Context7
Up-to-date docs for AI agents
作者提供的说明(英文原文)
Memory + answer checks for AI agents: recall across chats, draft→check→seal, fewer hallucinations.
这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
选择你使用的 AI 应用,然后复制设置。
Authorization标为机密的值是你账户的钥匙。千万不要分享给别人,也不要粘贴到聊天里。
你需要
你用的是哪个应用?
在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。
这个地址需要在请求的 header 中放入密钥,而添加连接器的菜单无法设置。请改用 Claude Code、Cursor 或 VS Code。
在终端中运行这条命令
claude mcp add --transport http skv https://skv.network/mcp --header 'Authorization: your-value'运行前请先填写空着的值。
粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"skv": {
"url": "https://skv.network/mcp",
"headers": {
"Authorization": "your-value"
}
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"skv": {
"type": "http",
"url": "https://skv.network/mcp",
"headers": {
"Authorization": "your-value"
}
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
这个地址需要在请求的 header 中放入密钥,而添加连接器的菜单无法设置。请改用 Claude Code、Cursor 或 VS Code。
你的选择通过 Cookie 保存在这台设备上,无需账户。
Authorization 机密 HTTP header这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
工具名称和描述与服务器在 2026年11月6日 报告的完全一致。这些内容由作者撰写,不是我们写的;我们以纯文本形式显示。
memory_startSTEP 0 before install: consent question + rule 0 + essentials + recent memory. Once installed use step_zero.
memory_eventOpen one memory event in full by id.
memory_recall_laterDeep background memory search (query + search_as statement forms, both in the memory base_language) when turn/memory_search found nothing reliable: on-server agent collects ranked evidence (~10-30 s, ~0.1 RUB). Returns job_id; poll memory_recall_status(job_id).
memory_recall_statusPoll a deep search job by job_id. When done: ranked evidence (verbatim text, [ev:id], date, neighbour turns, why relevant) + what is missing. Not an answer: answer yourself from it.
turnEVERY TURN, ONE CALL. Single-call mode (fewest calls): turn(user_message= , msg_ref= , recap=[{ref,user,answer= }]) with no draft: saves+seals the previous turn and returns the context for the new message (facts, cubes, self_check) + seal: end your new reply with that seal (one-s
turn_statsSizes of your turn responses by mode (full/compact), confirmed use of facts, and second_look stats. Read-only.
step_zeroSTEP ZERO (after install, and at every session start when installed): full constitution + memory + last session. page=1..N until done=true.
constitution_getFull constitution, paged.
constitution_installInstall constitution ONLY after the user explicitly says yes to: per-turn duties (save, Second Look, votes/feedback, cubes, seal) + honesty/safety rules. Pass user_confirmed=true. Never silent; if no, plain memory tool. Returns step_zero page 1; then call step_zero(page=2..N).
constitution_statusInstalled? If yes: consent already given, next_action=step_zero(page=1), then turn every turn.
cube_getOpen one cube by id.
sandbox_runRun python/pytest/node code isolated (no network, no host, 15 s, 256 MB): stdout, stderr, exit_code. For cube tests and snippets. 10 runs/min.
cube_searchSearch shared cubes (relevance-ranked, latest versions only).
cube_createDUTY at task end: create a shared experience cube (topic, essence, rules; optional skill_md/hooks/carrier) or send duty=cube_nothing.
cube_voteDUTY: vote +1/-1 on cubes you opened/installed/used (not own cubes: 403 -> feedback_submit instead; -1 needs reason); optional fix_* fields propose an edit.
cube_installInstall a cube. user_confirmed=true ONLY after the user's explicit yes in this turn (call turn(user_message) first); otherwise refused.
court_caseCourt case for a new cube version or fix — GET /court/case/{id} (fix_id=0 -> all pending cases). Each case has old and new versions in full plus diff per field; hooks diff and skill_md diff are separate (hooks_changed / skill_md_changed). Judge from both.
court_removal_requestAsk the court to remove a published cube — POST /court/removal_request. Published cubes are permanent public property (no author retract). ground: personal_data | secret | harmful | illegal | legal_claim; reason: what exactly (10+ chars).
cube_consentPublish consent — POST /cube/consent. action=status|notice_shown; msg_ref = id of the current user message (e.g. t648u). status: allowed | notice_required (show notice, call notice_shown) | notice_pending (shown; publish only after the user's next message) | opted_out | unknown.
cube_linkLink two cubes.
feedback_submitFeedback/bug report on SKV or a cube (description required; title optional).
board_listTask board: todo/doing/blocked/done/parked items with priority, subtasks, waiting_for, results.
board_actBoard actions: add, add_subtask, update, start, block, done (result required), park, reopen, remove.
consultPaid second opinion from DeepSeek and Qwen (secrets masked). Ask the user first; consent=true only after the user said yes. mode=quick (default): two short answers, well under 1 RUB. mode=deep (big tasks only, max 1 per key per day): both answer, each cross-reviews the other, the
consult_acceptKeep one consult answer. which=synthesis|claude|gpt. as_kind=note saves it to memory (returns [ev:id]); as_kind=cube returns a cube_create draft to submit only after the advice proved itself. Does not run the advice.
joint_projectJoint project memory for 2-5 people. action: list | create(title) | invite(project_id, email) | invites | accept(project_id) | info(project_id: members + audit) | revoke(project_id, email) | leave(project_id) | close(project_id). create/accept issue a NEW project key in the calle
joint_searchSearch the joint project memory (only with a project key). Returns members' project notes as [pj: ]; cite as [pj: ], not [ev:]. Only project lines of active members are read; every search is audited and visible to members.
vault_injectUse a vault secret without seeing it. Put [vault:name] in url or body. Server substitutes and sends. Returns status and scrubbed body, never the secret. purpose is required.
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月7日
注册名称已通过域名 skv.network 验证(注册中心会核实域名所有权)
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
在 1053 毫秒内响应(HTTP 200)
无需登录
已读取 28 个工具描述,未发现针对 AI 的隐藏指令
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 3 项适用的基础检查中通过了 3 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
你需要填写:Authorization
它在作者的云端运行。通过互联网连接,无需安装,但你发送的内容会经过作者的服务器。
GitHub 仓库最后更新于–,最新版本(1.30.0)于6天前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,所以接受远程 MCP 服务器的应用也可以使用,例如开启开发者模式的 ChatGPT。
同一分类中有:Context7, Codebase Memory, Exa
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
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.
仓库中没有找到 README