# presign-guard (remote · presign-guard.fizzl.eu)

Pre-sign, token and approval checks for agents: green/orange/red for signatures, tokens, wallets.

- Trust score: 66/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-29

## Components

- remote · `presign-guard.fizzl.eu`: 66/100 (this document), [markdown](https://verifymcp.io/servers/fizzl13-presign-guard/presign-guard-2.md), [page](https://verifymcp.io/servers/fizzl13-presign-guard/presign-guard-2)

## Channel facts

- Endpoint: `https://presign-guard.fizzl.eu/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.2.1`

## 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 2026-09-29.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 1 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - 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**: 66/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1580 tokens (~225/item across 7 items; 7 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 3/100
  - Stability observed for 1 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 7 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 7 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the presign-guard MCP server?

presign-guard is a hosted endpoint at https://presign-guard.fizzl.eu/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 fizzl13-presign-guard 'https://presign-guard.fizzl.eu/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "fizzl13-presign-guard": {
      "url": "https://presign-guard.fizzl.eu/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "fizzl13-presign-guard": {
      "type": "http",
      "url": "https://presign-guard.fizzl.eu/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.fizzl13-presign-guard]
url = "https://presign-guard.fizzl.eu/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "fizzl13-presign-guard": {
      "type": "remote",
      "url": "https://presign-guard.fizzl.eu/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add fizzl13-presign-guard --url 'https://presign-guard.fizzl.eu/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  fizzl13-presign-guard:
    url: "https://presign-guard.fizzl.eu/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "fizzl13-presign-guard": {
      "Transport": "http",
      "Url": "https://presign-guard.fizzl.eu/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add fizzl13-presign-guard -t streamable-http -u 'https://presign-guard.fizzl.eu/mcp'
```

### Other

```json
{
  "mcpServers": {
    "fizzl13-presign-guard": {
      "type": "http",
      "url": "https://presign-guard.fizzl.eu/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.

### 2026-09-29 (score 66, −6)

- [security regression] Authorization: partial → unverified
- [functional improvement] Stability: unverified → 0.03
- [functional] New tool “feedback”

### 2026-09-28 (score 72)

First indexed and scored.

## MCP tools (7)

### `presign_quick_check` (~276 tokens)

Quick pre-sign verdict (free)

Free: the green/orange/red verdict only, for a transaction, token approval or EIP-712 signature your agent is about to sign. Limited to 10 calls per hour. For the reason codes and details use presign_check ($0.01); for a plain-language explanation presign_check_explain ($0.03).

Input parameters:

- `amount` (string): approval: amount in base units (0 = revoke)
- `chainId` (integer, required): EVM chain id: 1, 10, 56, 137, 8453, 42161 (8453 = Base)
- `data` (string): transaction: 0x-prefixed calldata
- `origin` (string): optional: the site asking for the signature or transaction (URL or hostname); a domain under 30 days old is orange
- `spender` (string): approval: who gets the allowance
- `to` (string): transaction: the target contract
- `token` (string): approval: the token contract
- `type` (string, required): What the agent is about to sign
- `typedData`: signature: the exact eth_signTypedData_v4 payload (Permit, Permit2, EIP-3009 x402 payment, Seaport)
- `value` (string): transaction: native value in wei

### `token_quick_verdict` (~113 tokens)

Quick token verdict (free)

Free: the green/orange/red verdict and grade only, for a Solana or EVM token your agent is about to buy, hold or accept. Limited to 10 free calls per hour (shared with presign_quick_check). For the reasons, one-line summary and market data use token_verdict ($0.01).

Input parameters:

- `address` (string, required): Solana mint address (base58) or EVM token contract (0x...)
- `chain` (string, required): Chain the token lives on

### `presign_check` (~366 tokens)

Pre-sign risk check ($0.01 via x402)

Paid ($0.01 USDC via x402 on Base): call this before you sign. Send the transaction, token approval or EIP-712 signature (Permit, Permit2, EIP-3009 x402 payment, Seaport) your agent is about to sign; get back green, orange or red with reason codes: who gets access, whether the spender or recipient is flagged, sanctioned (OFAC SDN) or unverified, unlimited allowances, and the token itself (honeypot, fake look-alike, high tax). Only proceed on green; on orange ask your user; never sign on red. Same as POST /v1/check. The answer carries a signed receipt (EIP-191, bound to your arguments) that proves later which verdict you got.

Input parameters:

- `amount` (string): approval: amount in base units (0 = revoke)
- `chainId` (integer, required): EVM chain id: 1, 10, 56, 137, 8453, 42161 (8453 = Base)
- `data` (string): transaction: 0x-prefixed calldata
- `origin` (string): optional: the site asking for the signature or transaction (URL or hostname); a domain under 30 days old is orange
- `spender` (string): approval: who gets the allowance
- `to` (string): transaction: the target contract
- `token` (string): approval: the token contract
- `type` (string, required): What the agent is about to sign
- `typedData`: signature: the exact eth_signTypedData_v4 payload (Permit, Permit2, EIP-3009 x402 payment, Seaport)
- `value` (string): transaction: native value in wei

### `presign_check_explain` (~305 tokens)

Pre-sign risk check with explanation ($0.03 via x402)

Paid ($0.03 USDC via x402 on Base): the same verdict and reason codes as presign_check, plus a 3 to 5 sentence plain-language explanation a person can read before approving (lang en or nl). Same as POST /v1/check/explain. The answer carries a signed receipt (EIP-191, bound to your arguments) that proves later which verdict you got.

Input parameters:

- `amount` (string): approval: amount in base units (0 = revoke)
- `chainId` (integer, required): EVM chain id: 1, 10, 56, 137, 8453, 42161 (8453 = Base)
- `data` (string): transaction: 0x-prefixed calldata
- `lang` (string): Language of the explanation (default en)
- `origin` (string): optional: the site asking for the signature or transaction (URL or hostname); a domain under 30 days old is orange
- `spender` (string): approval: who gets the allowance
- `to` (string): transaction: the target contract
- `token` (string): approval: the token contract
- `type` (string, required): What the agent is about to sign
- `typedData`: signature: the exact eth_signTypedData_v4 payload (Permit, Permit2, EIP-3009 x402 payment, Seaport)
- `value` (string): transaction: native value in wei

### `token_verdict` (~213 tokens)

Token verdict ($0.01 via x402)

Paid ($0.01 USDC via x402 on Base or Solana): call this before your agent buys, holds or accepts a token. Send the chain (solana, base, ethereum, arbitrum, optimism, polygon, bsc) and the token address or mint; get back green/orange/red, a grade (SAFE, CAUTION, RISKY, AVOID), reason codes (mint or freeze authority still active, honeypot, tax or transfer fee, LP not locked, low liquidity, new token, concentrated holders, rugged), a one-line summary, and market data (price, liquidity, market cap, 24h volume, age). Same as GET /v1/token. The answer carries a signed receipt (EIP-191, bound to your arguments) that proves later which verdict you got.

Input parameters:

- `address` (string, required): Solana mint address (base58) or EVM token contract (0x...)
- `chain` (string, required): Chain the token lives on

### `wallet_approvals` (~198 tokens)

Wallet approval audit ($0.02 via x402)

Paid ($0.02 USDC via x402 on Base or Solana): audit the open token approvals of an EVM wallet (base, ethereum, arbitrum, optimism, polygon, bsc), for example your agent's own wallet as a periodic check. Get back green/orange/red, a grade, a one-line summary and every ERC-20 allowance with its spender: flagged malicious (red), a plain wallet, on a doubt list, an unverified contract or an unlimited allowance to a spender not on the GoPlus trust list (orange), plus which ones to revoke and a revoke.cash link. NFT approvals are not covered. Same as GET /v1/approvals. The answer carries a signed receipt (EIP-191, bound to your arguments) that proves later which verdict you got.

Input parameters:

- `address` (string, required): Wallet address (0x...)
- `chain` (string, required): EVM chain to audit

### `feedback` (~109 tokens)

Send feedback (free)

Report a bug, a missing feature or anything else about this service, in a structured way. Free. A person reads every report; nothing is run or changed automatically.

Input parameters:

- `contact` (string): Optional: how to reach you about it
- `endpoint` (string): Optional: the route or tool it is about, e.g. /v1/token
- `message` (string, required): What happened or what you need
- `type` (string): bug, feature (something missing) or other

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/fizzl13-presign-guard/presign-guard-2#diagnostics

## Score history

- 2026-09-29: 66
- 2026-09-28: 72

## Common questions

### What is the presign-guard MCP server?

presign-guard is an MCP server listed in the public MCP registry as io.github.Fizzl13/presign-guard. Pre-sign, token and approval checks for agents: green/orange/red for signatures, tokens, wallets. This page covers its hosted endpoint (https://presign-guard.fizzl.eu/mcp).

### Is the presign-guard MCP server safe to use?

presign-guard scores 66 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 presign-guard MCP server expose?

presign-guard exposes 7 tools: presign_quick_check, token_quick_verdict, presign_check, presign_check_explain, token_verdict, and 2 more. Their descriptions and schemas cost roughly 1,580 tokens of context every time the server is loaded.

### Does the presign-guard MCP server require authentication?

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

### Is the presign-guard MCP server still maintained?

presign-guard is still listed as active in the MCP registry. We last reached this channel on 29 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://presign-guard.fizzl.eu/mcp
- Repository: https://github.com/Fizzl13/presign-guard
- Website: https://presign-guard.fizzl.eu/
- Changelog RSS feed: https://verifymcp.io/servers/fizzl13-presign-guard/presign-guard-2.xml
- Changelog JSON feed: https://verifymcp.io/servers/fizzl13-presign-guard/presign-guard-2.json
- HTML version of this page: https://verifymcp.io/servers/fizzl13-presign-guard/presign-guard-2