trace-mcp
An MCP server that builds a code graph once and serves the answer to the agent instead of re-reading files
Medium risk
We rate an entry medium when the tool runs code, makes network calls or reads project files. Check what exactly it does before installing.
Why this level
- Reads and indexes the whole project code
- Keeps a local background process running
Install
In your terminal, with SkillFoxx CLI
npx skillfoxx add mcp/trace-mcpDetects the agents on your machine, checks the risk and pins the version.
Other ways to install
Run in a terminal
claude mcp add --transport stdio trace-mcp -- npx -y trace-mcp@3.32.0Or add to the file .mcp.json, in the project
{
"mcpServers": {
"trace-mcp": {
"command": "npx",
"args": [
"-y",
"trace-mcp@3.32.0"
]
}
}
}If the file already exists, add the server inside the mcpServers key.
The button opens the agent and offers to add the server. If nothing happens, copy the config below.
Add to the file ~/.cursor/mcp.json, for all projects
{
"mcpServers": {
"trace-mcp": {
"command": "npx",
"args": [
"-y",
"trace-mcp@3.32.0"
]
}
}
}If the file already exists, add the server inside the mcpServers key. For a single project, put the same block into .cursor/mcp.json.
The button opens the agent and offers to add the server. If nothing happens, copy the config below.
Run in a terminal
code --add-mcp '{"name":"trace-mcp","type":"stdio","command":"npx","args":["-y","trace-mcp@3.32.0"]}'Or add to the file .vscode/mcp.json, in the project
{
"servers": {
"trace-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"trace-mcp@3.32.0"
]
}
}
}If the file already exists, add the server inside the servers key.
Run in a terminal
codex mcp add trace-mcp -- npx -y trace-mcp@3.32.0Or add to the file ~/.codex/config.toml, for all projects
[mcp_servers.trace-mcp]
command = "npx"
args = ["-y", "trace-mcp@3.32.0"]If the file already exists, append the block to the end.
Add to the file ~/.gemini/settings.json, for all projects
{
"mcpServers": {
"trace-mcp": {
"command": "npx",
"args": [
"-y",
"trace-mcp@3.32.0"
]
}
}
}If the file already exists, add the server inside the mcpServers key.
Add to the file ~/.config/devin/mcp_config.json, for all projects
{
"mcpServers": {
"trace-mcp": {
"command": "npx",
"args": [
"-y",
"trace-mcp@3.32.0"
]
}
}
}If the file already exists, add the server inside the mcpServers key. Legacy Cascade keeps the MCP config in ~/.codeium/windsurf/mcp_config.json.
Formerly Windsurf.
Add to the file cline_mcp_settings.json, for all projects
{
"mcpServers": {
"trace-mcp": {
"command": "npx",
"args": [
"-y",
"trace-mcp@3.32.0"
]
}
}
}If the file already exists, add the server inside the mcpServers key. Open the settings file in Cline: MCP Servers tab, Configure MCP Servers.
Add to the file .roo/mcp.json, in the project
{
"mcpServers": {
"trace-mcp": {
"command": "npx",
"args": [
"-y",
"trace-mcp@3.32.0"
]
}
}
}If the file already exists, add the server inside the mcpServers key.
A fork of Roo Code, same .roo folders.
Add to the file opencode.json, in the project
{
"mcp": {
"trace-mcp": {
"type": "local",
"command": [
"npx",
"-y",
"trace-mcp@3.32.0"
]
}
}
}If the file already exists, add the server inside the mcp key.
Add to the file ~/.config/zed/settings.json, for all projects
{
"context_servers": {
"trace-mcp": {
"command": "npx",
"args": [
"-y",
"trace-mcp@3.32.0"
]
}
}
}If the file already exists, add the server inside the context_servers key.
Add to the file .codeassistant/mcp.json, in the project
{
"mcpServers": {
"trace-mcp": {
"command": "npx",
"args": [
"-y",
"trace-mcp@3.32.0"
]
}
}
}If the file already exists, add the server inside the mcpServers key.
Install trace-mcp: npm install -g trace-mcp, then trace init to wire it into the agent and trace add in the repo root to index it. Then use its tools over MCP.
Other ways from the author
npm install -g trace-mcp
trace init
trace addGlobal install, trace init wires the server into the agent, trace add indexes the current repo.
This is third-party code. Review the repository files before installing.
What it does
trace-mcp indexes the repository into a framework-aware graph and keeps it fresh as the code changes. Instead of dozens of grep calls and file reads, the agent asks over MCP: what breaks if this changes, how a request flows, which symbols tests never reach. The server understands edges between layers, such as a controller wired to a view or a dependency created through injection. It runs locally, the code stays on your machine, and it installs as a standalone server or a plugin for Claude Code and Codex.
Who it is for. For developers who want to cut token spend and the agent's step count on large codebases.
Good fit when
- The agent re-reads the same files over and over in a large codebase
- You need the blast radius before changing a symbol or model
- You need to trace a request flow or find untested code
Not a fit when
- The project is small and the agent copes by reading directly
- You cannot run a local background indexing process
Example request
What breaks if I change this model, show the affected code through traceLimitations
It needs an installed server and local indexing, which costs time and memory on large repos. Some features belong to a paid tier and the desktop app, while the core MCP server and CLI are open under MIT. Suggestion accuracy depends on how well a given framework is supported.
How to disable. Remove the server from your agent's MCP config or uninstall the package: npm uninstall -g trace-mcp.
MCP
- Transport
- stdio
- Authentication
- not required
Security check
- Reads and indexes the whole project code
- Keeps a local background process running
README in short
The README argues that agents pay repeatedly for work already done: every turn they re-read files and re-traverse dependencies. trace-mcp builds a code graph once and serves it over MCP, so instead of many grep calls the agent gets an answer in a single request. It claims broad framework and language coverage, decision memory tied to symbols, and search across past sessions. Install is npm global, then trace init and trace add. A desktop app acts as a visual explorer over the same index.
FAQ
Does my code leave for a third-party server?
No, the index is built and kept locally, and the server answers the agent from your machine.
Which agents does it work with?
Claude Code, Cursor, Codex, Windsurf and other MCP clients, with plugins for Claude Code and Codex.
Related
A skills library that gives coding agents a development process: brainstorming, planning, TDD, subagents and code review
Skills for real engineers by Matt Pocock
Skills For Real Engineers
Small composable skills for engineering with agents: plan grilling, TDD, bug diagnosis, code review and architecture
GitHub toolkit for spec-driven development: the specify CLI adds agent commands and skills to a project, from principles to implementation
Reference MCP servers
Model Context Protocol servers
Official reference MCP servers: Filesystem, Fetch, Git, Memory, Sequential Thinking, Time and Everything