llm-context.py MCP — 사용 사례, 설치 & 라이브 데모

왜 쓰나요

핵심 기능

Rule-based file selection (filter rules) — per-task context, not one-size-fits-all
Multiple rule types: prompt / filter / instruction / style / excerpt
lc_outlines compresses big codebases into structural outlines
lc_missing: LLM can fetch specific files mid-conversation
Clipboard-only mode for LLM clients that don't support MCP

라이브 데모

실제 사용 모습

llm-context-py.replay ▶ 준비됨

0/0

설치

클라이언트 선택

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "llm-context-py": {
      "command": "uvx",
      "args": [
        "llm-context.py"
      ],
      "_inferred": true
    }
  }
}

Claude Desktop → Settings → Developer → Edit Config 열기. 저장 후 앱 재시작.

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "llm-context-py": {
      "command": "uvx",
      "args": [
        "llm-context.py"
      ],
      "_inferred": true
    }
  }
}

Cursor는 Claude Desktop과 동일한 mcpServers 스키마 사용. 프로젝트 설정이 전역보다 우선.

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "llm-context-py": {
      "command": "uvx",
      "args": [
        "llm-context.py"
      ],
      "_inferred": true
    }
  }
}

Cline 사이드바의 MCP Servers 아이콘 클릭 후 "Edit Configuration" 선택.

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "llm-context-py": {
      "command": "uvx",
      "args": [
        "llm-context.py"
      ],
      "_inferred": true
    }
  }
}

Claude Desktop과 같은 형식. Windsurf 재시작 후 적용.

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "llm-context-py",
      "command": "uvx",
      "args": [
        "llm-context.py"
      ]
    }
  ]
}

Continue는 맵이 아닌 서버 오브젝트 배열 사용.

~/.config/zed/settings.json

{
  "context_servers": {
    "llm-context-py": {
      "command": {
        "path": "uvx",
        "args": [
          "llm-context.py"
        ]
      }
    }
  }
}

context_servers에 추가. 저장 시 Zed가 핫 리로드.

claude mcp add llm-context-py -- uvx llm-context.py

한 줄 명령. claude mcp list로 확인, claude mcp remove로 제거.

사용 사례

실전 활용법: llm-context.py

Ship a focused code-review context to your LLM

👤 Developers tired of pasting 3000 lines ⏱ ~15 min intermediate

언제 쓸까: You're about to ask 'review my auth module' and don't want the whole repo in context.

사전 조건

llm-context.py installed — uv tool install 'llm-context>=0.6.0'
Initialized in your repo — lc-init in your repo root

흐름

Create a filter rule for auth

Create an lc filter rule 'flt-auth' that includes src/auth/** and src/middleware/auth*.ts.✓ 복사됨

→ Rule file created under .lc/
Preview what the rule selects

Run lc_preview on flt-auth — show me which files will be sent and total token count.✓ 복사됨

→ File list + token count
Share context with the LLM via MCP

Using the flt-auth rule, review the module for security issues. If you need to see a specific file not included, ask via lc_missing.✓ 복사됨

→ Review with targeted file requests

결과: A code review that fits in context and can still explore — no manual paste.

함정

Rule too narrow → LLM can't understand callers of your module — Include interface / types of neighboring modules, use outlines for the rest
Rule too broad → token budget blown — Start broad, watch lc_preview, tighten until under your client's limits

함께 쓰기: filesystem

Give an LLM a structural map of a huge codebase

👤 Engineers onboarding to unfamiliar monorepos ⏱ ~20 min intermediate

언제 쓸까: 100k+ LOC repo; you need orientation, not all the code.

흐름

Generate outline

lc_outlines for the whole repo — classes, top-level functions, exports per file. Skip bodies.✓ 복사됨

→ Skeletal outline with a few thousand lines
Ask orientation questions

Given the outline, where's the entry point, where's routing defined, and which files hold the data-layer abstractions?✓ 복사됨

→ Architectural answers
Drill in on one area

Show me the full contents of the three files that define routing via lc_missing.✓ 복사됨

→ Specific files expand into context

결과: A guided tour without ever pasting the whole repo.

Attach project style rules to every prompt

👤 Teams with specific conventions ⏱ ~10 min beginner

언제 쓸까: You want Claude to always know 'we use pytest, not unittest' without repeating.

흐름

Write a style rule

Create sty-python rule: 'pytest only, type hints required, black formatting'.✓ 복사됨

→ Rule saved
Apply automatically

Use prm-default which composes flt-current + sty-python + ins-standards for every context.✓ 복사됨

→ Rule auto-attached

결과: Per-task conventions enforced without manual boilerplate.

함께 쓰기: drift

조합

다른 MCP와 조합해 10배 효율

llm-context-py + drift

drift records conventions; llm-context pushes only relevant files + style rules per task

Load drift conventions for this repo, then use lc with rule flt-auth + sty-ts to review the auth module.✓ 복사됨

llm-context-py + filesystem

After reviewing, filesystem applies edits

Based on the llm-context review, use filesystem to apply the suggested edits to src/auth/.✓ 복사됨

도구

이 MCP가 노출하는 것

도구	입력	언제 호출	비용
lc_outlines	rule?: str	Orient on large codebases	free (local)
lc_preview	rule: str	Before shipping context, verify scope	free
lc_missing	path: str	LLM calls this mid-conversation to request a file	free

비용 및 제한

운영 비용

API 쿼터: None
호출당 토큰: Depends entirely on your rule scope — that's the point
금액: Free, open source
팁: Always run lc_preview before lc_outlines/shipping context — one second of preview saves thousands of tokens.

보안

권한, 시크릿, 파급범위

자격 증명 저장: None

데이터 외부 송신: Only to whichever LLM client/provider you pipe context into

Review rule globs before running — a stray **/* will happily include node_modules.
lc_missing is powerful; constrain its allowed paths in rules if you store secrets in the repo.

문제 해결

자주 발생하는 오류와 해결

No rules found

Run lc-init in repo root to create .lc/ scaffolding.

확인: ls .lc/

lc_preview token count surprisingly high

Your filter is too loose or includes generated files. Narrow globs and add ignore patterns.

확인: lc_preview again

MCP tool not available

Use uvx --from llm-context lc-mcp in your MCP server config.

확인: claude mcp list

대안

llm-context.py 다른 것과 비교

대안	언제 쓰나	단점/장점
repomix / ai-digest	You want a single-file dump, not MCP tools	No interactive lc_missing; static snapshot
filesystem MCP	You want raw file access	No rule-based selection or outlines
drift	You want persistent convention memory, not per-task file bundling	Different problem entirely

llm-context.py