Kawal is an MCP server with 9 tools an agent can call, among them agents_by_owner, check_payment, compare_agents. It answers at https://kawal-three.vercel.app/api/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 6 of 6 times since 11 September 2026; the last check, on 20 October 2026, succeeded.
Evidence about ERC-8004 agents on BNB Smart Chain, gathered by calling them. No key.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
agents_by_owner | List the agents one wallet registered on BSC and call each of their declared endpoints now. Nothing on the chain tells an owner their endpoint went dark — the registry keeps listing it — so this is the answer to "is my agent still answering Inputs: owner, chainId |
check_payment | Send the opening request of the x402 protocol — no payment header — and report whether the server actually demands payment. `x402_supported` on the registry is a flag a registration sets about itself; this is the answer to asking. Kawal nev Inputs: chainId, tokenId |
compare_agents | Put two or three agents side by side and answer the same questions of each — the ones a buyer weighs before handing over a spend cap: can it be hired, does it answer right now, has it kept answering, what does it offer, what does it say it Inputs: agents |
deep_report | Everything Kawal holds about one agent in a single answer: the live handshake, the full probe history, how the endpoint fails when it fails, whether it really charges, and who wrote its feedback. This one costs money. Kawal measured that 75 Inputs: chainId, tokenId, txHash |
find_agents | Search the BSC roster by describing the problem rather than naming a product, and get back agents ranked with Kawal's evidence attached. Duplicate registrations are collapsed: roughly two thirds of the newest registrations are copies of a t Inputs: query, trending, limit, chainId |
plan_mandate | Turn a capital amount and a duration into the four scoped sessions Kawal would grant on Altana — one per seat, each with its own contract allowlist, spend cap and expiry — without granting anything. Pure arithmetic over the venue table: the Inputs: capitalUsdt, days, chainId |
read_reputation | Report who wrote an agent's ERC-8004 feedback, not how much of it there is. A sample of 1,200 BSC records came from 53 addresses, one of which wrote 265 of the oldest 600, so a count of records is a count of writes rather than of opinions. Inputs: chainId, tokenId |
uptime_history | Read the history Kawal keeps of one agent's endpoint without dialling it: how many times it was called, how many times it answered in the protocol it declared, since when, and the median and worst latency of the answering calls. This is the Inputs: chainId, tokenId |
verify_agent | Call an agent's declared endpoint right now and report what answered. This is a live handshake made by Kawal, not a reading of the registry: an agent whose registration declares MCP but whose endpoint is gone is reported as not answering. R Inputs: chainId, tokenId |
Every block below points at https://kawal-three.vercel.app/api/mcp. Pick your client and copy.
claude mcp add --transport http kawal https://kawal-three.vercel.app/api/mcp
{
"mcpServers": {
"kawal": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://kawal-three.vercel.app/api/mcp"]
}
}
}{
"mcpServers": {
"kawal": {
"url": "https://kawal-three.vercel.app/api/mcp"
}
}
}{
"servers": {
"kawal": {
"type": "http",
"url": "https://kawal-three.vercel.app/api/mcp"
}
}
}{
"context_servers": {
"kawal": {
"url": "https://kawal-three.vercel.app/api/mcp"
}
}
}{
"mcpServers": {
"kawal": {
"serverUrl": "https://kawal-three.vercel.app/api/mcp"
}
}
}{
"mcpServers": {
"kawal": {
"url": "https://kawal-three.vercel.app/api/mcp"
}
}
}name: Kawal
version: 0.0.1
schema: v1
mcpServers:
- name: Kawal
type: streamable-http
url: https://kawal-three.vercel.app/api/mcp{
"mcpServers": {
"kawal": {
"httpUrl": "https://kawal-three.vercel.app/api/mcp"
}
}
}{
"mcpServers": {
"kawal": {
"type": "http",
"url": "https://kawal-three.vercel.app/api/mcp"
}
}
}{
"mcpServers": {
"kawal": {
"url": "https://kawal-three.vercel.app/api/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fkawal-three.vercel.app%2Fapi%2Fmcp&type=streamable_http&id=kawal&name=Kawal
It answered our last check on 20 October 2026 in 961 ms. Over 6 checks since 11 September 2026 it answered 6. Status here comes from Neuronto's own probes, not from the publisher.
9, as returned by the server's own tools/list on 12 September 2026: agents_by_owner, check_payment, compare_agents, deep_report, find_agents, plan_mandate, read_reputation, uptime_history, and 1 more.
It answered our last check on 20 October 2026 in 961 ms. Over 6 checks since 11 September 2026 it answered 6.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://kawal-three.vercel.app/api/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: io.github.pugarhuda. Endpoint host: kawal-three.vercel.app. ARD identifier: urn:air:io.github.pugarhuda:mcp:kawal.
First indexed 10 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.