node, protobufjs, trace-mcp declare them. This runner does not run them. |
| Tarball | sha512-F53wWLO97sJQQLXCcEwiA30jlCUTEdNle9K+pR8R923n7roZn1EWX/3QbTVF7aeu1ErFETDg1LV07M7Hu4bFFw== |
Versions reported
| Version | Run | Result | Tools |
|---|---|---|---|
| 3.44.1 | 2026-11-16 | Starts with no setup | 29 |
| 3.44.0 | 2026-11-12 | Starts with no setup | 29 |
Check this report yourself
This site did not write the report. A public job on a GitHub-hosted machine did: the run, from this commit of the open-source runner. GitHub signed a token that names that job and the hash of the report, so any edit since would show.
Report as JSONExact text and tokenHow to verify it
Show it on your README
[](https://bragproof.smaverk.com/r/trace-mcp)
New version out? Ask for a fresh report.