trace-mcp

data-ai MCP Server

MCP server for Claude Code and Codex. One tool call replaces ~42 minutes of agent exploration

VerifiedInstall ReadyReviewed
data-aidata-ai
7 views89 stars13 forksv1.33.0MIT

Why This Matters

Discovered via github-seeds:mcp-hot and last synced 3mo ago.

VerifiedInstall ReadyReviewed
Source
github-seeds:mcp-hot
Stars
89
Last synced
3mo ago
Install
Instructions detected

Install

1. Install the package

npx trace-mcp

2. Add to claude_desktop_config.json

{
  "mcpServers": {
    "trace-mcp": {
      "command": "npx",
      "args": [
        "trace-mcp"
      ]
    }
  }
}

Config file location: ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) / %APPDATA%\Claude\claude_desktop_config.json (Windows)

49
Tools
0
Resources
0
Prompts
Standard I/O
Transport

Available Tools (49)

code-review-graph

codebase-memory-mcp

43K

45.7K

204

44

66

~15

get_change_impact

guessing

get_symbol

Read (full file)

get_model_context

reading model + migrations

get_decision_timeline

Chronological history of decisions for a symbol/file

get_subproject_impact

Cross-subproject impact: what breaks if endpoint X changes (resolves to symbol level)

23K

274

partial

❌

90

139

get_tests_for

Glob + Grep

Document

Description

get_decision_stats

Knowledge graph overview

get_subproject_clients

Find all client calls across subprojects that call a specific endpoint

TypeScript

Python

JavaScript

TypeScript

get_task_context

reading 15 files

find_usages

Grep

Tool

What it does

index_sessions

Index session content for cross-session search

subproject_add_repo

Add a subproject via MCP (bound to current project, or specify `project`)

Python

> **Why framework awareness matters:** A graph that knows `UserController` exists but doesn't know it renders `Users/Show.vue` via Inertia is missing the edges that matter most. Framework integrations turn a syntax graph into a **semantic** graph — the agent sees the same connections a developer sees. --- ## Up to 99% token reduction — real-world benchmark AI agents burn tokens reading files they don't need. trace-mcp returns **precision context** — only the symbols, edges, and signatures relevant to the query. **Benchmark: trace-mcp's own codebase** (694 files, 3,831 symbols): ``` Task Without trace-mcp With trace-mcp Reduction ───────────────────────────────────────────────────────────────────── Symbol lookup 42,518 tokens 7,353 tokens 82.7% File exploration 27,486 tokens 548 tokens 98.0% Search 22,860 tokens 8,000 tokens 65.0% Find usages 11,430 tokens 1,720 tokens 85.0% Context bundle 12,847 tokens 4,164 tokens 67.6% Batch overhead 16,831 tokens 9,031 tokens 46.3% Impact analysis 49,141 tokens 2,461 tokens 95.0% Call graph 178,345 tokens 10,704 tokens 94.0% Type hierarchy 94,762 tokens 1,030 tokens 98.9% Tests for 22,590 tokens 1,150 tokens 94.9% Composite task 93,634 tokens 3,836 tokens 95.9% ───────────────────────────────────────────────────────────────────── Total 572,444 tokens 49,997 tokens 91.3% ``` **91% fewer tokens** to accomplish the same code understanding tasks. That's ~522K tokens saved per exploration session — more headroom for actual coding, fewer context window evictions, lower API costs. **Savings scale with project size.** On a 650-file project, trace-mcp saves ~522K tokens. On a 5,000-file enterprise codebase, savings grow **non-linearly** — without trace-mcp, the agent reads more wrong files before finding the right one. With trace-mcp, graph traversal stays O(relevant edges), not O(total files). **Composite tasks deliver the biggest wins.** A single `get_task_context` call replaces a chain of ~10 sequential operations (search → get_symbol × 5 → Read × 3 → Grep × 2). That's **one round-trip instead of ten**, with 90%+ token reduction. **Per-task breakdown** — what it actually costs to answer common questions:

C

TypeScript

get_dead_code

~38,000

mine_sessions

Extract decisions from session logs (pattern-based, 0 LLM calls)

search_sessions

FTS5 search: "what did we discuss about auth?"

subproject_sync

Re-scan all subprojects

Go

Python

Task

trace-mcp tool

get_feature_context

reading 15 files

add_decision

Manually record a decision with code linkage + service scoping

get_wake_up

Compact orientation (~300 tokens): project + decisions + stats

Section

What it shows

trace-mcp

MemPalace

DeepContext

smart-coding-mcp

Narsil-MCP

Roam-Code

search

Grep

query_decisions

Query by type/service/symbol/file/tag + FTS5 search

Capability

trace-mcp

OpenMemory

engram

Languages

68

get_call_graph

~18,200

get_outline

Read (full file)

get_request_flow

reading route files

invalidate_decision

Mark a decision as superseded (preserved for history)

get_subproject_graph

All subprojects, their connections, and stats

Workload

Typical reduction