# Prescan (remote · prescan.canisell.xyz)

Agent security pre-checks: prompt-injection scan, MCP tool-poisoning scan, x402 endpoint check.

- Trust score: 66/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `prescan.canisell.xyz`: 66/100 (this document), [markdown](https://verifymcp.io/servers/xyz-canisell-prescan/prescan.md), [page](https://verifymcp.io/servers/xyz-canisell-prescan/prescan)

## Channel facts

- Endpoint: `https://prescan.canisell.xyz/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 2026-11-05.

- **Endpoint Security**: 63/100
  - 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 check failed: the endpoint is reachable over plaintext HTTP.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - 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**: 63/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1044 tokens (~174/item across 6 items; 6 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 10/100
  - Stability observed for 3 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 6 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 Prescan MCP server?

Prescan is a hosted endpoint at https://prescan.canisell.xyz/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 xyz-canisell-prescan 'https://prescan.canisell.xyz/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "xyz-canisell-prescan": {
      "url": "https://prescan.canisell.xyz/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "xyz-canisell-prescan": {
      "type": "http",
      "url": "https://prescan.canisell.xyz/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.xyz-canisell-prescan]
url = "https://prescan.canisell.xyz/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "xyz-canisell-prescan": {
      "type": "remote",
      "url": "https://prescan.canisell.xyz/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add xyz-canisell-prescan --url 'https://prescan.canisell.xyz/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  xyz-canisell-prescan:
    url: "https://prescan.canisell.xyz/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "xyz-canisell-prescan": {
      "Transport": "http",
      "Url": "https://prescan.canisell.xyz/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add xyz-canisell-prescan -t streamable-http -u 'https://prescan.canisell.xyz/mcp'
```

### Other

```json
{
  "mcpServers": {
    "xyz-canisell-prescan": {
      "type": "http",
      "url": "https://prescan.canisell.xyz/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.

### 2026-11-04 (score 66, +1)

- [security] The server rewrote its instructions, which are the text every model session reads

### 2026-11-03 (score 65, +1)

- [functional improvement] Stability: unverified → 0.03

### 2026-11-02 (score 64)

First indexed and scored.

## MCP tools (6)

### `scan_text` (~379 tokens)

Scan text for prompt injection (paid)

Prompt-injection pre-check for text your agent is about to read (tool output, web page, email, document, token names/metadata). Deterministic rules, no LLM: instruction override (EN/DE/FR/ES/IT/PT/PL/RU), role hijack, jailbreaks, system-prompt extraction, fake chat delimiters, text addressed to the AI, concealment, data exfiltration (markdown-image beacons, secrets to URLs), tool/fund hijack (shell pipes, transfers, unlimited approvals, skip-confirmation), crypto lures (seed-phrase requests, claim/airdrop links), hidden text (zero-width, Unicode tag and variation-selector smuggling, bidi, homoglyphs, CSS-hidden HTML, ANSI) and encoded payloads (base64/hex/percent decoded and re-scanned). Returns verdict safe/suspicious/malicious, action allow/treat_as_untrusted_data/block, 0-100 score, findings with character spans, risky links, decoded payloads and a sanitized copy. Batch up to 100 texts per call. Costs $0.002 USDC per call via x402 (charged only on success). Without an x402 wallet you get the payment terms and the paid HTTP URL instead.

Input parameters:

- `items` (array): Batch: up to 100 texts (e.g. token names, search results, emails), 200000 characters in total, one price.
- `sanitize` (boolean): Return `sanitized`: the text with invisible characters removed and injected instructions replaced by a marker. Default true.
- `source` (string): Where the text comes from; tunes a few rules (token_metadata flags any URL in a token name).
- `text` (string): Text to scan, up to 100000 characters. Use either text or items.

### `scan_tools` (~182 tokens)

Scan MCP tool definitions for tool poisoning (paid)

Tool-poisoning scan of MCP tool definitions (a tools/list result) or function schemas before your agent connects or calls them: hidden <IMPORTANT> instructions, cross-tool shadowing, side-channel parameters that ask for file/conversation contents, recipient/payee overrides, instructions hidden in parameter names, defaults or enums, Unicode/ANSI smuggling, duplicate or lookalike tool names. Per-tool verdict and findings with location, plus capability flags (shell, files, network, payments, messaging). Costs $0.002 USDC per call via x402 (charged only on success). Without an x402 wallet you get the payment terms and the paid HTTP URL instead.

Input parameters:

- `server` (object): Optional label echoed back.
- `tools` (array, required): Tool definitions as returned by MCP tools/list (or OpenAI/Anthropic function schemas), up to 200.

### `check_x402_endpoint` (~244 tokens)

Check an x402 endpoint before paying (paid)

Is this x402 endpoint safe to pay? Fetches its 402 terms with one GET (never pays) and checks: payTo validity and EIP-55 checksum, zero/token-contract/OFAC-sanctioned payTo, asset is canonical USDC for the network, amount vs your budget, price vs the price advertised in its OpenAPI and on x402scan, payTo vs the one x402scan recorded, HTTPS, redirects, resource host, domain age (RDAP), tunnels/shared hosts. Returns go/caution/no_go, the recommended payment option and findings. Costs $0.003 USDC per call via x402 (charged only on success). Without an x402 wallet you get the payment terms and the paid HTTP URL instead.

Input parameters:

- `max_usd` (number): Your budget per call in USD; above it the verdict is no_go.
- `network` (string): Preferred network, CAIP-2 (eip155:8453) or v1 name (base).
- `url` (string, required): The x402 endpoint you are about to pay (full URL incl. query). Only GET is sent; nothing is paid.

### `about` (~28 tokens)

About Prescan (free)

Free. What Prescan does, prices of the paid tools and HTTP endpoints, and links to docs.

### `preview_scan_text` (~102 tokens)

Preview prompt-injection scan (free)

Free. Prompt-injection pre-check for up to 1000 characters: verdict (safe/suspicious/malicious), score, categories and rule ids. For spans, a sanitized copy, long texts or batches use scan_text (paid).

Input parameters:

- `source` (string): Where the text comes from; tunes a few rules (token_metadata flags any URL in a token name).
- `text` (string, required): Text to check, up to 1000 characters

### `list_rules` (~26 tokens)

Detection categories (free)

Free. The detection categories, rule counts and thresholds used by scan_text and scan_tools.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/xyz-canisell-prescan/prescan#diagnostics

## Score history

- 2026-11-05: 66
- 2026-11-04: 66
- 2026-11-03: 65
- 2026-11-02: 64

## Common questions

### What is the Prescan MCP server?

Prescan is an MCP server listed in the public MCP registry as xyz.canisell/prescan. Agent security pre-checks: prompt-injection scan, MCP tool-poisoning scan, x402 endpoint check. This page covers its hosted endpoint (https://prescan.canisell.xyz/mcp).

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

Prescan 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 Prescan MCP server expose?

Prescan exposes 6 tools: scan_text, scan_tools, check_x402_endpoint, about, preview_scan_text, list_rules. Their descriptions and schemas cost roughly 961 tokens of context every time the server is loaded.

### Does the Prescan MCP server require authentication?

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

### Is the Prescan MCP server still maintained?

Prescan is still listed as active in the MCP registry. We last reached this channel on 5 November 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://prescan.canisell.xyz/mcp
- Website: https://prescan.canisell.xyz/
- Changelog RSS feed: https://verifymcp.io/servers/xyz-canisell-prescan/prescan.xml
- Changelog JSON feed: https://verifymcp.io/servers/xyz-canisell-prescan/prescan.json
- HTML version of this page: https://verifymcp.io/servers/xyz-canisell-prescan/prescan