Context7
Up-to-date docs for AI agents
제작자가 쓴 설명(영어 원문)
Hosted markdown project wikis your team's AI assistants read, search, and update over MCP.
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.
웹, 데스크톱, 모바일의 Claude에서 쓸 수 있어요:
https://getagentwiki.com/mcp터미널에서 이 명령어를 실행하세요
claude mcp add --transport http agent-wiki https://getagentwiki.com/mcp프로젝트의 .cursor/mcp.json 또는 ~/.cursor/mcp.json에 붙여 넣으세요
{
"mcpServers": {
"agent-wiki": {
"url": "https://getagentwiki.com/mcp"
}
}
}브라우저가 앱을 열지 물어본 다음, 앱이 설정을 보여 주고 확인을 요청해요. 키 값은 비워 두니 직접 입력하세요.
프로젝트의 .vscode/mcp.json에 붙여 넣으세요
{
"servers": {
"agent-wiki": {
"type": "http",
"url": "https://getagentwiki.com/mcp"
}
}
}브라우저가 앱을 열지 물어본 다음, 앱이 설정을 보여 주고 확인을 요청해요. 키 값은 비워 두니 직접 입력하세요.
ChatGPT는 인터넷에 있는 서버에만 연결할 수 있어요:
https://getagentwiki.com/mcp메뉴 이름은 요금제나 시기에 따라 조금 다를 수 있어요.
선택한 앱은 이 기기의 쿠키에만 저장돼요. 계정은 필요 없어요.
이 설정은 제작자의 레지스트리 정보로 만들었어요. README와 다르면 README를 따르세요.
아직 이 서버의 도구 목록을 읽지 않았어요. 엔드포인트는 차례대로 돌아가며 점검해요.
누구나 볼 수 있는 정보를 점검했고, 코드는 읽지 않았어요. 해당하지 않는 항목은 개수에서 뺐어요. · 2026년 11월 6일 점검
게시자(getagentwiki.com)가 저장소 소유자(animal-ltd)가 아니에요. 다른 사람이 등록했을 수 있어요
아직 GitHub에서 이 저장소를 읽어 오지 않았어요
아직 GitHub에서 이 저장소를 읽어 오지 않았어요
아직 점검하지 않았어요. 엔드포인트는 차례대로 돌아가며 점검해요
아직 점검하지 않았어요. 엔드포인트는 차례대로 돌아가며 점검해요
아직 점검하지 않았어요. 엔드포인트를 점검할 때 도구 목록을 읽어요
레지스트리에서 이 카테고리의 활성 서버 전체와 비교했어요. 스타는 게시자가 저장소를 소유한 경우에만 세요.
해당하는 기본 점검 1개 중 0개를 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.
제작자의 클라우드에서 실행돼요. 설치 없이 인터넷으로 연결하지만, 보내는 내용은 제작자의 서버를 거쳐요.
GitHub 저장소는 마지막으로 – 변경됐고, 최신 버전(0.1.0)은 2개월 전 레지스트리에 올라왔어요.
Claude Desktop, Claude Code, Cursor, VS Code처럼 MCP를 지원하는 앱에서 쓸 수 있어요. URL로 연결되기 때문에, 원격 MCP 서버를 지원하는 앱(예: 개발자 모드의 ChatGPT)에서도 쓸 수 있어요.
같은 카테고리에는: Context7, Codebase Memory, Exa
같은 카테고리에서 다른 제작자가 만든 서버예요. 스타 순으로 정렬했어요.
카드 보는 법:★ GitHub 스타i세 기둥: 리뷰 · 점검 · 사용 정도i업데이트 = 최신 버전을 레지스트리에 공개한 날i
Up-to-date docs for AI agents
Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
Connect AI agents to Exa for web search, content fetching, and multi-step research.
제작자의 저장소에서 쓰인 그대로 가져왔어요. PopNx MCP가 검토하거나 보증한 내용이 아니에요. HTML, 이미지, 스크립트는 제거했어요. 링크를 누르면 이 사이트를 벗어나요.
agent-wiki gives agents private markdown project memory over MCP. This public repository distributes version 0.3.0, including the explicitly invoked /agent-wiki:setup skill and a remote server at https://getagentwiki.com/mcp. It bundles no credentials, dependencies, or automatic write hooks.
First inspect /mcp in Claude Code. If agent-wiki already works through a direct server or a claude.ai connector, preserve that connection and read Existing connections before installing.
Run these commands in your shell:
claude plugin marketplace add animal-ltd/agent-wiki-plugin
claude plugin install agent-wiki@agent-wiki --scope user
The interactive equivalents are /plugin marketplace add animal-ltd/agent-wiki-plugin and /plugin install agent-wiki@agent-wiki; choose the intended scope in the plugin manager.
Use --scope project or --scope local only when intended. Installing in a project directory with --scope user still installs across projects. Installation scope does not grant wiki access. The bundled endpoint is account-wide; do not replace an existing single-wiki connection without choosing that broader connection yourself.
Restart Claude Code. In /plugin, check Installed for enabled agent-wiki version 0.3.0 and inspect Errors if /agent-wiki:setup is missing. A client that requests /reload-plugins supports that alternative; follow its reload instructions. Shell installation does not update an already-running conversation.
Installation only loads the skill and server. Open /mcp, select the active agent-wiki server, and choose Authenticate or Re-authenticate when needed. Complete sign-in and approval in the browser and return to the waiting client. Never share credentials or OAuth callback URLs. For a direct server named agent-wiki, Claude Code v2.1.186 or later also supports claude mcp login agent-wiki. A non-interactive prompt cannot complete interactive OAuth.
Once /mcp shows the connection and tools, invoke:
/agent-wiki:setup
You may supply a wiki name or id. The skill confirms access with list_wikis, asks if selection is ambiguous, checks the wiki's state, and reads at most three orientation pages. It configures private project instructions and a read-only retrieval hook using that existing connection. Native hooks require Claude Code 2.1.282 or newer. Before enabling retrieval, it explains that each current prompt, including pasted text, is sent transiently for retrieval and lets you choose instructions-only instead. The hook adds no separate transcript, local-path, or credential fields, but all text included in the prompt is sent. Agent-wiki does not retain that prompt text in its logs; client conversation history is separate. Existing settings, permissions, and other hooks are preserved.
Configuration does not require saving a new decision. If one is needed, the assistant shows the exact note and destination and waits for your approval. It uses a stable write request ID, preserves current versions, verifies the saved revision, and searches the result. Existing decisions are not saved again. No examples are saved as decisions.
If credentials expire, return to /mcp and re-authenticate the selected connection. If permission is read-only, access is missing, a tool call is refused, or you cancel, setup reports what remains incomplete and does not bypass the failure. A rerun checks for an already-saved decision rather than duplicating it. A save followed by failed verification is reported as unverified, not complete.
/mcp identifies server origins and hidden duplicates. Direct definitions can take precedence over a plugin server or an inherited claude.ai connector pointing at the same URL. The setup skill can use a confirmed existing connection; installation does not require deleting it. If more than one is usable, select one explicitly. Do not remove a working server or authenticate a duplicate merely to make the list shorter.
Claude.ai inheritance depends on the active login method. Check /status: API-key and other provider authentication do not load inherited connectors. A previous claude.ai login alone does not prove inheritance now. If an inherited connector needs authorization, use its claude.ai controls; a rejected Claude Code session token requires /login. Changing login method or connection scope is your choice, not a setup step performed automatically. Anthropic's MCP documentation explains the current behavior.
Without the plugin, a direct connection remains available via claude mcp add --transport http agent-wiki https://getagentwiki.com/mcp; its default local scope is for you in this project. It does not install the setup skill. Check existing connections first, then authenticate separately.
Use the same scope as the existing installation (shown in /plugin):
claude plugin marketplace update agent-wiki
claude plugin update agent-wiki@agent-wiki --scope user
Restart Claude Code, check version 0.3.0 in /plugin, and confirm /agent-wiki:setup is available before using it. Refreshing the catalog alone is not a plugin update. The plugin version controls cache updates; do not edit cached runtime files. If the old version remains, inspect the update output, marketplace source, selected scope, and /plugin Errors. Do not erase the whole Claude configuration or credential cache.
These are the supported commands in Claude Code 2.1.282; see the plugin reference and installation guide. Client acceptance receipts, including tested versions and public release SHAs, are tracked in #83. Source checks alone do not prove authentication or a successful setup.
To stop using this version, disable it in /plugin and restart. This does not delete wiki content; a direct connection can remain in use.
The retrieval hook is project-local and remains independent of plugin enablement. To stop automatic retrieval, ask Claude to remove only the recognized agent-wiki UserPromptSubmit hook from .claude/settings.local.json, preserving other hooks, permissions, and the existing connection. Keep or deliberately remove the marked instructions separately.
For the earlier public 0.1.0 artifact, first note your marketplace source and installation scope. This marketplace contains only agent-wiki. Removing it uninstalls its plugins, so do this only when you choose to replace that installation:
git clone https://github.com/animal-ltd/agent-wiki-plugin.git agent-wiki-plugin-rollback
git -C agent-wiki-plugin-rollback checkout --detach 81a790d715dfbd9412d1a30862d9c297afc290d7 claude plugin marketplace remove agent-wiki claude plugin marketplace add ./agent-wiki-plugin-rollback claude plugin install agent-wiki@agent-wiki --scope user
Restart and check 0.1.0 in /plugin. The old artifact has an MCP server but no setup skill. Keep that checkout at the pinned commit and do not update or delete its directory until ready to upgrade; replace it with the unpinned public source above to return to current releases. Use the original installation scope throughout. Wiki writes have separate version history; plugin rollback does not undo them.
The canonical source is animal-ltd/agent-wiki: plugins/agent-wiki, .claude-plugin/marketplace.json, this README (plugins/README.md there), plugins/LICENSE, and scripts/verify-plugin-package.mjs. Export through its scripts/export-plugin.mjs from a committed source into a reviewed public PR. Do not hand-edit the public copy or push an unattended synchronization to main.
SOURCE.json records the application source SHA, every exported file's SHA-256, a combined checksum, and the generated first-prompt checksum. Verify the self-contained public artifact with Node.js 22 or later:
node scripts/verify-plugin-package.mjs .
claude plugin validate . --strict claude plugin validate plugins/agent-wiki --strict
The receipt is a consistency check, not a signature: compare it to the independent application export and reviewed commits. Public release SHA and client receipts live outside the source commit so the receipt does not refer to its own hash.
Setup guide · Privacy · Terms · Security