Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
Check a Base or BNB Chain address before you pay it: on-chain risk reports, EAS attestations.
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": {
"chainward": {
"command": "npx",
"args": [
"-y",
"chainward-mcp-server"
]
}
}
}Run this in your terminal
claude mcp add chainward -- npx -y chainward-mcp-serverPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"chainward": {
"command": "npx",
"args": [
"-y",
"chainward-mcp-server"
]
}
}
}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": {
"chainward": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"chainward-mcp-server"
]
}
}
}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 registry name was verified with the GitHub account saltxd, which owns the repo
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 1 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 (0.2.3) reached the registry 26 days ago.
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, LexPact UK Contracts
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.
Generate UK-law contracts: NDA, service, freelance, recruiter terms of business, IR35.
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.
Model Context Protocol server for ChainWard: check an address on Base or BNB Chain before you pay it, and query ChainWard's intelligence on AI-agent wallets on Base.
ChainWard labels AI-agent wallets, tracks their on-chain activity in real time, and publishes investigative Decodes. This package lets any MCP-compatible assistant (Claude Desktop, Cursor, Claude Code, Codex, ChatGPT) query that intelligence in plain language, without leaving the chat.
This is the standalone distribution path. It works alongside Base MCP (which handles signing) but does not depend on Base MCP's web_request allowlist.
| Tool | Purpose |
|---|---|
check_counterparty | Before paying 0x…: ChainWard's verdict (label pay / hold / unknown, shown as Pay, Hold, Inactive, No track record or Couldn't check) with the one reason, the flags behind it, and the EAS attestation on Base (uid + explorer link) when one exists. Optional chain: base (default) or bsc for a BNB Chain address (since 0.2.3; BNB Chain reports are not attested yet). On-chain behavior only; Pay isn't a guarantee. |
rug_check | Before buying a Base token: ChainWard's rug check (hold / review / no_flags) with the one reason and the launch facts: who launched it, whether that wallet sent out its launch tokens, later mints, and the launch wallet's sanctions status, age and first funder. Free up to 20 fresh checks an hour; the paid route for volume is GET https://api.chainward.ai/api/risk/rugcheck?address=0x… ($0.02 over x402). Hold when the launch wallet pulled the liquidity it added. No honeypot or sell simulation; no flags isn't a guarantee. Since 0.3.0. |
lookup_agent | Is 0x… a known AI agent? Returns label + Decode pointers. Cheap. |
get_agent_profile | Full profile: 7d balance, 30d gas, recent 20 txs, related Decodes. |
get_agent_economics | Lifetime ACP revenue, jobs and success rate, plus the last 30 days on-chain: revenue received, gas, profit (30-day revenue minus 30-day gas) and gas efficiency. |
get_observatory_overview | Ecosystem-wide stats. |
get_top_agents | Leaderboard by activity. |
get_activity_feed | Recent labeled-agent activity. |
list_decodes | Every published Decode, newest first. |
find_decodes_for_address | All Decodes referencing a specific address. |
All tools default to ChainWard's public endpoints (no auth). Setting CHAINWARD_API_KEY enables future authenticated tools.
// claude_desktop_config.json or .cursor/mcp.json
{ "mcpServers": { "chainward": { "command": "npx", "args": ["-y", "chainward-mcp-server"], "env": { "CHAINWARD_API_URL": "https://api.chainward.ai" } } } }
CHAINWARD_MCP_TRANSPORT=http PORT=3300 npx -y chainward-mcp-server
Then point your client at http://your-host:3300/mcp.
We run one, so you do not have to:
https://api.chainward.ai/mcp
Same tools, no API key, nothing to install. It speaks Streamable HTTP, so the request needs Accept: application/json, text/event-stream; a plain GET in a browser answers 406 and that is correct, not an outage.
Run the package yourself instead when you want to pin a version, keep traffic inside your own network, or point it at a different CHAINWARD_API_URL.
| Var | Default | Description |
|---|---|---|
CHAINWARD_MCP_TRANSPORT | stdio | stdio or http |
PORT | 3300 | HTTP transport listen port |
CHAINWARD_API_URL | https://api.chainward.ai | API base URL |
CHAINWARD_API_KEY | _(none)_ | Optional ag_… Bearer key |
This server is read-only. To act on what you learn (swap, lend, etc.), install Base MCP alongside this server. Recommended assistant prompt pattern:
Before paying or transacting with any unfamiliar address, call ChainWard's
check_counterparty(andlookup_agentfor agents). Before buying a token, callrug_check. If a Decode exists, summarise it for the user before invoking any Base MCP plugin.
MIT