Model Context ProviderSAFE
MCP server for authorized pentest workflows: Nmap/Gobuster orchestration, context aggregation, AI-assisted triage, and reporting.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Authorized penetration-testing MCP server for AI-assisted security operators. It orchestrates common assessment tools, normalizes engagement context, and keeps the human pentester in control of scope, methodology, and reporting.
[](https://mseep.ai/app/allsmog-mcp-pentest)
An AI-driven assistant and middleware for penetration testing engagements
[](https://opensource.org/licenses/MIT) [](https://www.python.org/downloads/) [](https://www.docker.com/) [](https://github.com/allsmog/mcp-pentest/releases/tag/v0.1.0)
At a glance
Status
mcp-pentest is in alpha and under active development. Contributors are welcome for new tool integrations, UI/UX, documentation, testing, and reporting workflows. See CONTRIBUTING.md for how to get started.
🔍 Overview
The Model Context Provider (MCP) is an open-source framework that bridges AI with penetration testing tools. MCP interfaces with a wide array
37f774d50635OBSERVED · 2026-10-10Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add mcp-pentest -- uvx mcp-pentest
{
"mcpServers": {
"mcp-pentest": {
"command": "uvx",
"args": [
"mcp-pentest"
]
}
}
}Exposed tools (3)
1 read · 1 write · 1 destructive. Blast radius: 1 tool can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.
| Tool | Risk | Description |
|---|---|---|
get_scan_events | read | Retrieve events from completed scans |
gobuster_scan | destructive | Execute Gobuster directory/file brute-force scans for web application enumeration |
nmap_scan | write | Execute Nmap network scans for port discovery, service detection, and OS fingerprinting |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (1 observation(s))
- Network
- declared (2 observation(s))
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (1)
gobuster_scan
Gates applied: no_behavioural_pass.
37f774d50635full audit observations/trust-audit/mcp-server/allsmog__model-context-provider-1.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-10 | 37f774d50635 | SAFE | B | 89 | first audit |
Questions
What is the Model Context Provider MCP server?
MCP server for authorized pentest workflows: Nmap/Gobuster orchestration, context aggregation, AI-assisted triage, and reporting.
What tools does Model Context Provider expose?
3 in total: 1 read-only, 1 that write, and 1 that can delete or overwrite (gobuster_scan). Every one is listed on this page with its risk.
Is Model Context Provider safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B. Separately from the audit: 1 of its tools can destroy data, so scope the token you give it to what you actually need.
What credentials does Model Context Provider need?
No credential environment variables were found in its source, so it appears to need none.
How does Model Context Provider run?
It speaks stdio, so it runs as a local process your client starts. It is published on PyPI as mcp-pentest.
How current is this page?
The grade is for one exact copy of the source (37f774d50635), read on 2026-10-10. The repository is watched and re-audited when it changes.