# Kawal (remote · kawal-three.vercel.app)

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

- Trust score: 85/100 (high trust)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-21

## Components

- remote · `kawal-three.vercel.app`: 85/100 (this document), [markdown](https://verifymcp.io/servers/pugarhuda-kawal/api-mcp.md), [page](https://verifymcp.io/servers/pugarhuda-kawal/api-mcp)

## Channel facts

- Endpoint: `https://kawal-three.vercel.app/api/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.1.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-09-21.

- **Endpoint Security**: 80/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 84/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1627 tokens (~135/item across 12 items; 9 tools + 3 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 70/100
  - Stability observed for 21 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 9 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 11 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the Kawal MCP server?

Kawal is a hosted endpoint at https://kawal-three.vercel.app/api/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http pugarhuda-kawal 'https://kawal-three.vercel.app/api/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "pugarhuda-kawal": {
      "url": "https://kawal-three.vercel.app/api/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "pugarhuda-kawal": {
      "type": "http",
      "url": "https://kawal-three.vercel.app/api/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.pugarhuda-kawal]
url = "https://kawal-three.vercel.app/api/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "pugarhuda-kawal": {
      "type": "remote",
      "url": "https://kawal-three.vercel.app/api/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add pugarhuda-kawal --url 'https://kawal-three.vercel.app/api/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  pugarhuda-kawal:
    url: "https://kawal-three.vercel.app/api/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "pugarhuda-kawal": {
      "Transport": "http",
      "Url": "https://kawal-three.vercel.app/api/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add pugarhuda-kawal -t streamable-http -u 'https://kawal-three.vercel.app/api/mcp'
```

### Other

```json
{
  "mcpServers": {
    "pugarhuda-kawal": {
      "type": "http",
      "url": "https://kawal-three.vercel.app/api/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-09-20 (score 85, +1)

No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-18 (score 84, +1)

No change was recorded against any check on this day. Stability & Change Management went from 57 to 60. That category is still filling its 30-day observation window: 17 days of observed history at the previous scan, 18 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-16 (score 83, +1)

No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-14 (score 82, +1)

No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-12 (score 81, +1)

No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-10 (score 80, +1)

No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-08 (score 79, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-05 (score 78, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (9)

### `verify_agent` (~118 tokens)

Verify an agent by calling it

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.

Input parameters:

- `chainId` (number): Chain id. One of 56, 97. Defaults to 56.
- `tokenId` (string, required): ERC-8004 token id, decimal digits.

### `check_payment` (~117 tokens)

Ask whether an agent really charges

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.

Input parameters:

- `chainId` (number): Chain id. One of 56, 97. Defaults to 56.
- `tokenId` (string, required): ERC-8004 token id, decimal digits.

### `read_reputation` (~135 tokens)

Who wrote an agent's feedback

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.

Input parameters:

- `chainId` (number): Chain id. One of 56, 97. Defaults to 56.
- `tokenId` (string, required): ERC-8004 token id, decimal digits.

### `find_agents` (~217 tokens)

Search the roster by problem

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.

Input parameters:

- `chainId` (number): Chain id. One of 56, 97. Defaults to 56.
- `limit` (number): How many to return, at most 20.
- `query` (string): What you need done, in plain words. Optional when `trending` is given; then it filters the trending list by name or description.
- `trending` (string): Return 8004scan's trending agents for this window instead of a search, in the registry's order.

### `agents_by_owner` (~146 tokens)

Every agent an address minted, called now

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.

Input parameters:

- `chainId` (number): Chain id. One of 56, 97. Defaults to 56.
- `owner` (string, required): The wallet that minted the registrations: 0x followed by forty hex characters. `address` is accepted as an alias.

### `compare_agents` (~120 tokens)

The same questions of two or three 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.

Input parameters:

- `agents` (array, required): One to 3 agents to compare.

### `uptime_history` (~123 tokens)

Every probe Kawal has made of an agent

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.

Input parameters:

- `chainId` (number): Chain id. One of 56, 97. Defaults to 56.
- `tokenId` (string, required): ERC-8004 token id, decimal digits.

### `plan_mandate` (~175 tokens)

Plan four bounded seats for a capital amount

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.

Input parameters:

- `capitalUsdt` (number, required): Capital to entrust, in USDT. Positive, at most 1000000000000.
- `chainId` (number): Chain id. One of 56, 97. Defaults to 56.
- `days` (integer, required): How long the mandate runs, in whole days. 1 to 365.

### `deep_report` (~202 tokens)

Everything Kawal holds about one agent (paid)

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.

Input parameters:

- `chainId` (number): Chain id. One of 56, 97. Defaults to 56.
- `tokenId` (string, required): ERC-8004 token id, decimal digits.
- `txHash` (string): Hash of the BNB transfer that paid the terms: 0x followed by 64 hex characters. Omit to receive the terms.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/pugarhuda-kawal/api-mcp#diagnostics

## Score history

- 2026-09-21: 85
- 2026-09-20: 85
- 2026-09-19: 84
- 2026-09-18: 84
- 2026-09-17: 83
- 2026-09-16: 83
- 2026-09-15: 82
- 2026-09-14: 82
- 2026-09-13: 81
- 2026-09-12: 81
- 2026-09-11: 80
- 2026-09-10: 80
- 2026-09-09: 79
- 2026-09-08: 79
- 2026-09-07: 78
- 2026-09-06: 78
- 2026-09-05: 78
- 2026-09-04: 77
- 2026-09-03: 77
- 2026-09-02: 76
- 2026-09-01: 76
- 2026-08-31: 75

## Common questions

### What is the Kawal MCP server?

Kawal is an MCP server listed in the public MCP registry as io.github.PugarHuda/kawal. Evidence about ERC-8004 agents on BNB Smart Chain, gathered by calling them. No key. This page covers its hosted endpoint (https://kawal-three.vercel.app/api/mcp).

### Is the Kawal MCP server safe to use?

Kawal scores 85 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Kawal MCP server expose?

Kawal exposes 9 tools: verify_agent, check_payment, read_reputation, find_agents, agents_by_owner, and 4 more. Their descriptions and schemas cost roughly 1,353 tokens of context every time the server is loaded.

### Does the Kawal MCP server require authentication?

No. We connected to Kawal without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Kawal MCP server still maintained?

Kawal is still listed as active in the MCP registry. We last reached this channel on 21 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://kawal-three.vercel.app/api/mcp
- Website: https://kawal-three.vercel.app/
- Changelog RSS feed: https://verifymcp.io/servers/pugarhuda-kawal/api-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/pugarhuda-kawal/api-mcp.json
- HTML version of this page: https://verifymcp.io/servers/pugarhuda-kawal/api-mcp