Context7
Up-to-date docs for AI agents
作者提供的说明(英文原文)
Verified, local-first retrieval over pinned Knolo Knowledge Images.
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。
KNOLO_MCP_CONFIG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 …”。
打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json
{
"mcpServers": {
"knolo": {
"command": "npx",
"args": [
"-y",
"@knolo/mcp"
],
"env": {
"KNOLO_MCP_CONFIG": "your-value"
}
}
}
}在终端中运行这条命令
claude mcp add knolo --env KNOLO_MCP_CONFIG=your-value -- npx -y @knolo/mcp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": {
"knolo": {
"command": "npx",
"args": [
"-y",
"@knolo/mcp"
],
"env": {
"KNOLO_MCP_CONFIG": "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": {
"knolo": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@knolo/mcp"
],
"env": {
"KNOLO_MCP_CONFIG": "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。
这个服务器在你的电脑上运行,而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。
你的选择通过 Cookie 保存在这台设备上,无需账户。
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。
它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。
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 GitHub 账户 HiveForensics-AI 验证,该账户拥有此仓库
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
它在你的电脑上运行,没有互联网端点
在你的电脑上运行,改用本地设置
它在你的电脑上运行;我们只能读取互联网端点的工具列表
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 1 项适用的基础检查中通过了 1 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:KNOLO_MCP_CONFIG
它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。
GitHub 仓库最后更新于–,最新版本(0.1.0)于25天前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Node.js。
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.
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
@knolo/mcp is a read-only MCP server for pinned Knolo V5 Knowledge Images. It exposes the same four tools as @knolo/openclaw: knolo_search, knolo_get, knolo_verify, and knolo_status. Pins, policy checks, and query receipts come from @knolo/tools. When at least one mount includes a kar block, the server also exposes knolo_kar_evaluate, knolo_kar_verify, and knolo_cortex_verify.
The server speaks stdio only. It does not download images, open a runtime network connection, write or compile knowledge, or expose MCP resources or prompts. Install and pin each image before starting it. A hash, state-root, or policy-root mismatch exits non-zero before the MCP connection starts.
Caller identity is agentId in the config file, default mcp. That id must be listed in the mount's agents array. Tool arguments cannot set it. The MCP client's clientInfo.name is stored on the receipt as sessionId and is not used for authorization. One principal per mount is what policy evaluation sees.
Every search writes an openclaw-knolo-query-v1 receipt before it returns hits. An unwritable auditDir returns AUDIT_UNAVAILABLE and no hits. Before each tool call, a server started from a config file stats that config, every mounted image, and any pinned KAR graph. An unchanged size and modification time keeps the loaded image. A changed file is checked against the pin in that config. A match replaces the loaded image. A mount removed from the config is no longer served, even when its image file is still on disk. A mismatch returns IMAGE_INVALID and does not serve the previous image. A config file that cannot be read fails that call. agentId and maxHits stay at the values from process start. KAR graphs are authorized with that same startup agentId.
@knolo/mcp@0.2.0 is published on npm. A mount without a kar block exposes the four tools above. A mount with a kar block also exposes knolo_kar_evaluate, knolo_kar_verify, and knolo_cortex_verify. The registry name in server.json is io.github.HiveForensics-AI/knolo. Published @knolo/mcp@0.1.0 remains the four-tool server.
The Google ADK examples start this server over stdio and run one search. Python and TypeScript both use MCP.
Paths are absolute. sha256 is 64 lowercase hex characters. stateRoot is sha256- plus 64 lowercase hex characters.
{
"agentId": "mcp", "auditDir": "/var/lib/knolo/receipts", "mounts": [ { "id": "handbook", "path": "/opt/knolo/handbook.knolo", "sha256": "<64 hex>", "stateRoot": "sha256-<64 hex>", "policyPath": "/opt/knolo/handbook.policy.json", "agents": ["mcp"], "principal": " ", "kar": { "graphPath": "/opt/knolo/handbook.kar.json", "graphSha256": "<64 hex>" } } ] }
kar is optional. graphSha256 is the raw file SHA-256, 64 lowercase hex characters, without a sha256- prefix. The server hashes that file and binds it to the mount before it accepts a connection. A hash or binding mismatch exits before MCP starts. A call for a mount that has no kar block fails closed when the three tools are enabled by another mount.
knolo_kar_evaluate takes mountId, proposition, and an inline plan object of at most 65536 UTF-8 bytes. SATISFIED means evidence requirements were met. It does not mean a claim is proven. UNSATISFIED_EVIDENCE_REQUIREMENTS is a completed evaluation. The plan is parsed by the KAR plan parser. Domain Pack template names are not accepted.
knolo_kar_verify takes the same mount, proposition, and plan, plus exactly one of result or dossier. knolo_cortex_verify takes mountId, an answer trace, and an optional question. It uses the pinned graph when the trace references KAR. These tools do not call a model and do not run askCortex.
Query receipts stay openclaw-knolo-query-v1. KAR and Cortex tools write knolo-mcp-evidence-receipt-v1 in auditDir before they return a result. An unwritable audit directory returns AUDIT_UNAVAILABLE and no result.
Start it with knolo-mcp --config /absolute/knolo-mcp.json or KNOLO_MCP_CONFIG. Logs go to stderr. Stdout is JSON-RPC only.
Claude Desktop, Claude Code, and Cursor:
{
"mcpServers": { "knolo": { "command": "npx", "args": ["-y", "@knolo/mcp", "--config", "/absolute/knolo-mcp.json"] } } }
Claude Code CLI:
claude mcp add knolo -- npx -y @knolo/mcp --config /absolute/knolo-mcp.json
VS Code (.vscode/mcp.json):
{
"servers": { "knolo": { "type": "stdio", "command": "npx", "args": [ "-y", "@knolo/mcp", "--config", "${workspaceFolder}/knolo-mcp.json" ] } } }
The package requires Node 20 or newer, @knolo/core ^6.2.0, and @knolo/tools ^0.2.0. Coverage, composition, and authoring stay outside this server. Verification checks integrity. It does not decide that a claim or an answer is true.