# Frogeye Security Scanner (remote · mcp.frogeye.ai)

Zero-config MCP security scanner for AI-generated apps. 25K+ vulnerability patterns.

- Trust score: 66/100 (medium)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `mcp.frogeye.ai`: 66/100 (this document), [markdown](https://verifymcp.io/servers/frogeye-ai-mcp/mcp.md), [page](https://verifymcp.io/servers/frogeye-ai-mcp/mcp)
- remote · `mcp.frogeye.ai`: 31/100, [markdown](https://verifymcp.io/servers/frogeye-ai-mcp/mcp-2.md), [page](https://verifymcp.io/servers/frogeye-ai-mcp/mcp-2)

## Channel facts

- Endpoint: `https://mcp.frogeye.ai/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.5.18`

## 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 2026-08-03.

- **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 7 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**: 74/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 783 tokens (~111/item across 7 items; 7 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 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.
- **Capabilities**: 40/100
  - Spec-recency check failed: implements MCP spec 2025-03-26; the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http frogeye-ai-mcp https://mcp.frogeye.ai/mcp
```

### Codex

```toml
[mcp_servers.frogeye-ai-mcp]
url = "https://mcp.frogeye.ai/mcp"
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add frogeye-ai-mcp --url https://mcp.frogeye.ai/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  frogeye-ai-mcp:
    url: "https://mcp.frogeye.ai/mcp"
```

### Other

```json
{
  "mcpServers": {
    "frogeye-ai-mcp": {
      "type": "http",
      "url": "https://mcp.frogeye.ai/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.

### 2026-08-03 (score 66, +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.

### 2026-07-31 (score 65, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 64, 0)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-29 (score 64, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-28 (score 63, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-27 (score 62, 0)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-26 (score 62)

First indexed and scored.

## MCP tools (7)

### `frogeye_search` (~181 tokens)

Search the Frogeye vulnerability knowledge graph for patterns similar to the given code snippet. Returns the top 10 matching vulnerability patterns with severity, class, and fix suggestions.

Input parameters:

- `context` (string): Optional additional context about where this pattern appears (e.g. "auth middleware", "payment handler").
- `filename` (string): Optional filename or path of the file being scanned (e.g. ".env.example", "config/secrets.template"). Used to detect placeholder files that should not be flagged.
- `language` (string, required): Programming language or framework (e.g. "javascript", "python", "solidity", "react").
- `pattern` (string): Alias for query — accepted for backwards compatibility.
- `query` (string): The code pattern, snippet, or vulnerability description to search for. Canonical field name (also accepted: pattern).

### `frogeye_post` (~105 tokens)

Submit a new vulnerability pattern to the Frogeye knowledge graph. The pattern will be anonymized and queued for human review before being published.

Input parameters:

- `context` (string): Optional context about the vulnerability (how it was found, impact, etc.).
- `language` (string, required): Programming language or framework where this vulnerability was found.
- `pattern` (string, required): The vulnerable code pattern or description. Minimum 10 characters.
- `severity` (string, required): Severity classification of the vulnerability.

### `frogeye_register` (~51 tokens)

Claim a username for this agent. Idempotent — safe to call multiple times.

Input parameters:

- `username` (string, required): Your agent username (3-32 chars, lowercase alphanumeric and hyphens only).

### `frogeye_scan` (~178 tokens)

Scan a code snippet for security vulnerabilities against 24,000+ patterns. Pass your code snippet directly via the content parameter. The hosted Frogeye server cannot access your local filesystem — Claude Code should read the file content and pass it here.

Input parameters:

- `content` (string): Direct code content to scan. This is the recommended parameter for the hosted Frogeye server.
- `file_path` (string): Absolute path to the file to scan. Use content instead when running against the hosted server.
- `language` (string): Programming language hint. Auto-detected from file extension.
- `owner` (string): GitHub repo owner (optional) — used to record scan in the Frogeye verify database
- `repo` (string): GitHub repo name (optional) — used to record scan in the Frogeye verify database

### `frogeye_learn` (~99 tokens)

Teach Frogeye a team-specific security rule. Writes a private, team-scoped pattern to your KB — visible only when searching with your API key. Requires authentication.

Input parameters:

- `example` (string, required): Code example of the bad pattern.
- `finding` (string, required): Description of the vulnerability or security rule.
- `fix` (string): How to fix or avoid the vulnerability. Optional but recommended.
- `severity` (string, required): Severity classification.

### `frogeye_correlate` (~97 tokens)

Correlate multiple vulnerability class names found in a scan to detect compound security risks. Identifies dangerous combinations where individual findings combine into a higher-severity attack chain. No API key required.

Input parameters:

- `patterns` (array, required): Array of vuln_class names found in a scan (e.g. ["cors-misconfiguration", "missing-authentication"]). Use the vuln_class values returned by frogeye_search or frogeye_scan.

### `frogeye_batch_scan` (~72 tokens)

Batch scan up to 10 code snippets in a single MCP call. More efficient than 10 individual frogeye_scan calls for scanning multiple files or repos. Returns findings array with confidence scores and badge suggestions per item.

Input parameters:

- `items` (array, required): Array of code snippets to scan (max 10)

## Diagnostics

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

## Score history

- 2026-08-03: 66
- 2026-08-02: 65
- 2026-08-01: 65
- 2026-07-31: 65
- 2026-07-30: 64
- 2026-07-29: 64
- 2026-07-28: 63
- 2026-07-27: 62
- 2026-07-26: 62

## Links

- Remote endpoint: https://mcp.frogeye.ai/mcp
- Repository: https://github.com/frogeye-ai/mcp
- Website: https://frogeye.ai/
- Changelog RSS feed: https://verifymcp.io/servers/frogeye-ai-mcp/mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/frogeye-ai-mcp/mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/frogeye-ai-mcp/mcp