Agent skill

Trace MCP

by nikolai-vysotskyi in nikolai-vysotskyi/trace-mcp

Use trace-mcp tools for code navigation, impact analysis, and framework-aware queries instead of Read/Grep/Glob/Bash.

Install Trace MCP

skills CLI

$ npx skills add nikolai-vysotskyi/trace-mcp --skill trace-mcp -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install nikolai-vysotskyi/trace-mcp trace-mcp --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/nikolai-vysotskyi/trace-mcp.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/trace-mcp .claude/skills/trace-mcp && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "trace-mcp" agent skill from https://github.com/nikolai-vysotskyi/trace-mcp/tree/master/skills/trace-mcp into .claude/skills/trace-mcp/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "trace-mcp", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/nikolai-vysotskyi/trace-mcp/tree/master/skills/trace-mcp

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add nikolai-vysotskyi/trace-mcp --skill trace-mcp -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install nikolai-vysotskyi/trace-mcp trace-mcp --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/nikolai-vysotskyi/trace-mcp.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/trace-mcp .agents/skills/trace-mcp && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "trace-mcp" agent skill from https://github.com/nikolai-vysotskyi/trace-mcp/tree/master/skills/trace-mcp into .agents/skills/trace-mcp/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "trace-mcp", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add nikolai-vysotskyi/trace-mcp --skill trace-mcp -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install nikolai-vysotskyi/trace-mcp trace-mcp --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/nikolai-vysotskyi/trace-mcp.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/trace-mcp .cursor/skills/trace-mcp && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "trace-mcp" agent skill from https://github.com/nikolai-vysotskyi/trace-mcp/tree/master/skills/trace-mcp into .cursor/skills/trace-mcp/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "trace-mcp", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/nikolai-vysotskyi/trace-mcp.git --path skills/trace-mcp

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add nikolai-vysotskyi/trace-mcp --skill trace-mcp -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install nikolai-vysotskyi/trace-mcp trace-mcp --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/nikolai-vysotskyi/trace-mcp.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/trace-mcp .gemini/skills/trace-mcp && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "trace-mcp" agent skill from https://github.com/nikolai-vysotskyi/trace-mcp/tree/master/skills/trace-mcp into .gemini/skills/trace-mcp/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "trace-mcp", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install nikolai-vysotskyi/trace-mcp trace-mcp

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add nikolai-vysotskyi/trace-mcp --skill trace-mcp -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/nikolai-vysotskyi/trace-mcp.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/trace-mcp .github/skills/trace-mcp && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "trace-mcp" agent skill from https://github.com/nikolai-vysotskyi/trace-mcp/tree/master/skills/trace-mcp into .github/skills/trace-mcp/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "trace-mcp", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add nikolai-vysotskyi/trace-mcp --skill trace-mcp -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install nikolai-vysotskyi/trace-mcp trace-mcp --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/nikolai-vysotskyi/trace-mcp.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/trace-mcp .opencode/skills/trace-mcp && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "trace-mcp" agent skill from https://github.com/nikolai-vysotskyi/trace-mcp/tree/master/skills/trace-mcp into .opencode/skills/trace-mcp/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "trace-mcp", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: trace-mcp
GitHub stars: 189
Token cost: ~1.6k tokens
SKILL.md length: 713 words
Files: 1
Skills in repo: 5
Repo updated: Oct 11, 2026
First seen: Oct 10, 2026
Licence: MIT

At a glance

Use trace-mcp tools for code navigation, impact analysis, and framework-aware queries instead of Read/Grep/Glob/Bash.

Works in 2 steps: get_project_map with summary_only=true —… → get_task_context with task: "" — gather…
Tasks that involve MCP servers
SKILL.md covers When to Use, Start-of-Session Checklist, Decision Matrix and Environment Variables (Safe…, plus 5 more sections
Calls python

What it does

Trace MCP is an agent skill from nikolai-vysotskyi/trace-mcp. Use trace-mcp tools for code navigation, impact analysis, and framework-aware queries instead of Read/Grep/Glob/Bash. Activate whenever the agent needs to explore, understand, or modify a codebase that has trace-mcp indexed.

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering MCP servers and Codebase onboarding. It works with Model Context Protocol and Bash. The repository describes itself as: Framework-aware code intelligence MCP server — 88 framework integrations, 81 languages, 72.7% fewer input tokens to review a pull request, comprehension at parity. The licence is MIT.

When your agent uses it

Tasks that involve MCP servers
Tasks that involve Codebase onboarding

Example prompts

“/trace-mcp”

Requirements

Python 3

Workflow steps

2 steps, taken from the first numbered list in SKILL.md.

get_project_map with summary_only=true — orient yourself to the project structure
get_task_context with task: "" — gather all relevant code in a single call instead of chaining search → get_symbol → Read

What it can do on your machine

Read from SKILL.md and the folder at commit a577015. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
- python
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Trace MCP loads about 1.6k tokens when it runs. Until then it costs about 59 tokens; SKILL.md has 713 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~59
When it runs · the whole SKILL.md, loaded when a task matches: ~1.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

NoteMentions a .env fileSKILL.md:49

values) | `os.environ` dump, `cat` of a `.env` file |

NoteMentions a .env fileSKILL.md:56

`get_env_vars { "file": ".env", "redacted": true }` gives a line-by-line redacted

NoteMentions a .env fileSKILL.md:68

> - never `cat` or directly Read a `.env` file for discovery

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from nikolai-vysotskyi/trace-mcp at commit a577015, republished under its MIT licence (© nikolai-vysotskyi). 713 words, ~1,567 tokens.

Download SKILL.mdSave it as .claude/skills/trace-mcp/SKILL.md (or your agent's skills folder).

name: trace-mcp
description: Use trace-mcp tools for code navigation, impact analysis, and framework-aware queries instead of Read/Grep/Glob/Bash. Activate whenever the agent needs to explore, understand, or modify a codebase that has trace-mcp indexed.

trace-mcp — Code Intelligence Routing

trace-mcp is a framework-aware code intelligence MCP server. It exposes 182 tools that return semantic, structured results over a cross-language dependency graph. When trace-mcp is available, it is almost always cheaper and more accurate than native file tools.

When to Use

Activate this skill whenever you need to:

Find a function, class, method, route, component, or any symbol
Understand a file, module, or feature before editing
Determine what breaks if you change something
Trace a request flow, call graph, or data flow
Audit architecture, dead code, tests, or security

Do not use Read, Grep, Glob, or shell ls/find/cat/head/tail for exploring source code (.ts, .js, .py, .php, .go, .rb, .java, etc.). Use trace-mcp tools instead. Native tools stay allowed only for non-code files (.md, .json, .yaml, configs) or immediately before an Edit on a known file.

Start-of-Session Checklist

get_project_map with summary_only=true — orient yourself to the project structure
get_task_context with task: "<natural-language description>" — gather all relevant code in a single call instead of chaining search → get_symbol → Read

Decision Matrix

Task	trace-mcp tool	Instead of
Find a symbol by name	`search`	Grep
Understand a file before editing	`get_outline`	Read (full file)
Read one symbol's source	`get_symbol`	Read (full file)
Multiple symbols + shared imports	`get_context_bundle`	chained `get_symbol`
What breaks if I change X	`get_change_impact`	guessing
Who calls this / what does it call	`get_call_graph`	Grep
All usages of a symbol	`find_usages`	Grep
Implementations of an interface	`get_implementations`	Grep / ls
Classes implementing X	`search` with `implements` filter	Grep
Tests for a symbol or file	`get_tests_for`	Glob + Grep
Project overview	`get_project_map` (summary_only)	Bash ls/find
Context for a task	`get_task_context` / `get_feature_context`	reading many files
HTTP request flow	`get_request_flow`	reading route + controller files
DB model relationships	`get_model_context`	reading model + migrations
Component tree	`get_component_tree`	reading component files
Circular dependencies	`get_circular_imports`	manual tracing
Dead code / dead exports	`get_dead_code` (`mode: "exports_only"`)	Grep for unused
Project health / coverage gaps	`self_audit`	manual inspection
Complexity / hotspots	`get_complexity_report` / `get_risk_hotspots`	guessing
List env keys / what config exists	`get_env_vars` (keys + types/formats only, never values)	`os.environ` dump, `cat` of a `.env` file

Environment Variables (Safe Path)

Task "list env keys / what config exists" → get_env_vars. It returns keys plus inferred types/formats only — never values, so it is safe for secrets.
get_env_vars { "pattern": "DB_" } filters by key prefix. get_env_vars { "file": ".env", "redacted": true } gives a line-by-line redacted per-file view (keys + type hints, no values, preserves order/comments; requires file).
Config file discovery goes via search / get_symbol / get_outline / get_task_context — never by importing a module to see what it touches.

FORBIDDEN — never use these for env/config discovery (values leak into model context):

never dump the environment: python -c "import os; print(os.environ)" or any os.environ / process.env printout

never import-diff the environment: before = dict(os.environ), import a module, then diff os.environ to see what it touched

never print(module.__file__) for file discovery

never cat or directly Read a .env file for discovery

Show full SKILL.md (262 more words)Show less

Token-Efficiency Rules

Batch independent queries. Use batch when you need 2+ independent tool calls:

batch({ calls: [
  { tool: "get_outline", args: { path: "src/foo.ts" } },
  { tool: "get_outline", args: { path: "src/bar.ts" } },
  { tool: "search",      args: { query: "handleRequest", kind: "function" } }
]})

Never read the same file twice. Use get_outline once, then get_symbol for specific pieces.
Prefer get_context_bundle over chained get_symbol calls — it deduplicates shared imports.
Read-before-Edit optimization. When you must Read a file to edit it:
- Call get_outline first to find the line range of the target symbol.
- Read only that range with offset + limit. Never read a 500-line file to edit 5 lines.
Do not delegate code exploration to subagents. Agent subprocesses carry ~50k tokens of overhead before doing anything. Use trace-mcp tools in the main conversation instead.

After Editing a File

Call register_edit with the edited file_path to reindex just that file and invalidate caches. This is much lighter than a full reindex and keeps subsequent queries accurate.
If the response includes _duplication_warnings, review the referenced symbols — you may be duplicating existing logic.
Do not re-read the file to "verify" the edit. The Edit tool already confirmed success.

Before Creating New Symbols

Call check_duplication with { name, kind } to verify no similar symbol exists. Prevents reinventing existing logic.

Health Checks (Once Per Session)

audit_config — stale references in CLAUDE.md / settings
self_audit — dead exports, untested code, hotspots
get_tech_debt — per-module tech-debt grades
get_optimization_report — detects repeated reads, Bash grep usage, missed trace-mcp opportunities

trace-mcp-refactoring — safe refactoring workflow (risk assessment → rename → impact check)
trace-mcp-codemod — bulk mechanical changes via apply_codemod
trace-mcp-pre-commit — security, quality-gate, and antipattern checks before commit

Files

Just SKILL.md in skills/trace-mcp of nikolai-vysotskyi/trace-mcp.

Open the folder on GitHubat commit a577015

Compare with similar skills

Trace MCP next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Trace MCP compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Trace MCP this skillnikolai-vysotskyi/trace-mcp	189	—	~1.6k	Automated safety check: Notes	MIT	today
Crush Configurationcharmbracelet/crush	29k	—	~3.7k	Automated safety check: Pass	Custom licence	today
Record Demoapify/mcpc	1k	—	~3.3k	Automated safety check: Notes	Apache-2.0	2 days ago
Codebase SearchHelweg/open-codebase-index	218	—	~1.3k	Automated safety check: Pass	MIT	today
Codebase Search WorkflowHelweg/open-codebase-index	218	—	~822	Automated safety check: Pass	MIT	today
1c Code Searchcomol/ai_rules_1c	481	—	~1k	Automated safety check: Pass	None	3 days ago

Similar skills

Crush Configuration
charmbracelet/crush
Explains how to configure the Crush coding agent with crushrc or crush.json, covering providers, models, LSPs, MCP servers, hooks, permissions and config precedence.
29k GitHub stars~3.7k tokensUpdated today
Agent WorkflowsAuto-check passed
Record Demo
apify/mcpc
Official
Record or regenerate the mcpc demo GIFs (the README hero docs/images/mcpc-demo.gif and the focused tapes in docs/vhs/) with VHS.
1k GitHub stars~3.3k tokensUpdated 2 days ago
Agent WorkflowsAuto-check: notes
Codebase Search
Helweg/open-codebase-index
Chooses the right retrieval tool for code questions: compact context for unfamiliar repos, direct lookup for known symbols, call graphs for relationships and grep for exhaustive matches.
218 GitHub stars~1.3k tokensUpdated today
Agent WorkflowsAuto-check passed
Codebase Search Workflow
Helweg/open-codebase-index
Directs an agent to use a local codebase index for repository orientation, definition lookups, call graphs and semantic search before turning to web lookups.
218 GitHub stars~822 tokensUpdated today
Agent WorkflowsAuto-check passed
1c Code Search
comol/ai_rules_1c
Find BSL code in a 1C project — routines by name, code by behaviour or exact literal, module layout, members of a context — through the graph and code-metadata MCP servers before any Grep.
481 GitHub stars~1k tokensUpdated 3 days ago
Agent WorkflowsAuto-check passed
Basemind Index Scan
Goldziher/basemind
Builds or refreshes the basemind code index from the command line, for when basemind reports no index or its MCP server is not running.
108 GitHub stars~1.1k tokensUpdated today
Agent WorkflowsAuto-check: warnings

Questions about Trace MCP

What does Trace MCP do?

Use trace-mcp tools for code navigation, impact analysis, and framework-aware queries instead of Read/Grep/Glob/Bash. Trace MCP is an agent skill from nikolai-vysotskyi/trace-mcp. Use trace-mcp tools for code navigation, impact analysis, and framework-aware queries instead of Read/Grep/Glob/Bash.

When should I use Trace MCP?

Trace MCP fits situations like: tasks that involve MCP servers; tasks that involve Codebase onboarding.

How do I install Trace MCP in Claude Code?

Run `npx skills add nikolai-vysotskyi/trace-mcp --skill trace-mcp -a claude-code`. Or copy the skill folder (skills/trace-mcp in nikolai-vysotskyi/trace-mcp) into .claude/skills/trace-mcp in your project. Claude Code loads it when a task matches its description.

How do I install Trace MCP in Codex?

Run `npx skills add nikolai-vysotskyi/trace-mcp --skill trace-mcp -a codex`. Or copy the skill folder (skills/trace-mcp in nikolai-vysotskyi/trace-mcp) into .agents/skills/trace-mcp in your project. Codex loads it when a task matches its description.

Can I use Trace MCP in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add nikolai-vysotskyi/trace-mcp --skill trace-mcp -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/trace-mcp, .gemini/skills/trace-mcp, .github/skills/trace-mcp and .opencode/skills/trace-mcp in your project.

What does Trace MCP need to run?

Going by SKILL.md and its folder, Trace MCP needs the command-line tools its instructions call (python). Our summary lists: Python 3.

Does Trace MCP access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Trace MCP safe to install?

Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Trace MCP use?

Trace MCP is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Trace MCP use?

About 1.6k tokens (SKILL.md is roughly 6.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Trace MCP?

Skills that share tags, products or a category with Trace MCP: Crush Configuration (charmbracelet/crush, 29k stars), Record Demo (apify/mcpc, 1k stars), Codebase Search (Helweg/open-codebase-index, 218 stars) and Codebase Search Workflow (Helweg/open-codebase-index, 218 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Trace MCP?

nikolai-vysotskyi (a GitHub user) maintains it in nikolai-vysotskyi/trace-mcp, which has 189 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on October 11, 2026.

Source: nikolai-vysotskyi/trace-mcp on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Trace MCP

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

trace-mcp — Code Intelligence Routing

When to Use

Start-of-Session Checklist

Decision Matrix

Environment Variables (Safe Path)

Token-Efficiency Rules

After Editing a File

Before Creating New Symbols

Health Checks (Once Per Session)

Related Skills

Files

Compare with similar skills

Similar skills

More from nikolai-vysotskyi/trace-mcp

Related

Questions about Trace MCP