OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
MCP & Tooling

Trace MCP

Trace MCP is a TypeScript MCP server and CLI that indexes software repositories and supplies framework-aware code context to compatible AI agents. Its tools support repository exploration and change-impact analysis.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Trace MCP — OpenViST project profile in MCP & Tooling.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Trace MCP when an MCP-compatible coding agent needs structured context from a repository, particularly for code navigation or tracing the possible effects of a change.

Who it is for

  • Developers who use MCP-compatible coding agents on software repositories.
  • Teams seeking indexed code context for repository questions and pull-request review.

Documented uses

  • Register a repository for indexing and connect the index to an MCP client.
  • Retrieve framework-aware context for code exploration instead of repeatedly rereading files.
  • Use symbol, call-graph, or change-impact tools to investigate code relationships.
Before you choose

Requirements & limits

The project is an MIT-licensed public GitHub repository. The README documents npm installation and downloadable macOS and Windows releases.

  • It is an MCP server and developer CLI, not a standalone coding agent.
  • Project indexing is registered per repository with trace add.
  • The README states 88 framework integrations and 81 languages; actual usefulness depends on the codebase and agent workflow.
  • Usage telemetry is documented with environment-variable and configuration opt-outs.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Benchmark a repository before client setup

Run the documented structured benchmark on the current project and view its estimated token costs.

Before you start

  • A terminal in the repository to assess
  • npx

Steps

  1. From the project directory, run the command below.

    Documented command
    npx trace-mcp benchmark .

  2. Review the output for the 11 structured task benchmarks and estimated token costs with and without Trace MCP.

Expected outcome

A synthetic estimate based on the project index, showing task-level token costs.

Guide limitations

  • The estimate is not a record of real agent tool calls.
  • The README recommends trace-mcp analytics savings for measured savings from your own sessions.
Documentation 1 ↗
Source-based practical guide

Install the CLI and register a project

Install Trace MCP, configure a supported MCP client, and register the current repository for indexing.

Before you start

  • npm
  • A terminal
  • An MCP client supported by Trace MCP

Steps

  1. Install the CLI with the command below.

    Documented command
    npm install -g trace-mcp

  2. Run trace init for the documented one-time client setup.

  3. In each repository to index, run trace add.

Expected outcome

The client is configured and the current project is registered for indexing.

Guide limitations

  • Run trace add separately for each project you want Trace MCP to understand.
  • Claude Code and Codex CLI have separate documented plugin installation paths.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
13 October 2026
Original website title
nikolai-vysotskyi/trace-mcp · Official homepage title · retained in its source language
How we review sourcesSuggest a correction