data-ai MCP Server
MCP server for Claude Code and Codex. One tool call replaces ~42 minutes of agent exploration
Discovered via github-seeds:mcp-hot and last synced 3mo ago.
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)
codebase-memory-mcp
45.7K
44
~15
guessing
Read (full file)
reading model + migrations
Chronological history of decisions for a symbol/file
Cross-subproject impact: what breaks if endpoint X changes (resolves to symbol level)
274
❌
139
Glob + Grep
Description
Knowledge graph overview
Find all client calls across subprojects that call a specific endpoint
Python
TypeScript
reading 15 files
Grep
What it does
Index session content for cross-session search
Add a subproject via MCP (bound to current project, or specify `project`)
> **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:
TypeScript
~38,000
Extract decisions from session logs (pattern-based, 0 LLM calls)
FTS5 search: "what did we discuss about auth?"
Re-scan all subprojects
Python
trace-mcp tool
reading 15 files
Manually record a decision with code linkage + service scoping
Compact orientation (~300 tokens): project + decisions + stats
What it shows
MemPalace
smart-coding-mcp
Roam-Code
Grep
Query by type/service/symbol/file/tag + FTS5 search
trace-mcp
engram
68
~18,200
Read (full file)
reading route files
Mark a decision as superseded (preserved for history)
All subprojects, their connections, and stats
Typical reduction