# Machina (pypi · machina-mcp)

x402-powered AI agent services — URL extraction, PDF processing, code scanning, and more.

- Trust score: 52/100 (low)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- pypi · `machina-mcp`: 52/100 (this document), [markdown](https://verifymcp.io/servers/nyterry-machina-mcp/machina-mcp.md), [page](https://verifymcp.io/servers/nyterry-machina-mcp/machina-mcp)

## Channel facts

- Registry: `pypi`
- Package: `machina-mcp`
- Version: `0.1.1`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, 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.

- **Supply Chain Security**: 50/100
  - Malware scan not yet available for this package.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs hatchling.build at install time, a recognised build step with no custom scripting around it.
  - 2 of 33 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 1 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 70/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 701 tokens (~87/item across 8 items; 8 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 71/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 8 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 8 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### How do I install the Machina MCP server?

Machina runs locally as a PyPI package, launched with uvx machina-mcp. 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 nyterry-machina-mcp -- uvx machina-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "nyterry-machina-mcp": {
      "command": "uvx",
      "args": [
        "machina-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "nyterry-machina-mcp": {
      "command": "uvx",
      "args": [
        "machina-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add nyterry-machina-mcp -- uvx machina-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "nyterry-machina-mcp": {
      "type": "local",
      "command": [
        "uvx",
        "machina-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add nyterry-machina-mcp --command uvx --arg machina-mcp
```

### Hermes

```yaml
mcp_servers:
  nyterry-machina-mcp:
    command: "uvx"
    args: ["machina-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "nyterry-machina-mcp": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "machina-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add nyterry-machina-mcp -t stdio -c uvx -a machina-mcp
```

### Other

```json
{
  "mcpServers": {
    "nyterry-machina-mcp": {
      "command": "uvx",
      "args": [
        "machina-mcp"
      ]
    }
  }
}
```

## 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.

### 2026-11-05 (score 52, −15)

- [security regression] Malware scan: pass → unverified

### 2026-11-04 (score 67, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-11-03 (score 52)

First indexed and scored.

## MCP tools (8)

### `url_extract` (~63 tokens)

Fetch a URL and return its full content as clean Markdown. Useful for reading web pages, articles, blog posts, and documentation. Returns title, word count, and the full text as Markdown. Cost: $0.005 per call.

Input parameters:

- `url` (string, required)

Output parameters:

- `result` (string)

### `scan_python` (~107 tokens)

Scan Python source code for security vulnerabilities. Detects: hardcoded secrets/API keys, eval/exec misuse, shell injection, insecure SSL/TLS, dangerous deserialization (pickle, yaml.load), path traversal, and CVE-affected dependency versions. Returns structured findings with severity (critical/high/medium/low) and line numbers. Handles up to 10,000 lines. Cost: $0.020 per call.

Input parameters:

- `code` (string, required)
- `filename` (string)

Output parameters:

- `result` (string)

### `validate_email` (~102 tokens)

Validate a single email address. Checks: syntax/format, MX record existence, disposable email provider detection, and role-address detection (noreply@, info@, etc.). With smtp_probe=True, attempts an SMTP connection to verify the mailbox exists (best-effort — some servers block probes). Returns a deliverability score and per-check results. Cost: $0.007 per call.

Input parameters:

- `email` (string, required)
- `smtp_probe` (boolean)

Output parameters:

- `result` (string)

### `validate_email_bulk` (~98 tokens)

Validate up to 100 email addresses in a single call. Same checks as validate_email (syntax, MX, disposable, role-address) but optimised for batch processing. SMTP probing is off by default to keep latency low. Returns per-address results plus a summary. Cost: $0.500 per call (up to 100 emails, ~$0.005/email).

Input parameters:

- `emails` (array, required)
- `smtp_probe` (boolean)

Output parameters:

- `result` (string)

### `domain_intel` (~86 tokens)

Get comprehensive intelligence on a domain name. Returns: DNS records (A/MX/NS/TXT/SPF/DMARC), WHOIS registration data and domain age, SSL certificate details and expiry, HTTP response headers, tech stack detection (CMS, server, CDN, etc.), and email infrastructure analysis. Cost: $0.050 per call.

Input parameters:

- `domain` (string, required)

Output parameters:

- `result` (string)

### `pdf_inspect` (~83 tokens)

FREE pre-check for a PDF file. Returns page count, file size, and metadata (title, author, creator, creation date) without extracting any text. Use this before pdf_extract or pdf_extract_large to check the page count and decide which extractor to use. No payment required. Cost: FREE.

Input parameters:

- `pdf_base64`
- `pdf_path`

Output parameters:

- `result` (string)

### `pdf_extract` (~81 tokens)

Extract text from a PDF (up to 50 pages) and return it as Markdown. Preserves headings, tables, lists, and document structure. Call pdf_inspect first to verify page count — use pdf_extract_large for documents over 50 pages. Cost: $0.050 per call.

Input parameters:

- `pdf_base64`
- `pdf_path`

Output parameters:

- `result` (string)

### `pdf_extract_large` (~81 tokens)

Extract text from a large PDF (up to 200 pages) and return it as Markdown. For documents over 50 pages. Call pdf_inspect first to check the page count. For documents ≤50 pages, prefer pdf_extract (cheaper). Cost: $0.180 per call.

Input parameters:

- `pdf_base64`
- `pdf_path`

Output parameters:

- `result` (string)

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/nyterry-machina-mcp/machina-mcp#diagnostics

## Score history

- 2026-11-05: 52
- 2026-11-04: 67
- 2026-11-03: 52

## Common questions

### What is the Machina MCP server?

Machina is an MCP server listed in the public MCP registry as io.github.NyTerry/machina-mcp. x402-powered AI agent services, URL extraction, PDF processing, code scanning, and more. This page covers its PyPI package (machina-mcp).

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

Machina scores 52 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 2026. 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 Machina MCP server expose?

Machina exposes 8 tools: url_extract, scan_python, validate_email, validate_email_bulk, domain_intel, and 3 more. Their descriptions and schemas cost roughly 701 tokens of context every time the server is loaded.

### Is the Machina MCP server still maintained?

Machina 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.

### What licence is the Machina MCP server under?

Machina declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

### What did VerifyMCP test on the Machina MCP server?

VerifyMCP ran 14 checks on Machina, covering Known CVEs, Install scripts, Dependency health, Source repository and 10 more. 2 items could not be completed, a gap on our side rather than a finding about Machina: Malware scan and Stability. One category scores 0 for that reason, because we only credit what we can confirm. Endpoint Security and Transport & Reachability do not apply to a PyPI package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- PyPI project: https://pypi.org/project/machina-mcp/
- Socket report: https://socket.dev/pypi/package/machina-mcp
- Repository: https://github.com/NyTerry/machina-mcp
- Changelog RSS feed: https://verifymcp.io/servers/nyterry-machina-mcp/machina-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/nyterry-machina-mcp/machina-mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/nyterry-machina-mcp/machina-mcp.json
- HTML version of this page: https://verifymcp.io/servers/nyterry-machina-mcp/machina-mcp