list_indexed_repositoriesLABSCO SUMMARY
The graph is parsed, not inferred — no LLM calls to build it, so re-indexing is cheap enough to run continuously.
That choice is why the impact and evolution questions are answerable at all: every symbol carries its version history, so "what changed and what does it touch" is a graph query rather than a diff you read. Cross-service API topology only appears once you have indexed both ends, which is worth doing before you ask about it.
What it is
A local code knowledge graph for AI coding agents: symbols as nodes, calls and imports as edges, with version history attached to every symbol and HTTP topology across services.
What you get
- find_symbol and find_code — exact or fuzzy symbol lookup, and hybrid retrieval that handles natural-language queries and string literals baked into function bodies
- get_symbol_context — callers, callees, community, processes and recent changes for one symbol in a single call
- get_impact and find_dependency_path — blast radius before a refactor, and how two symbols relate in the call graph
- list_communities, find_central_symbols, find_bridge_symbols and get_codebase_briefing — architecture at a glance for a repo you just met
- get_evolution, get_timeline, get_changes_since, detect_changes and get_cochange_context — what changed, when, and what historically changes alongside it
- find_api_endpoints, find_api_calls, get_api_topology and get_service_diagram — HTTP endpoints and cross-service call graphs across repos you have indexed
- find_dead_code, calculate_cyclomatic_complexity and find_most_complex_functions
- index_directory, watch_directory and check_job_status — indexing runs async, and watched paths make in-progress edits queryable
- get_source_window — a span of a file with surrounding context, cheaper than reading the whole file
Requirements
npm install -g memtrace, which sets up the binary, skills and MCP config for Claude Code, Claude Desktop, Cursor, Codex, Windsurf, VS Code, Hermes, OpenCode and Kiro. Memtrace is in private beta — you need access before the CLI is useful, and it signs you in through the browser the first time it starts; MEMTRACE_LICENSE_KEY stands in for that sign-in only on headless machines and CI. Indexing is local and needs no API key; the graph lives in a per-repo .memdb directory.
Setup effort
One command plus credentials — npm install -g memtrace, then supply credentials
USE CASES
01
Deciding whether a refactor is safe
Locate the symbol, pull its blast radius at the depth you want, then check whether it has been churning lately.
02
Getting oriented in an unfamiliar repo
Read the briefing, then the Louvain-detected modules and the most-depended-on symbols.
03
Finding the handler behind a route
Search endpoints by path fragment, then find where that endpoint is called from — including from another indexed repo.
04
Querying code you have not committed yet
Watch the directory so edits become working-tree episodes the agent can search within about a second of saving.
44 tools
Listed in project docs. Your client may show a different list.
index_directorydelete_repositorycleanup_stale_recordscheck_job_statuslist_jobsfind_symbolfind_codeget_symbol_contextget_source_windowget_impactfind_dependency_pathanalyze_relationshipslist_communitiesfind_central_symbolsfind_bridge_symbolsget_codebase_briefingget_repository_statsget_evolutionget_timelineget_changes_sincedetect_changesget_cochange_contextget_episode_replayreplay_historycleanup_episodesrecall_decisionverify_intentget_arcwhy_is_this_heregoverning_contractslist_processesget_process_flowfind_api_endpointsfind_api_callsget_api_topologyget_service_diagramfind_dead_codecalculate_cyclomatic_complexityfind_most_complex_functionswatch_directoryunwatch_directorylist_watched_pathsrecord_external_episodeBEFORE YOU INSTALL
What to know first
Tools you get
44 tools named in the project's documentation.
Requires
memtrace on PATH
INSTALLATION
Connect your client
Server setup
TERMINAL
npm install -g memtraceMCP Clients
Claude Code
CLAUDE CODE · TERMINAL
claude mcp add memtrace -- memtrace mcpThe first time memtrace starts it signs you in through the browser, so the configuration needs no key. On a headless machine or in CI, export MEMTRACE_LICENSE_KEY instead; license keys come from memtrace.io once you are past the waitlist.
Claude Desktop, Cline
JSON
{
"mcpServers": {
"memtrace": {
"command": "memtrace",
"args": [
"mcp"
],
"env": {}
}
}
}The first time memtrace starts it signs you in through the browser, so the configuration needs no key. On a headless machine or in CI, export MEMTRACE_LICENSE_KEY instead; license keys come from memtrace.io once you are past the waitlist.
VS Code
VS CODE · JSON
{
"servers": {
"memtrace": {
"command": "memtrace",
"args": [
"mcp"
],
"env": {}
}
}
}The first time memtrace starts it signs you in through the browser, so the configuration needs no key. On a headless machine or in CI, export MEMTRACE_LICENSE_KEY instead; license keys come from memtrace.io once you are past the waitlist.
Cursor
CURSOR · TERMINAL
npx memtrace-skills install --only cursor --localThe first time memtrace starts it signs you in through the browser, so the configuration needs no key. On a headless machine or in CI, export MEMTRACE_LICENSE_KEY instead; license keys come from memtrace.io once you are past the waitlist.
