Skip to content
Back to search
100
MCP live MCP 2026-07-28 streamable-http

Kawal

io.github.pugarhuda/kawal

Evidence about ERC-8004 agents on BNB Smart Chain, gathered by calling them. No key.

Watch this dependency Share evidence report
Uptime
100.0%
5 direct probes · 30d
Response
2374ms
last probe
Tools
9
callable
Resources
3
readable
Prompts
1
available
Score: 100/100
Handshake verified by our own probe.
pass Answers the MCP handshake 50/50
The handshake and the list calls succeeded on the primary URL.
pass Lists tools, resources or prompts 30/30
9 tools, 3 resources, 1 prompts returned.
pass 3 or more catalogue items 10/10
13 items in total; 3 or more earns these points.
pass Describes itself 10/10
84 characters; more than 30 earns these points.

Tools · 9

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…

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;…

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 c…

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 th…

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 th…

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, …

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 lat…

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. P…

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…

Resources · 3

taxonomy

The five categories Kawal files agents under — four seats plus security — with the seat each fills, the search query that finds it and the terms that classify it. 8004scan has no category field; this …

kawal://taxonomy
venues

Every contract a seat may be allowed to call, with the chain it is proven on and what the identity call returned; and the four seat policies — cap share, period, venues, priority — that plan_mandate b…

kawal://venues
known-defects

The defects of the probing method, published with every uptime record Kawal writes into the ERC-8004 reputation registry. Read this before treating a failed probe as a verdict.

kawal://known-defects

Prompts · 1

hire_under_cap

Walk through hiring from the BSC roster the way Kawal does it: search by the problem, call the candidates, compare the evidence, read who rated them, and plan the spend cap before anything is granted.

How to use

Claude Desktop or claude.ai: add a custom connector (Customize → Connectors; on Team and Enterprise plans an owner adds it under Organization settings → Connectors) with this server URL: https://kawal-three.vercel.app/api/mcp

Cursor or Cline: add to your MCP config:

{
  "mcpServers": {
    "kawal": {
      "url": "https://kawal-three.vercel.app/api/mcp",
      "transport": "streamable-http"
    }
  }
}