GitHub
Connect AI assistants to GitHub - manage repos, issues, PRs, and workflows through natural language.
제작자가 쓴 설명(영어 원문)
Pre-computed atlas of your codebase for Claude Code: LSP + ADRs + git. 45-72% token reduction.
이 세 가지는 절대 하나의 점수로 합치지 않아요. 의견, 측정, 인기는 서로 다른 것이니까요.
이 서버는 아직 쉬운 말로 된 요약을 쓰지 못했어요. 아래는 레지스트리에서 읽어 온 사실이에요.
쓰고 있는 AI 앱을 고른 다음 설정을 복사하세요.
필요한 것
어떤 앱을 쓰세요?
위에서 앱을 고르세요. 기억해 두었다가 다음부터는 버튼에 “…에 설치”라고 표시해요.
Claude Desktop → Settings → Developer → Edit Config를 열고 claude_desktop_config.json에 이 내용을 붙여 넣으세요
{
"mcpServers": {
"contextatlas": {
"command": "npx",
"args": [
"-y",
"contextatlas"
]
}
}
}터미널에서 이 명령어를 실행하세요
claude mcp add contextatlas -- npx -y contextatlas프로젝트의 .cursor/mcp.json 또는 ~/.cursor/mcp.json에 붙여 넣으세요
{
"mcpServers": {
"contextatlas": {
"command": "npx",
"args": [
"-y",
"contextatlas"
]
}
}
}브라우저가 앱을 열지 물어본 다음, 앱이 설정을 보여 주고 확인을 요청해요. 키 값은 비워 두니 직접 입력하세요.
프로젝트의 .vscode/mcp.json에 붙여 넣으세요
{
"servers": {
"contextatlas": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"contextatlas"
]
}
}
}브라우저가 앱을 열지 물어본 다음, 앱이 설정을 보여 주고 확인을 요청해요. 키 값은 비워 두니 직접 입력하세요.
이 서버는 내 컴퓨터에서 실행되는데, ChatGPT는 인터넷에 있는 서버에만 연결할 수 있어요. 다른 앱을 고르세요.
선택한 앱은 이 기기의 쿠키에만 저장돼요. 계정은 필요 없어요.
이 설정은 제작자의 레지스트리 정보로 만들었어요. README와 다르면 README를 따르세요.
내 컴퓨터에서 실행돼요. 설치하면 AI 앱에 도구 목록이 나타나요.
누구나 볼 수 있는 정보를 점검했고, 코드는 읽지 않았어요. 해당하지 않는 항목은 개수에서 뺐어요. · 2026년 11월 6일 점검
레지스트리 이름이 GitHub 계정 traviswye 기준으로 확인되었고, 이 계정이 저장소를 소유하고 있어요
아직 GitHub에서 이 저장소를 읽어 오지 않았어요
아직 GitHub에서 이 저장소를 읽어 오지 않았어요
내 컴퓨터에서 실행되는 서버라 인터넷 엔드포인트가 없어요
내 컴퓨터에서 실행되며, 대신 로컬 설정을 사용해요
내 컴퓨터에서 실행돼요. 도구 목록은 인터넷 엔드포인트가 있는 서버에서만 읽을 수 있어요
레지스트리에서 이 카테고리의 활성 서버 전체와 비교했어요. 스타는 게시자가 저장소를 소유한 경우에만 세요.
해당하는 기본 점검 1개 중 1개를 통과했어요. 코드는 읽지 않았어요. 키나 토큰을 넣기 전에 서버가 어떤 권한을 요구하는지 확인하고, 꼭 필요한 권한만 있는 키를 쓰세요.
레지스트리에 필수 키가 나와 있지 않아요. 다만 처음 쓸 때 로그인을 요구하는 서버도 있어요.
내 컴퓨터에서 실행돼요. AI 앱이 필요할 때 실행하고, 데이터는 제작자의 서버를 거치지 않아요(서버 자체가 온라인 서비스를 호출하는 경우는 제외).
GitHub 저장소는 마지막으로 – 변경됐고, 최신 버전(1.0.1)은 6개월 전 레지스트리에 올라왔어요.
Claude Desktop, Claude Code, Cursor, VS Code처럼 MCP를 지원하는 앱에서 쓸 수 있어요. 내 컴퓨터에 Node.js도 있어야 해요.
같은 카테고리에는: GitHub, Desktop Commander, Cloudflare MCP
같은 카테고리에서 다른 제작자가 만든 서버예요. 스타 순으로 정렬했어요.
카드 보는 법:★ GitHub 스타i세 기둥: 리뷰 · 점검 · 사용 정도i업데이트 = 최신 버전을 레지스트리에 공개한 날i
Connect AI assistants to GitHub - manage repos, issues, PRs, and workflows through natural language.
MCP server for terminal commands, file operations, and process management
Cloudflare MCP servers
제작자의 저장소에서 쓰인 그대로 가져왔어요. PopNx MCP가 검토하거나 보증한 내용이 아니에요. HTML, 이미지, 스크립트는 제거했어요. 링크를 누르면 이 사이트를 벗어나요.
Stop watching Claude burn tokens grepping for context it can't possibly find.
ContextAtlas turns your codebase into a *single-call* context bundle for Claude Code — fusing LSP-grade structure, architectural intent from your Architectural Decision Records (ADRs), git history, and test associations. Measured 45-72% token reduction with zero quality regression across benchmark axes on architectural prompts across the hono / httpx / cobra benchmark suite.
Quick start → · Benchmark results → · Why not graph-based? → · Architecture → · ADRs →
ContextAtlas ships two equivalent paths — CLI and Claude Code Skills — both producing the same atlas.json. See Quick Start for setup.
Claude Code currently learns your codebase by brute force. Every session starts fresh. Every "where is X?" triggers multiple grep calls. Every "what depends on Y?" is another flurry of file reads. On a mid-sized codebase, answering a single architectural question can consume 40+ tool calls and 100,000+ tokens before Claude has enough context to reason well.
Worse: the architectural intent that governs your code — the ADRs, the design decisions, the "we did it this way because" — is invisible to Claude. The rule that OrderProcessor must be idempotent lives in docs/adr/. When Claude proposes a change, it has no way to know that constraint exists.
Yesterday's understanding doesn't carry to today. Every conversation starts from zero. Your ADRs, your commit history, your test coverage — none of it is on the agent's table.
What if expensive understanding happened once, at index time, and every query became a dictionary lookup?
That's ContextAtlas.
ContextAtlas is an MCP server that gives Claude Code a curated atlas of your codebase — fusing LSP-grade structural precision with architectural intent extracted from your ADRs, docs, and git history, delivered to Claude in single-call context bundles.
Every bundle Claude receives combines four independent signals about a symbol:
One MCP call returns all four, fused. No ADRs in your repo yet? You still get LSP + git + tests in one call instead of fifteen — a meaningful baseline improvement. Add ADRs and the bundles get richer. The architecture is designed so any subset of signals produces value.
Given an ADR stating that OrderProcessor must be idempotent, a call to get_symbol_context("OrderProcessor") returns:
SYM OrderProcessor@src/orders/processor.ts:42 class
SIG class OrderProcessor extends BaseProcessor INTENT ADR-07 hard "must be idempotent" RATIONALE "All order processing must be safely retryable." INTENT ADR-12 soft "prefer async base class for new processors" REFS 23 [billing:14 admin:9] TOP ref:ts:src/billing/charges.ts:88 TOP ref:ts:src/admin/orders.ts:12 GIT hot last=2026-03-14 RECENT "Fix idempotency bug in retry path" a3f2c1d TESTS src/orders/processor.test.ts (+11)
When Claude is asked to modify OrderProcessor, it sees the idempotency constraint *before* proposing changes — not after a user review catches the violation.
Who this is for. ContextAtlas is built for the average developer using Claude Code on real codebases — not just engineers at large orgs working on 500,000-file monorepos. Token-burn reduction scales with codebase size — dramatic on a 200-file framework, modest on a 30-file library. But architectural intent capture is size-invariant. A 30-file library can have meaningful architectural decisions worth surfacing, and Claude respecting them matters just as much as on a larger codebase.
Efficiency and quality are necessary but not sufficient. The substantive value of context-grounding shows up in design choices on non-trivial code-change tasks.
A/B trial during v0.3 development. Identical 3-paragraph prompt across two ContextAtlas clones: implement a known bug fix — locate the bug, design and implement the fix, write tests, document via ADR. The only setup difference: MCP availability.
| Arm | MCP | Approach selected |
|---|---|---|
| A (vanilla) | none | Recall-first approach (broader matching; fought the project's precision-thesis with noise) |
| B (CA-aided) | ContextAtlas | Precision-optimization approach (aligned with the project's pre-extracted-claims-with-structural-attribution thesis) |
Arm B's approach landed in main. Both arms functionally fixed the bug at similar wall-clock and token cost. The substantive difference was *alignment with project design thesis* — the CA-aided arm could read the relevant ADR + prior architectural work from the atlas, and made a choice that fit. The vanilla arm couldn't see that context and chose an approach that worked but fought the architecture.
Arm A's substantive consideration wasn't lost — captured as future-work investigation trigger. The recall-vs-precision tradeoff is preserved.
Full synthesis at v0.3 Round 3 dogfood evidence.
N=1 trial; this is anecdote, not benchmark. The systematic benchmark suite (hono / httpx / cobra) measures efficiency and quality (see §The Numbers below). This A/B trial measures the substantively-distinct *design-alignment* axis — which doesn't fit benchmark-suite methodology (every code-change task is repo- specific) but is the substantive value proposition for cohort developers building on real codebases.
We benchmark ContextAtlas against baseline Claude Code on three repositories chosen to reflect realistic developer workloads:
| Repo | Language | Source files | Role |
|---|---|---|---|
| honojs/hono | TypeScript | 186 | Mid-sized framework |
| encode/httpx | Python | 23 | Focused production library |
| spf13/cobra | Go | 19 | CLI framework |
Methodology. 24 prompts per repo, 6 task buckets, blind manual grading, pre-registered rubric, no cherry-picking. Full methodology in RUBRIC.md.
Phase 5 reference run on hono, six pre-registered prompts:
| Prompt | Bucket | Alpha calls | CA calls | Δ | Alpha $ | CA $ |
|---|---|---|---|---|---|---|
| h1-context-runtime | win | 18 | 9 | −50% | $2.36 | $1.52 |
| h2-router-contract | win | 11 | 5 | −55% | $0.60 | $0.53 |
| h3-middleware-onion | win | 5 | 5 | 0% | $0.38 | $0.47 |
| h4-validator-typeflow | win | 21 | 6 | −71% | $2.95 | $0.52 |
| h5-hono-generics | tie | 11 | 13 | +18% | $0.79 | $1.17 |
| h6-fetch-signature | trick | 3 | 4 | +33% | $0.17 | $0.29 |
| aggregate | 69 | 42 | −39% | $7.25 | $4.50 (−38%) |
The headline case: h4-validator-typeflow ran 7.3× cheaper ($2.95 → $0.52) at equivalent answer depth. CA opens with the governing ADR by number; the baseline reconstructs the architecture from source. Tie and trick buckets (h5, h6) show CA net-negative as the rubric predicted — CA over-engineers on questions where architectural intent doesn't carry load. Bucket-aware methodology surfaces these expected cases rather than burying them.
Cross-language replication: the same architectural-intent win mechanism holds on Python (Phase 6 — httpx) and Go (Phase 7 — cobra). Phase 8 re-ran the locked prompt sets against v0.3-sharpened atlases at the same pinned target SHAs: 45-72% token reduction on architectural-intent prompts across all three target languages. Full synthesis at phase-8-v0.3-reference-run.md.
v0.5 shipped the LLM-judge methodology under paired-mode anonymization (per ADR-19). Cross-cell rollup paired-t at N=27 differences per axis (5 anchor cells × n=5 trials × 2 conditions; hono h1 auto-stretch to n=8):
| Quality axis | Mean Δ (0-3 scale) | 95% CI | Tier |
|---|---|---|---|
| Factual correctness | +0.370 | [0.176, 0.565] | CLEAN |
| Hallucination | +0.296 | [0.032, 0.561] | Borderline |
| Actionability | +0.148 | [0.005, 0.291] | Borderline |
| Completeness | +0.037 | [-0.039, 0.113] | Not distinguishable |
Threshold pre-registration: the three-tier framing (≥0.05 CLEAN; 0.001-0.05 BORDERLINE; ≤0 NOT distinguishable) was locked before precision values were computed. No goalpost-shifting after data. 76% tie rate confirms anonymization worked — the judge couldn't tell which condition was which on three-quarters of comparisons.
Full per-axis numerics + 9 named findings at the Phase-9 reference doc. Honest methodology limits documented in §Methodology and Honest Limits below.
A few deliberate framings — what ContextAtlas is and isn't relative to neighboring tools:
vs. graph-based code intelligence (Graphify and similar). We're in the same category — both build pre-computed indexes over codebases for LLM agents via MCP. That's genuine category overlap, and we want to be straight about it. Where we differ:
graph_query, get_neighbors, shortest_path) that callers compose.앞부분만 보여 드려요. 나머지는 저장소에서 읽어 보세요