Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
Token due-diligence for AI agents: grade verdicts, mint activity, settlement safety.
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.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json
{
"mcpServers": {
"forensics": {
"command": "npx",
"args": [
"-y",
"onchain-forensics-mcp"
]
}
}
}Run this in your terminal
claude mcp add forensics -- npx -y onchain-forensics-mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"forensics": {
"command": "npx",
"args": [
"-y",
"onchain-forensics-mcp"
]
}
}
}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": {
"forensics": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"onchain-forensics-mcp"
]
}
}
}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.
This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.
Your choice stays on this device in a cookie; no account needed.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Runs on your computer; the tool list appears in your AI app after you install it.
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 publisher (onchainforensics.dev) is not the repo owner (leohoudinisanders-byte); someone else may have listed it
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
This one runs on your computer; there is no internet endpoint
Runs on your computer and uses local settings instead
Runs on your computer; we can only read tool lists from internet endpoints
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 0 of 1 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.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
The GitHub repo last changed –, and the latest version (1.1.1) reached the registry today.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Node.js on your computer.
In the same category: Spec Driven Development, Remote Desktop Commander, Hunter Killer
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.
Liquidation walls, snapshot age, evidence labels and a public record. Managed OAuth.
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.
Token due-diligence tools for any MCP-capable agent: ask "should I touch this token" and get a letter grade with a reason instead of a price chart. Zero dependencies, stdio transport, no install step.
npx -y onchain-forensics-mcp
Published on npm as onchain-forensics-mcp. If the registry is unreachable, the same code installs straight from GitHub: npx -y github:leohoudinisanders-byte/forensics-mcp.
| Tool | Question it answers | Price |
|---|---|---|
token_verdict | Should I touch this token? Grade A-F, verdict tier, activity score, one-line roast. | free trial, then $0.001 |
token_mints | Is this token being printed? Mint events, minted amount, mint authority, exact window. | free trial, then $0.02 |
settlesafe_check | Can this token actually settle? Registry canonicality, ERC-20 readability, pause state. | free trial, then $0.02 |
token_profile | Full readable profile: supply, decimals, holders, top wallets. | free trial, then $0.05 |
wallet_profile | Is this wallet real, and what does it hold? | free trial, then $0.05 |
forensics_catalog | What else can this server answer, and what does it cost? Free, no network call. | free |
Grades are computed by deterministic rules over live chain reads. No LLM sits in the decision path, so the same token grades the same way twice.
Claude Desktop (~/Library/Application Support/Claude/claude_desktop_config.json):
{
"mcpServers": { "onchain-forensics": { "command": "npx", "args": ["-y", "onchain-forensics-mcp"] } } }
Claude Code:
claude mcp add onchain-forensics -- npx -y onchain-forensics-mcp
Cursor (.cursor/mcp.json) and any other client use the same command + args pair.
LangChain / Vercel AI SDK / custom runtimes: the server speaks newline-delimited JSON-RPC 2.0 on stdio, so it drops into any MCP client implementation. Methods implemented: initialize, tools/list, tools/call, ping.
curl -X POST https://api.onchainforensics.dev/functions/devKeys \
-H "Content-Type: application/json" -d '{"email":"you@example.com"}'
The response contains a key shown once. Set it and every tool call becomes a plain data read with no payment signature:
{
"mcpServers": { "onchain-forensics": { "command": "npx", "args": ["-y", "onchain-forensics-mcp"], "env": { "FORENSICS_DEV_KEY": "fxk_..." } } } }
Every tool calls the free trial tier first. When that route's daily allowance is spent, the paid endpoint answers HTTP 402 and the tool returns the decoded x402 challenge (price, USDC asset, payTo, network) rather than an error, so an agent that can sign a payment proceeds and an agent that cannot still learns the exact cost.
https://api.onchainforensics.dev/functions/ POST /functions/forensicsCredits {"plan":"pack1"}| Variable | Default |
|---|---|
FORENSICS_BASE_URL | https://api.onchainforensics.dev/functions |
FORENSICS_CHAIN | base |
FORENSICS_TIMEOUT_MS | 45000 |
FORENSICS_DEV_KEY | empty (falls back to free trial, then the x402 challenge) |
MIT