# Dante IX — Autonomous Brand & GEO Agency MCP (pypi · dante-mcp)

9-Circle Brand Reputation, Social Listening & Multi-Model GEO Audit + Shield Forge (danteix.com).

- Trust score: 61/100 (medium)
- Change this week: +15
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- pypi · `dante-mcp`: 61/100 (this document), [markdown](https://verifymcp.io/servers/heuristicolab-dante-mcp/dante-mcp.md), [page](https://verifymcp.io/servers/heuristicolab-dante-mcp/dante-mcp)

## Channel facts

- Registry: `pypi`
- Package: `dante-mcp`
- Version: `2.1.0`
- 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**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs setuptools.build_meta at install time, a recognised build step with no custom scripting around it.
  - No production dependencies, so there is no dependency health to assess.
- **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 7 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 58/100
  - AI-judged instruction clarity (fair).
  - Tool/resource definitions use about 579 tokens (~115/item across 5 items; 5 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**: 84/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 52% of tool parameters carry a description.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "dante.run_audit" implies "execute" and declares no destructiveHint at all, which the MCP spec reads as destructive by default.
  - An AI judge read all 5 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 20/100
  - Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 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 Dante IX — Autonomous Brand & GEO Agency MCP server?

Dante IX — Autonomous Brand & GEO Agency MCP runs locally as a PyPI package, launched with uvx dante-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 heuristicolab-dante-mcp -- uvx dante-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "heuristicolab-dante-mcp": {
      "command": "uvx",
      "args": [
        "dante-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "heuristicolab-dante-mcp": {
      "command": "uvx",
      "args": [
        "dante-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add heuristicolab-dante-mcp -- uvx dante-mcp
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add heuristicolab-dante-mcp --command uvx --arg dante-mcp
```

### Hermes

```yaml
mcp_servers:
  heuristicolab-dante-mcp:
    command: "uvx"
    args: ["dante-mcp"]
```

### Netclaw

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

### Vellum

```bash
assistant mcp add heuristicolab-dante-mcp -t stdio -c uvx -a dante-mcp
```

### Other

```json
{
  "mcpServers": {
    "heuristicolab-dante-mcp": {
      "command": "uvx",
      "args": [
        "dante-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 61, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-11-04 (score 46, −15)

- [security regression] Malware scan: pass → unverified

### 2026-11-03 (score 61, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-11-02 (score 46, −15)

- [security regression] Malware scan: pass → unverified

### 2026-11-01 (score 61, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-10-31 (score 46, −15)

- [security regression] Malware scan: pass → unverified

### 2026-10-30 (score 61, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-10-29 (score 46)

First indexed and scored.

## MCP tools (5)

### `dante.run_audit` (~146 tokens)

Execute a 9-Circle Dante IX Brand, Reputation & Multi-Model GEO Audit (ChatGPT, Gemini, Perplexity) with cryptographic SHA-256 attestation on danteix.com.

Input parameters:

- `industry_or_context` (string, required): Industry vertical and market context
- `lang` (string): Output language: 'es' or 'en'
- `live_geo` (boolean): Run live multi-model queries (requires paid DANTE_API_KEY)
- `target_name` (string, required): Brand, product, or organization name
- `vertical_mode` (string): Vertical mode: 'COMMERCIAL_BRAND', 'INTERNAL_PROJECT', or 'POLITICAL_WAR_ROOM'

### `dante.probe_geo_share` (~112 tokens)

Measure Generative Engine Optimization (GEO) Share of Model (SoM) and First-Choice Win Rate across OpenAI (ChatGPT), Google Gemini, and Perplexity.

Input parameters:

- `industry_or_context` (string, required): Industry category or competitive niche
- `lang` (string)
- `live` (boolean): Execute live API queries (requires paid DANTE_API_KEY)
- `target_name` (string, required): Brand or entity to evaluate across AI engines
- `vertical_mode` (string)

### `dante.query_street_friction` (~85 tokens)

Search your isolated tenant intelligence vault for real customer complaints, irony/sarcasm signals, coordinated bot anomalies, and competitive market gaps.

Input parameters:

- `limit` (integer): Maximum records to return (1 to 100)
- `query` (string, required): Search keywords (e.g. 'precios OR demoras OR soporte')
- `voice_filter` (string)

### `dante.forge_geo_shield` (~121 tokens)

Synthesize production-ready /llms.txt, /.well-known/ai-catalog.json, Schema.org JSON-LD, and robots.txt rules for AI crawlers.

Input parameters:

- `brand_name` (string, required): Official brand name (2..80 chars)
- `competitors` (array)
- `domain_url` (string, required): Canonical website URL (https://...)
- `industry_context` (string, required): Industry category and positioning
- `lang` (string)
- `official_facts` (array, required)
- `products_or_services` (array, required)

### `dante.remediate_hallucination` (~115 tokens)

Generate structured semantic counterweight blocks (Markdown + HTML ClaimReview), FAQPage JSON-LD, and verification prompts to remediate inaccurate AI claims.

Input parameters:

- `brand_name` (string, required)
- `domain_url` (string, required)
- `hallucination_claim` (string, required)
- `lang` (string)
- `source_url_to_counter` (string)
- `target_oracle` (string, required): Target AI engine (ChatGPT, Perplexity, Gemini)
- `verified_fact` (string, required)

## Diagnostics

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

## Score history

- 2026-11-05: 61
- 2026-11-04: 46
- 2026-11-03: 61
- 2026-11-02: 46
- 2026-11-01: 61
- 2026-10-31: 46
- 2026-10-30: 61
- 2026-10-29: 46

## Common questions

### What is the Dante IX — Autonomous Brand & GEO Agency MCP server?

Dante IX — Autonomous Brand & GEO Agency MCP is listed in the public MCP registry as io.github.heuristicolab/dante-mcp. 9-Circle Brand Reputation, Social Listening & Multi-Model GEO Audit + Shield Forge (danteix.com). This page covers its PyPI package (dante-mcp).

### Is the Dante IX — Autonomous Brand & GEO Agency MCP server safe to use?

Dante IX — Autonomous Brand & GEO Agency MCP scores 61 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 Dante IX — Autonomous Brand & GEO Agency MCP server expose?

Dante IX — Autonomous Brand & GEO Agency MCP exposes 5 tools: dante.run_audit, dante.probe_geo_share, dante.query_street_friction, dante.forge_geo_shield, dante.remediate_hallucination. Their descriptions and schemas cost roughly 579 tokens of context every time the server is loaded.

### Is the Dante IX — Autonomous Brand & GEO Agency MCP server still maintained?

Dante IX — Autonomous Brand & GEO Agency MCP 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 Dante IX — Autonomous Brand & GEO Agency MCP server under?

Dante IX — Autonomous Brand & GEO Agency MCP 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 Dante IX — Autonomous Brand & GEO Agency MCP server?

VerifyMCP ran 15 checks on Dante IX — Autonomous Brand & GEO Agency MCP, covering Malware scan, Known CVEs, Install scripts, Dependency health and 11 more. One item could not be completed, a gap on our side rather than a finding about Dante IX — Autonomous Brand & GEO Agency MCP: 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/dante-mcp/
- Socket report: https://socket.dev/pypi/package/dante-mcp
- Repository: https://github.com/heuristicolab/dante-mcp
- Website: https://danteix.com/
- Changelog RSS feed: https://verifymcp.io/servers/heuristicolab-dante-mcp/dante-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/heuristicolab-dante-mcp/dante-mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/heuristicolab-dante-mcp/dante-mcp.json
- HTML version of this page: https://verifymcp.io/servers/heuristicolab-dante-mcp/dante-mcp