Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
Generate IDs, QR codes, and hashes, encode values, geolocate IPs, plus gated host diagnostics.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
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_MINValues marked secret are keys to your account. Never share them or paste them into a chat.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Works in Claude on the web, desktop and mobile:
https://toolkit.caseyjhand.com/mcpOpen Claude Desktop → Settings → Developer → Edit Config, and paste this into 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"
}
}
}
}Run this in your terminal
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-serverFill in the empty values before running it.
Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"toolkit": {
"url": "https://toolkit.caseyjhand.com/mcp"
}
}
}Paste into .cursor/mcp.json in your project, or ~/.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"
}
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"toolkit": {
"type": "http",
"url": "https://toolkit.caseyjhand.com/mcp"
}
}
}Paste into .vscode/mcp.json in your project
{
"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"
}
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
ChatGPT connects only to servers on the internet:
https://toolkit.caseyjhand.com/mcpMenu names can differ slightly by plan and over time.
Your choice stays on this device in a cookie; no account needed.
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 envThese settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Tool names and descriptions exactly as the server reported them on Nov 6, 2026. The maker wrote them, not us; we show them as plain text.
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.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 7, 2026
The registry name was verified with the GitHub account cyanheads, which owns the repo
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
Responded in 168 ms (HTTP 200)
No sign-in needed
Read 5 tool descriptions and found no hidden instructions to the AI
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 3 of 3 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
You need to fill in: TOOLKIT_GEO_API_KEY
Either way works: install it on your computer or connect to the cloud version.
The GitHub repo last changed –, and the latest version (2.4.0) reached the registry 3 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. It connects by URL, so apps that accept remote MCP servers work too, such as ChatGPT in developer mode.
In the same category: Spec Driven Development, Remote Desktop Commander, Asset Notation
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
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.
Read and maintain an Asset Notation file on disk: net worth, holdings, valuations, CSV import.
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
@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 deploymentsOnly the beginning is shown; read the rest in the repo