trace-mcp
About
Framework-aware code intelligence server that builds a cross-language dependency graph from source code — 53 framework integrations across 68 languages, 100+ tools for navigation, impact analysis, refactoring, and session memory with up to 97% token reduction.
Details
- Author
- nikolai-vysotskyi
- Categories
- Developer Tools
Jump to
Setup
Install trace-mcp in your MCP client (Claude Desktop, Cursor, Windsurf, and others).
Repository: https://github.com/nikolai-vysotskyi/trace-mcp
Follow the installation instructions in the repository README, then restart your MCP client.
AI agents recompute the same work. trace-mcp makes them reuse instead.
The recomputation → reuse layer for AI systems.
40–50% fewer tokenson average ·up to 2× effective capacity·up to 99% less redundant processing
Based on early benchmarks across agent workflows with repeated context and dependency traversal.
AI systems don't scale because they recompute instead of reuse. Every turn, the agent re-reads the same files, re-traverses the same dependencies, and re-inflates the context window with structure it already discovered. Token bills grow. Latency grows. Reasoning quality drops. The model isn't the bottleneck — the recomputation leak is.
trace-mcp builds a framework-aware graph of your codebaseonce, then serves it through MCP so the agent reasons from a precomputed structure instead of brute-reading the repo. Ask"what breaks if I change this model?"— instead of 80 Grep calls and 190 file reads, the agent callsget_change_impactonce and gets the blast radius across PHP, Vue, migrations, and DI. One tool call replaces ~42 minutes of agent exploration. 81 framework integrations across 80 languages, 170 tools.
The same engine indexes markdown vaults.[[wikilinks]]become first-class edges, frontmatter and#tagsbecome metadata, headings become nested sections.find_usagesreturns backlinks.apply_renamerewrites every link to a renamed note. One MCP for code and knowledge — no second tool to plug in.
Also ships adesktop appwith a GPU graph explorer over the same index.
AI is bottlenecked not by models, but byrecomputation. Agents treat the context window like a database — they re-read the same files, re-traverse the same dependencies, and re-inflate context every turn with structure they already computed five steps ago. Token bills, latency, and hallucinations all grow with project size instead of with task complexity.
trace-mcp closes the recomputation leak. The graph is built once, kept incrementally fresh, and served to every agent that asks — so the same work isn't paid for over and over.
- Lower cost— fewer tokens per successful answer, on average and at peak
- Lower latency— fewer sequential tool calls, fewer round-trips to the model
- Higher accuracy— less noise in context means fewer hallucinations and stronger first-response correctness
- Production stability— context that scales with project size, not against it
We started with code intelligence — the hardest, noisiest context most agents handle today — and the same engine now indexes markdown knowledge vaults (Obsidian, Logseq, plain MD) as a peer domain. Wikilinks, tags, frontmatter, and embeds become graph edges and symbol metadata;search,find_usages,get_change_impact, andapply_renamework identically over both.
-
Framework-aware edges— trace-mcp understands thatInertia::render('Users/Show')connects PHP to Vue, that@Injectable()creates a DI dependency, that$user->posts()means apoststable from migrations. 58 integrations across 15 frameworks, 7 ORMs, 13 UI libraries.
Code-linked decision memory— when you record "chose PostgreSQL for JSONB support", it's linked tosrc/db/connection.ts::Pool#class. When someone runsget_change_impacton that symbol, they see the decision. MemPalace stores decisions as text; trace-mcp ties them to the dependency graph.
Cross-session intelligence— past sessions are mined for decisions and indexed for search. When you start a new session,get_wake_upgives you orientation in ~300 tokens;plan_turnshows relevant past decisions for your task;get_session_resumecarries over structural context from previous sessions.
Code and knowledge in one graph— point trace-mcp at a markdown vault (Obsidian, Logseq, plain MD) and the same engine indexes it: each note becomes anote:<basename>symbol, headings become nested sections,[[wikilinks]]and![[embeds]]become graph edges, frontmatter and#tagsride on metadata. PageRank, Signal Fusion ranking, embeddings, and rename refactoring all apply unchanged. The agent does not learn a second tool — it learns one graph that happens to contain both your codebase and your second brain.
AI coding agents recompute the same work every turn — and they'reframework-blindwhile doing it.
They re-readUserController.php, then re-read it again next turn. They don't know thatInertia::render('Users/Show', $data)connects a Laravel controller toresources/js/Pages/Users/Show.vue. They don't know that$user->posts()means thepoststable defined three migrations ago. They can't trace a request from URL to rendered pixel — so they trace it again, and again, every session.
The result: 5–15× repeated reads of hot files in a single task, context windows used as scratch databases, and agents that get more expensive the bigger the project gets — instead of more capable.
trace-mcp builds across-language dependency graphfrom your source code and exposes it through theModel Context Protocol— the plugin format Claude Code, Cursor, Windsurf and other AI coding agents speak. Any MCP-compatible agent gets framework-level understanding out of the box.
trace-mcp ships with an optional Electron desktop app (packages/app) that gives you a visual surface over the same index the MCP server uses. It manages multiple projects, wires up MCP clients, and provides a GPU-accelerated graph explorer — all without opening a terminal.
Projects & clients.The menu window lists indexed projects with live status (Ready/ indexing / error) and re-index / remove controls. TheMCP Clientstab detects installed clients (Claude Code, Claw Code, Claude Desktop, Cursor, Windsurf, Continue, Junie, JetBrains AI, Codex, AMP, Warp, Factory Droid) and wires trace-mcp into them with one click, including enforcement level (Base / Standard / Max — CLAUDE.md only, + hooks, + tweakcc & agent-behavior rules; Max-tier features are Claude Code–specific). Warp and JetBrains AI require manual paste in the IDE because their config storage is GUI-only.
Per-project overview.Each project opens in its own tabbed window:Overview(files, symbols, edges, coverage, linked services, re-index),Ask(natural-language query over the index), andGraph. Overview also surfacesMost Symbolsfiles, last-indexed timestamp, and the dependency coverage meter.
GPU graph explorer.The Graph tab renders the full dependency graph on the GPU viacosmos.gl— tens of thousands of nodes/edges at interactive frame rates. Filter by Files / Symbols, overlay detected communities, highlight groups, toggle labels/FPS, and step through graph depth. Good for getting a feel for coupling, hotspots, and how a codebase is actually shaped before you dive into tools.
Install:grab the latest build from[Releases—
- macOS—trace-mcp-<version>-arm64-mac.zip(Apple Silicon) ortrace-mcp-<version>-mac.zip(Intel). Unzip and dragtrace-mcp.appinto/Applications.
- Windows— runtrace-mcp.Setup.<version>.exe.
The app talks to the sametrace-mcpdaemon (http://127.0.0.1:3741) that MCP clients use, so anything you index from the app is immediately available to Claude Code / Cursor / etc.
trace-mcp combinescode graph navigation,cross-session memory, andreal-time code understandingin a single tool. Most adjacent projects solve one of these — trace-mcp unifies all three and is the only one withframework-aware cross-language edges(81 integrations) andcode-linked decision memory.
…
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
