Kawal is listed as active in the registry but did not answer our last check. It exposes 9 tools.
Evidence about ERC-8004 agents on BNB Smart Chain, gathered by calling them. No key.
Uptime history
64 days of history · worst day 0%
64 days agonow
3.3%
Uptime 24h
3 of 91 checks
9
Tools
read from the server
1538 ms
Response time
average over 24h
open, no key
Access
streamable-http
Kawal does not always answer
Over the last week it answered 5.0% of our checks. We check every 15 minutes, so you hear about the next outage within the hour — not from your users.
Connect this server
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 7 min ago.
run in your terminal
claude mcp add kawal --transport http https://kawal-three.vercel.app/api/mcpSettings → Connectors → Add custom connector, then paste this address
https://kawal-three.vercel.app/api/mcp~/.codex/config.toml
[mcp_servers.kawal]
url = "https://kawal-three.vercel.app/api/mcp".cursor/mcp.json
{
"mcpServers": {
"kawal": {
"url": "https://kawal-three.vercel.app/api/mcp"
}
}
}.vscode/mcp.json
{
"servers": {
"kawal": {
"type": "http",
"url": "https://kawal-three.vercel.app/api/mcp"
}
}
}Available tools 9
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
agents
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?": what answered, how each failure looks, and every probe Kawal kept. At most 12 agents are dialled, so a large owner sees the first page.
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 template, and returning all of them would be returning the same agent many times. With `trending`, the list is instead what 8004scan's visitors looked at most over that window — attention, not evidence — each entry carrying the tier Kawal's own record gives it, which is where the two disagree.
compare
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 costs, does its domain verify, what is its track record, what is flagged against it, and when it was registered. Each agent is dialled for this call. No combined score: the disagreements are the point.
deep
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 of 200 BSC registrations declare x402 support and that none of the reachable ones ever asks to be paid; this is the counter-example. Calling it without payment returns the terms rather than the report. Pay the terms with a plain BNB transfer and call again with `txHash`; the receipt is read on-chain and spent once.
payment
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 never settles a payment, so the price is quoted in the server's own words and nothing moves.
plan
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 same plan the mandate form shows, and the same refusals, since a plan that would widen authority (an unproven venue, an empty allowlist, caps that overcommit) is refused rather than built.
reputation
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. Returns how many carry a mark, how many distinct addresses wrote them, and what share came from the busiest one.
uptime
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 record the registry does not have. Null when Kawal has never called this endpoint; verify_agent makes the first call.
verify
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. Returns the hireability tier and the evidence behind it, including how many times Kawal has reached this endpoint before.
Endpoints
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://kawal-three.vercel.app/api/mcp | streamable-http | answering | 47 ms | 7 min ago |
Alternatives to Kawal
same job, measured the same wayAgent Evidence API
by thx93
Cited web evidence and fact checking for AI agents. $0.01 per call, no API key.
Priors (hosted, read-only)
by priors-agents
Credit records and scores of ERC-8004 AI agents on Robinhood Chain, from Priors. No key needed.
Tracea
by chriscorp
Tracea — legal identity (Know Your Agent) for AI agents, on-chain. ERC-8004 compatible.
D
DidWork
by didwork
Verify that an agent's claimed outcome actually happened, using independently gathered evidence
AIDEN
by aiden
Look up AI agents on Robinhood Chain: ERC-8004 identity, feedback and USDG-backed trust scores.
Agent Erc8004 Bridge
by jdhart81
The MCP-native bridge to ERC-8004 (on-chain agent identity/reputation/validation): resolve registrat
App Pain API
by apppainapi
What users hate about ANY iOS/Android app: clustered complaints, evidence, trends. No key needed.
GAIP — evidence on AI agents before and after you call them
by tjcgraham-rgb
GAIP keeps an independent, dated record of what AI agents, MCP servers and online shops publish.
Kawal — questions
Answers built from our own checks of this server.
What can Kawal do?
It exposes 9 tools, read directly from the server on our last check. Among them: agents_by_owner, check_payment, compare_agents, deep_report, find_agents, plan_mandate and 3 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README.
How MCP servers expose tools in the first place →
Is Kawal working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 3 of 91 checks got a reply (3.3%), average response time 1538 ms. The bar chart above shows every period we have measured.
The registry lists Kawal as active — why does it not respond?
The official MCP registry stores what the author submitted; it does not verify that the server still runs. We check the endpoint ourselves, and this one does not answer. Catalogues that copy the registry without checking will show it as working.
How do I connect Kawal?
Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does Kawal need an API key?
No. Kawal completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 9 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is Kawal?
It answers our handshake in 1538 ms on average, which is faster than 1% of all working MCP servers we measure. That is on the slow side — worth knowing if the tool sits inside an interactive loop. The comparison comes from our own checks across the whole registry, every 15 minutes.