# Cyanheads Pentest MCP server

Source: https://glimind.com/server/mcp-registry%2Fio.github.cyanheads%2Fpentest-mcp-server
Registry id: `mcp-registry/io.github.cyanheads/pentest-mcp-server`
Status: live (checked 2026-10-27T01:45:23.262Z)

## Verdict

Cyanheads Pentest MCP server answered 99.83% of Glimind's liveness checks over 30 days, better than 25% of MCP servers, with 526 ms median handshake and 18 outages in 90 days. Its agent-readiness grade is A (94/100) across 7 tools, costing an agent about 2,619 tokens to load. Checked every few minutes; no tool is ever called.

## Measurements (30 days)

| Metric | Value | Better than |
|---|---|---|
| Uptime, 30 days | 99.83% | 25% of MCP servers |
| Median handshake latency | 526 ms | 47% of MCP servers |
| p95 handshake latency | 2885 ms | — |
| Checks in 30 days | 4,961 | — |
| Outages, 90 days | 18 | — |
| Median recovery | 3 min | — |
| Agent-readiness score | 94/100 (A) | 78% of MCP servers |
| Tools | 7 | — |
| Tool-list size for an agent | ~2,619 tokens | 48% of MCP servers |
| Days observed | 29 | — |

## Install

```json
{
  "mcpServers": {
    "cyanheads-pentest-mcp-server": {
      "type": "http",
      "url": "https://pentest.caseyjhand.com/mcp"
    }
  }
}
```

Claude Code:

```sh
claude mcp add --transport http cyanheads-pentest-mcp-server https://pentest.caseyjhand.com/mcp
```

## Tools (7)

- `pentest_analyze_response`: Analyze an HTTP response from authorized probing for information leakage, fingerprinting signals, and related exposure. Structured findings cover version disclo
- `pentest_encode_payload`: Transform a payload string through an ordered encoding chain for authorized filter research. Results include the final value, intermediate values, optional deco
- `pentest_generate_payloads`: Generate context-specific payload templates for authorized systems. Each template includes its vulnerability category, context rationale, WAF/IDS detection sign
- `pentest_get_guide`: Return an authorized-testing methodology for a selected vector and optional target context. The playbook covers reconnaissance, enumeration, exploitation, and p
- `pentest_lookup_group`: Look up a MITRE ATT&CK threat group or software entry by ID, name, or keyword. Results include ATT&CK identity, aliases, type, description, and associated techn
- `pentest_lookup_technique`: Look up a MITRE ATT&CK technique by exact ID or keyword. Results include tactics, platforms, description, detection data, public procedure examples, mitigations
- `pentest_map_techniques`: Rank ATT&CK techniques and OWASP test cases against an authorized target profile of technology stack, exposed services, authentication type, and operating syste

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.