Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
作者提供的说明(英文原文)
Generate IDs, QR codes, and hashes, encode values, geolocate IPs, plus gated host diagnostics.
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。
MCP_LOG_LEVEL, TOOLKIT_ENABLE_NET_DIAGNOSTICS, TOOLKIT_ENABLE_SYSTEM_INFO, TOOLKIT_ALLOW_PRIVATE_NETWORK, TOOLKIT_GEO_API_KEY, TOOLKIT_GEO_BASE_URL, TOOLKIT_GEO_CACHE_TTL_SECONDS, TOOLKIT_GEO_RATE_LIMIT_PER_MIN, TOOLKIT_GEO_BATCH_RATE_LIMIT_PER_MIN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 …”。
适用于网页版、桌面版和手机版 Claude:
https://toolkit.caseyjhand.com/mcp打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json
{
"mcpServers": {
"toolkit": {
"command": "npx",
"args": [
"-y",
"@cyanheads/toolkit-mcp-server"
],
"env": {
"MCP_LOG_LEVEL": "your-value",
"TOOLKIT_ENABLE_NET_DIAGNOSTICS": "your-value",
"TOOLKIT_ENABLE_SYSTEM_INFO": "your-value",
"TOOLKIT_ALLOW_PRIVATE_NETWORK": "your-value",
"TOOLKIT_GEO_API_KEY": "your-value",
"TOOLKIT_GEO_BASE_URL": "your-value",
"TOOLKIT_GEO_CACHE_TTL_SECONDS": "your-value",
"TOOLKIT_GEO_RATE_LIMIT_PER_MIN": "your-value",
"TOOLKIT_GEO_BATCH_RATE_LIMIT_PER_MIN": "your-value"
}
}
}
}在终端中运行这条命令
claude mcp add --transport http toolkit https://toolkit.caseyjhand.com/mcpclaude mcp add toolkit --env MCP_LOG_LEVEL=your-value --env TOOLKIT_ENABLE_NET_DIAGNOSTICS=your-value --env TOOLKIT_ENABLE_SYSTEM_INFO=your-value --env TOOLKIT_ALLOW_PRIVATE_NETWORK=your-value --env TOOLKIT_GEO_API_KEY=your-value --env TOOLKIT_GEO_BASE_URL=your-value --env TOOLKIT_GEO_CACHE_TTL_SECONDS=your-value --env TOOLKIT_GEO_RATE_LIMIT_PER_MIN=your-value --env TOOLKIT_GEO_BATCH_RATE_LIMIT_PER_MIN=your-value -- npx -y @cyanheads/toolkit-mcp-server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": {
"toolkit": {
"url": "https://toolkit.caseyjhand.com/mcp"
}
}
}粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"toolkit": {
"command": "npx",
"args": [
"-y",
"@cyanheads/toolkit-mcp-server"
],
"env": {
"MCP_LOG_LEVEL": "your-value",
"TOOLKIT_ENABLE_NET_DIAGNOSTICS": "your-value",
"TOOLKIT_ENABLE_SYSTEM_INFO": "your-value",
"TOOLKIT_ALLOW_PRIVATE_NETWORK": "your-value",
"TOOLKIT_GEO_API_KEY": "your-value",
"TOOLKIT_GEO_BASE_URL": "your-value",
"TOOLKIT_GEO_CACHE_TTL_SECONDS": "your-value",
"TOOLKIT_GEO_RATE_LIMIT_PER_MIN": "your-value",
"TOOLKIT_GEO_BATCH_RATE_LIMIT_PER_MIN": "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": {
"toolkit": {
"type": "http",
"url": "https://toolkit.caseyjhand.com/mcp"
}
}
}粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"toolkit": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@cyanheads/toolkit-mcp-server"
],
"env": {
"MCP_LOG_LEVEL": "your-value",
"TOOLKIT_ENABLE_NET_DIAGNOSTICS": "your-value",
"TOOLKIT_ENABLE_SYSTEM_INFO": "your-value",
"TOOLKIT_ALLOW_PRIVATE_NETWORK": "your-value",
"TOOLKIT_GEO_API_KEY": "your-value",
"TOOLKIT_GEO_BASE_URL": "your-value",
"TOOLKIT_GEO_CACHE_TTL_SECONDS": "your-value",
"TOOLKIT_GEO_RATE_LIMIT_PER_MIN": "your-value",
"TOOLKIT_GEO_BATCH_RATE_LIMIT_PER_MIN": "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。
ChatGPT 只能连接互联网上的服务器:
https://toolkit.caseyjhand.com/mcp菜单名称可能因套餐和版本不同而略有差异。
你的选择通过 Cookie 保存在这台设备上,无需账户。
MCP_LOG_LEVEL envTOOLKIT_ENABLE_NET_DIAGNOSTICS envTOOLKIT_ENABLE_SYSTEM_INFO envTOOLKIT_ALLOW_PRIVATE_NETWORK envTOOLKIT_GEO_BASE_URL envTOOLKIT_GEO_CACHE_TTL_SECONDS envTOOLKIT_GEO_RATE_LIMIT_PER_MIN envTOOLKIT_GEO_BATCH_RATE_LIMIT_PER_MIN env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。
toolkit_hash_valueGenerate a cryptographic digest or HMAC of a value, or verify a value against an expected digest. Set operation to "generate" for a digest, or "compare" to constant-time-check value against the expected digest — compare is timing-safe and avoids manual string equality checks. Omi
toolkit_generate_idMint cryptographically-random identifiers using the platform CSPRNG — the correct source for IDs that must be unpredictable, unlike model-generated values. type selects the format: uuid_v4 (random, the default), uuid_v7 (time-ordered, sortable by creation), or ulid (26-char Crock
toolkit_generate_qrEncode text or a URL into a QR code. data is the content to encode (a link, a generated identifier such as toolkit_generate_id's ids[0], or any string). format selects the output: svg returns inline SVG markup sized in pixels, png_base64 returns base64-encoded PNG bytes (with mim
toolkit_encode_valueEncode or decode a value across base64, base64url, hex, or URL (percent) encoding, in either direction. Set operation to "encode" to transform raw UTF-8 text into the chosen encoding, or "decode" to recover the original bytes from an encoded value. Decoded bytes come back as UTF-
toolkit_geolocate_ipResolve a public IP or dotted hostname to country, region, city, coordinates, ASN, AS holder and name, organization, ISP, timezone, and proxy/hosting/mobile flags. Supply target for one lookup or targets for an ordered batch, never both; blank target and empty targets are unset.
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 cyanheads 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
在 168 毫秒内响应(HTTP 200)
无需登录
已读取 5 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:TOOLKIT_GEO_API_KEY
两种方式都可以:安装在你的电脑上,或者连接云端版本。
GitHub 仓库最后更新于–,最新版本(2.4.0)于3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:Spec Driven Development, Remote Desktop Commander, Signoff
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
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Five gates that make an agent's 'done' provable: run them, read the verdict, audit the record.
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。
@cyanheads/toolkit-mcp-server Generate random IDs, QR codes, and hashes, encode and decode values, and geolocate IPs, plus gated network and system diagnostics, via MCP. STDIO or Streamable HTTP. 7 Tools • 1 Skill
Public Hosted Server: https://toolkit.caseyjhand.com/mcp
Everyday developer utilities: generate IDs, QR codes, and hashes, encode and decode values, and geolocate a public IP or hostname. Only the geolocation lookup and the gated network diagnostics (off by default) make network calls; everything else runs locally.
| Tool | Description |
|---|---|
toolkit_hash_value | Generate a digest or HMAC (sha256/sha384/sha512/sha1/md5) as hex, base64, base64url, or SRI, or constant-time-compare a value against an expected digest or signature |
toolkit_generate_id | Mint cryptographically random UUIDv4, UUIDv7, or ULID identifiers, up to 1000 per call |
toolkit_generate_qr | Encode text or a URL as a QR code in SVG, base64 PNG, or terminal half-blocks |
toolkit_encode_value | Encode or decode base64, base64url, hex, or URL percent-encoding |
toolkit_geolocate_ip | Resolve a public IP or hostname to country, city, coordinates, ASN, and timezone |
toolkit_check_network | Gated, off by default. Ping, traceroute, TCP connectivity, or IPv4 egress-IP check from the server host |
toolkit_check_system | Gated, off by default. OS, CPU, memory, load average, or network interfaces of the server host |
| Skill | Description |
|---|---|
toolkit-guide | Gates the tool descriptions don't carry: reading a digest or signature mismatch, webhook and JWT signing inputs, moving digest bytes between hex, base64, and base64url, who runs an IP's network, and host diagnostics |
MCP clients that support the Skills extension read it as skill://toolkit-guide/SKILL.md. Plugin installs load it from skills/, which also ships in the npm package, the Docker image, and the .mcpb bundle.
toolkit_hash_value toolvalue read per inputEncoding (utf8 default, hex, base64); algorithm is sha256 (default), sha384, or sha512, with sha1 and md5 for checksum compatibility and verifying existing HMAC-SHA1 signatures only; operation is generate or compare, and when omitted it compares if expected is sentsecret makes the digest an HMAC keyed by it, for webhook signatures (GitHub's X-Hub-Signature-256 pastes into expected as-is) and HS256 JWT signatures; secretEncoding is utf8 (default), hex, base64, or base64url (a JWK k). The result then carries hmac: true, and the secret is never echoed in the result or an error; a secret invalid for its encoding fails as invalid_secret_encodinggenerate returns digest in digestEncoding (hex default, base64, unpadded base64url, or sri for plain SHA-2 digests, where an HMAC fails as sri_with_secret) plus lengthInBytes; compare returns matches against expected, pasted as published: hex, base64, or base64url, bare or prefixed (sha256: , sha256= ); SRI, including a multi-entry npm integrity value; or one checksum-file line as sha256sum, shasum, md5, or openssl dgst prints itexpected fails as expected_malformed (including a whole multi-line checksum file, with a hint to pass the file's own line), expected_length_mismatch (the hint names the algorithm that length fits), or expected_algorithm_mismatch (a tag, prefix, or SRI entry naming another algorithm)toolkit_generate_id tooltype is uuid_v4 (default), uuid_v7, or ulid; count is 1–1000 (default 1)ids always holds exactly count values; uuid_v7 and ulid batches are strictly increasing even within one millisecond, with random gaps so no id is derivable from anothertoolkit_generate_qr tooldata up to 2953 UTF-8 bytes at errorCorrection L, less at M (default), Q, and H; format is svg (default), png_base64, or terminal; margin 0–20 modules (default 4), scale 1–32 px per module (default 4)content, the symbol version (1–40), mimeType for image formats, and byteLength for PNG; png_base64 also arrives as an MCP image block, and terminal is plain Unicode half-blocks drawn for a dark backgrounddata_too_large with its byte count; a PNG over 2048 px per side fails as raster_too_large with a scale that fits, while svg and terminal have no pixel captoolkit_encode_value tooloperation (encode or decode) and encoding (base64, base64url, hex, url) are required; whitespace in hex, base64, and base64url input is ignored, so wrapped MIME and PEM bodies decode as-isresult as utf8 text unless outputEncoding asks for hex, base64, or unpadded base64url, which returns the bytes losslessly and transcodes between encodings; malformed input fails as decode_failed, and binary bytes as decode_not_utf8 rather than with replacement characterstoolkit_geolocate_ip tooltarget is an IPv4/IPv6 address or a dotted hostname, DNS-resolved first; private or reserved addresses, and public-format ones the provider reports as unlocatable, fail as private_target, unresolvable hostnames as unresolvable_hosttargets (up to 1000) instead, never both: the first 100 return ordered results with per-target errors, failedCount counts failures, and unprocessedTargets lists the rest to resubmitcountry, countryCode, region, city, latitude/longitude, asn, asHolder, asName, org, isp, and timezone with resolvedIp and source; a true in proxy, hosting, or mobile means the location describes infrastructure, not a personorg can name a customer or sub-allocation (APNIC and Cloudflare DNS Resolver project for 1.1.1.1); isp, asHolder, and asName (CLOUDFLARENET) name the network operator. With no org from the provider, org carries asHolder, then ispTOOLKIT_GEO_BASE_URL, TOOLKIT_GEO_API_KEY); results are cached per resolved IPTOOLKIT_GEO_RATE_LIMIT_PER_MIN=45, TOOLKIT_GEO_BATCH_RATE_LIMIT_PER_MIN=15); refusals report rate_limited with seconds to wait, and cache hits stay freetoolkit_check_network toolmode is ping, traceroute, connectivity, or public_ip (the host's IPv4 egress address; it can't show whether IPv6 egress works); target is required except for public_ip, and port (1–65535) for connectivity; count 1–10 pings (default 3), timeoutMs 100–30000 (default 3000, one budget across every address for connectivity); family 4 or 6 probes one address familyresolvedIp names the address whose result is reportedreachable: false, not an error; ping adds rttMs, sent, received, and packetLossPercent, connectivity adds outcome (open, refused, timeout, unreachable), and traceroute returns hops; a hostname that won't resolve fails as unreachable in every mode, as does ping or traceroute when its binary gives no result for any address tried (missing, stopped at its time limit, or exited with an error), and a family the target has no address in fails as family_mismatchTOOLKIT_ENABLE_NET_DIAGNOSTICS=true; unless TOOLKIT_ALLOW_PRIVATE_NETWORK=true, a hostname's private and reserved addresses are skipped, a target with nothing else fails as private_target_blocked, and error messages count those addresses instead of naming themtoolkit_check_system toolwhat is os, cpu, memory, load, or interfaces; exactly one matching facet object is populatedos names the runtime (runtime is bun or node, runtimeVersion its version) beside nodeVersion, the Node.js version the process reportsmemory.availableBytes is the allocation headroom, the same figure under Bun and Node, and limitBytes appears under a container memory limit; totalBytes, freeBytes, and usedBytes are raw OS figures, and on macOS freeBytes is free pages alone, so usedBytes counts reclaimable cache as used therememory_stats_unavailable instead of reporting free pagesTOOLKIT_ENABLE_SYSTEM_INFO=true, since os and interfaces disclose host topology and version detailsBuilt on @cyanheads/mcp-ts-core: stdio and Streamable HTTP transports, pluggable auth (none / jwt / oauth), swappable storage (in-memory, filesystem, Supabase, Cloudflare KV/R2/D1), structured logging with optional OpenTelemetry tracing.
Toolkit-specific:
node:crypto, Buffer, and the qrcode library, with no upstream callstoolkit_check_network and toolkit_check_system are absent from tools/list unless enabled. Both report on the server's host, not the caller's, so they belong on local or self-hosted deployments只显示了开头部分;其余内容请在仓库中阅读