Agent skill

Filescope MCP

by admica in admica/FileScopeMCP

Codebase intelligence via FileScopeMCP — symbol lookup, dependency mapping, importance ranking, and semantic search.

ProprietaryAuto-check passedDevelopment

Install Filescope MCP

skills CLI
$ npx skills add admica/FileScopeMCP --skill filescope-mcp -a claude-code

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

GitHub CLI
$ gh skill install admica/FileScopeMCP filescope-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/admica/FileScopeMCP.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/filescope-mcp .claude/skills/filescope-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/

Facts

Skill name
filescope-mcp
GitHub stars
302
Token cost
~1.7k tokens
SKILL.md length
709 words
Files
1
Skills in repo
1
Repo updated
First seen
Licence
Proprietary

At a glance

Codebase intelligence via FileScopeMCP — symbol lookup, dependency mapping, importance ranking, and semantic search.

  • Works in 3 steps: status() — verify FileScopeMCP is… → find_important_files(maxItems: 10) — see… → get_file_summary(filepath) — read the…
  • Navigating unfamiliar code
  • SKILL.md covers Getting Oriented in a New…, Tool Reference, Common Workflows and Tips
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Filescope MCP is an agent skill from admica/FileScopeMCP. Codebase intelligence via FileScopeMCP — symbol lookup, dependency mapping, importance ranking, and semantic search. Use when navigating unfamiliar code, planning refactors, assessing change impact, or finding entry points in a large project.

Its SKILL.md is about 1.7k 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 Development, covering Refactoring. It works with Model Context Protocol. The repository describes itself as: Analyzes your codebase identifying important files based on dependency relationships. Generates diagrams and importance scores per file, helping AI assistants understand the…

When your agent uses it

  • Navigating unfamiliar code
  • Planning refactors
  • Assessing change impact
  • Finding entry points in a large project

Example prompts

  • “/filescope-mcp”

Workflow steps

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

  1. status() — verify FileScopeMCP is initialized and healthy. Check file count, broker state, last update time.
  2. find_important_files(maxItems: 10) — see the top 10 most critical files. These are your entry points.
  3. get_file_summary(filepath) — read the summary of each important file. Gives you: what it does, what it depends on, what depends on it…

What it can do on your machine

Read from SKILL.md and the folder at commit fd179e0. 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

    No scripts in the folder and no shell commands in SKILL.md.

    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

Filescope MCP loads about 1.7k tokens when it runs. Until then it costs about 64 tokens; SKILL.md has 709 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~64
When it runs · the whole SKILL.md, loaded when a task matches
~1.7k

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 passed

The automated check found no risky patterns in SKILL.md.

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

Its licence (Proprietary) doesn't allow us to republish the file, so here is its outline and opening line. It has 709 words (~1,747 tokens).

“FileScopeMCP is an MCP server that indexes your codebase and exposes it as tools. This skill teaches you when and how to use each tool effectively.”

— opening of SKILL.md by admica, Proprietary
name
filescope-mcp
version
1.0.0
author
admica
license
All Rights Reserved

Read the full SKILL.md on GitHub

Files

Just SKILL.md in skills/filescope-mcp of admica/FileScopeMCP.

Open the folder on GitHubat commit fd179e0

Compare with similar skills

Filescope 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.

Filescope MCP compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Filescope MCP this skilladmica/FileScopeMCP302—~1.7kAutomated safety check: PassProprietary
Gograph Go Repository Intelligenceozgurcd/gograph229—~4.8kAutomated safety check: NotesMIT
Scoring Checkscaliber-ai-org/ai-setup1.3k—~3kAutomated safety check: PassMIT
Writers Patterncaliber-ai-org/ai-setup1.3k—~3.7kAutomated safety check: PassMIT
Memtrace Decision Memorysyncable-dev/memtrace-public489—~1.9kAutomated safety check: PassCustom licence
Testing With API Mocksstacklok/toolhive-studio171—~1.5kAutomated safety check: PassApache-2.0

Similar skills

  • Gives an agent working in a Go codebase a structural view through a local MCP server: call graphs, blast-radius and impact analysis, and bounded first-call exploration.

    229 GitHub stars~4.8k tokensUpdated today
    DevelopmentAuto-check: notes
  • Scoring Checks

    caliber-ai-org/ai-setup

    Add a new deterministic scoring check in src/scoring/checks/ that evaluates config quality.

    1.3k GitHub stars~3k tokensUpdated 17 days ago
    DevelopmentAuto-check passed
  • Writers Pattern

    caliber-ai-org/ai-setup

    Add a new platform writer module in src/writers/ that generates and writes agent config files for a supported platform.

    1.3k GitHub stars~3.7k tokensUpdated 17 days ago
    DevelopmentAuto-check passed
  • Memtrace Decision Memory

    syncable-dev/memtrace-public

    Use Cortex decision memory through the normal Memtrace MCP tools.

    489 GitHub stars~1.9k tokensUpdated 2 days ago
    DevelopmentAuto-check passed
  • Testing With API Mocks

    stacklok/toolhive-studio

    Start here for all API mocking in tests. An agent skill from stacklok/toolhive-studio.

    171 GitHub stars~1.5k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Edt MCP Project Local Fix

    DitriXNew/EDT-MCP

    Apply one bounded BSL correction through EDT-MCP with lost-update protection, targeted validation, and minimal diff.

    296 GitHub stars~507 tokensUpdated 3 days ago
    DevelopmentAuto-check passed

Questions about Filescope MCP

What does Filescope MCP do?

Codebase intelligence via FileScopeMCP — symbol lookup, dependency mapping, importance ranking, and semantic search. Filescope MCP is an agent skill from admica/FileScopeMCP. Codebase intelligence via FileScopeMCP — symbol lookup, dependency mapping, importance ranking, and semantic search.

When should I use Filescope MCP?

Filescope MCP fits situations like: navigating unfamiliar code; planning refactors; assessing change impact; finding entry points in a large project.

How do I install Filescope MCP in Claude Code?

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

How do I install Filescope MCP in Codex?

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

Can I use Filescope 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 admica/FileScopeMCP --skill filescope-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/filescope-mcp, .gemini/skills/filescope-mcp, .github/skills/filescope-mcp and .opencode/skills/filescope-mcp in your project.

What does Filescope MCP need to run?

SKILL.md names no scripts, command-line tools or credentials: Filescope MCP is instructions for the agent only.

Does Filescope 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 Filescope MCP safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Filescope MCP use?

Filescope MCP carries a proprietary licence (declared in SKILL.md). It is published on GitHub, but it is not open source: read the licence file before using or sharing it.

How many tokens does Filescope MCP use?

About 1.7k tokens (SKILL.md is roughly 7k 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 Filescope MCP?

Skills that share tags, products or a category with Filescope MCP: Gograph Go Repository Intelligence (ozgurcd/gograph, 229 stars), Scoring Checks (caliber-ai-org/ai-setup, 1.3k stars), Writers Pattern (caliber-ai-org/ai-setup, 1.3k stars) and Memtrace Decision Memory (syncable-dev/memtrace-public, 489 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Filescope MCP?

admica (a GitHub user) maintains it in admica/FileScopeMCP, which has 302 GitHub stars. The repository was last updated on May 10, 2026.

Source: admica/FileScopeMCP on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.