Memtrace MCP Server

Memtrace gives AI coding agents structural memory — your codebase as a live knowledge graph so agents stop re-deriving code structure from scratch

Local serverstdioPython

What is the Memtrace MCP server?

Memtrace gives AI coding agents structural memory — your codebase as a live knowledge graph so agents stop re-deriving code structure from scratch and start reasoning from fact. Exposed over MCP by the memtrace mcp server, that capability becomes something an assistant can invoke while it works, not something you go and do afterwards.

What it actually does

Adding it to your client

The server ships on npm as memtrace-skills, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.

Its toolset

Everything the assistant can do here goes through one of these:

  • find_code — hybrid BM25 + semantic + RRF
  • find_symbol — exact / fuzzy with Levenshtein
  • analyze_relationships — callers, callees, hierarchy, imports
  • get_symbol_context — 360° view in one call
  • get_impact — blast radius with risk rating
  • detect_changes — diff-to-symbols scope mapping
  • find_dead_code — zero-caller detection
  • find_most_complex_functions — complexity hotspots
  • calculate_cyclomatic_complexity — get_repository_stats
  • get_evolution — 6 scoring modes
  • get_timeline — full version history
  • find_bridge_symbols — betweenness centrality

Configuration

You will need one environment variable: MEMTRACE_TELEMETRY. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

Memtrace runs locally — first index is CPU/RAM intensive, subsequent queries and incremental indexing are much lighter. | | Minimum | Recommended | |---|---|---| | CPU | 4 cores | 8+ cores for large monorepos | | Memory | 8 GB RAM | 16–32 GB RAM | | Disk | 5 GB free | 10–20 GB free | | GPU | Not required | Not required | | Node.js | ≥ 18 | Current LTS | | Git | Required for temporal analysis |

Caveats

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Memtrace.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the memtrace mcp server does with a few real requests.

When to reach for it

This sits in the knowledge and memory group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Memtrace's toolset — find_code, find_symbol, analyze_relationships and 11 more — is a fair guide to whether it matches your workflow.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Available tools

ToolWhat it does
find_codehybrid BM25 + semantic + RRF
find_symbolexact / fuzzy with Levenshtein
analyze_relationshipscallers, callees, hierarchy, imports
get_symbol_context360° view in one call
get_impactblast radius with risk rating
detect_changesdiff-to-symbols scope mapping
find_dead_codezero-caller detection
find_most_complex_functionscomplexity hotspots
calculate_cyclomatic_complexityget_repository_stats
get_evolution6 scoring modes
get_timelinefull version history
find_bridge_symbolsbetweenness centrality
find_central_symbolsPageRank / degree
list_communitiesLouvain modules

How to install the Memtrace MCP server

{
  "mcpServers": {
    "github-com-syncable-dev-memtrace-public-tree-main": {
      "command": "npx",
      "args": ["-y", "memtrace-skills"],
      "env": {
        "MEMTRACE_TELEMETRY": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

Memtrace runs locally — first index is CPU/RAM intensive, subsequent queries and incremental indexing are much lighter. | | Minimum | Recommended | |---|---|---| | CPU | 4 cores | 8+ cores for large monorepos | | Memory | 8 GB RAM | 16–32 GB RAM | | Disk | 5 GB free | 10–20 GB free | | GPU | Not required | Not required | | Node.js | ≥ 18 | Current LTS | | Git | Required for temporal analysis |

VariableDescriptionRequired
MEMTRACE_TELEMETRYConfiguration value read at startup.Optional

Example prompts to try

  • Use Memtrace to find code.
  • Use Memtrace to find symbol.
  • Use Memtrace to analyze relationships.

Frequently asked questions

It connects Memtrace to MCP-compatible AI assistants such as Claude and Cursor, exposing 14 tools (find_code, find_symbol, analyze_relationships, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Memtrace directly.