# GEO Tracker by DigestSEO (npm · @digestseo/mcp-geo)

Track brand citations across five AI search engines. Free OSS; optional EUR 99 client-ready audit.

- Trust score: 75/100 (medium)
- Change this week: −6
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-20

## Components

- npm · `@digestseo/mcp-geo`: 75/100 (this document), [markdown](https://verifymcp.io/servers/akzar1el-mcp-geo/digestseo-mcp-geo.md), [page](https://verifymcp.io/servers/akzar1el-mcp-geo/digestseo-mcp-geo)

## Channel facts

- Registry: `npm`
- Package: `@digestseo/mcp-geo`
- Version: `0.3.15`
- 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 2026-09-20.

- **Supply Chain Security**: 63/100
  - No malware found by supply-chain analysis.
  - Known CVEs could not be checked: the version this server declares is not published in its registry.
  - No install/post-install scripts declared.
  - Dependency health could not be checked: the version this server declares is not published in its registry.
- **Provenance & Transparency**: 100/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to AKzar1el/mcp-geo).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 0 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 76/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1353 tokens (~135/item across 10 items; 10 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 33/100
  - Stability observed for 10 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.
  - 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 10 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 11 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the GEO Tracker by DigestSEO MCP server?

GEO Tracker by DigestSEO runs locally as an npm package, launched with npx -y @digestseo/mcp-geo. 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 akzar1el-mcp-geo -- npx -y @digestseo/mcp-geo
```

### Cursor

```json
{
  "mcpServers": {
    "akzar1el-mcp-geo": {
      "command": "npx",
      "args": [
        "-y",
        "@digestseo/mcp-geo"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "akzar1el-mcp-geo": {
      "command": "npx",
      "args": [
        "-y",
        "@digestseo/mcp-geo"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add akzar1el-mcp-geo -- npx -y @digestseo/mcp-geo
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "akzar1el-mcp-geo": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@digestseo/mcp-geo"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add akzar1el-mcp-geo --command npx --arg -y --arg @digestseo/mcp-geo
```

### Hermes

```yaml
mcp_servers:
  akzar1el-mcp-geo:
    command: "npx"
    args: ["-y", "@digestseo/mcp-geo"]
```

### Netclaw

```json
{
  "McpServers": {
    "akzar1el-mcp-geo": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@digestseo/mcp-geo"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add akzar1el-mcp-geo -t stdio -c npx -a -y @digestseo/mcp-geo
```

### Other

```json
{
  "mcpServers": {
    "akzar1el-mcp-geo": {
      "command": "npx",
      "args": [
        "-y",
        "@digestseo/mcp-geo"
      ]
    }
  }
}
```

## 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.

### 2026-09-20 (score 75, −10)

- [security regression] Known CVEs: pass → unverified
- [security regression] Tool safety: pass → unverified
- [security regression] Stability: 0.30 → unverified
- [functional regression] Schema quality: 1193 → 1353
- [functional regression] Dependency health: 0.85 → unverified
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional] Schema quality: Schema quality not yet verified: we do not have a sandbox capture of the MCP schema this version of the package serves yet.
- [functional] Package version: 0.3.11 → 0.3.15
- [functional] Package version: 0.3.11 → 0.3.14
- [functional] Package version: 0.3.11 → 0.3.13
- [functional] Package version: 0.3.2 → 0.3.12
- [functional] Package version: 0.3.11 → 0.3.12

### 2026-09-19 (score 85, +15)

- [security regression] Known CVEs: pass → unverified
- [security regression] Stability: 0.27 → unverified
- [security regression] Tool safety: pass → unverified
- [security improvement] Malware scan: unverified → pass
- [functional regression] Dependency health: 0.85 → unverified
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional] Schema quality: Schema quality not yet verified: we do not have a sandbox capture of the MCP schema this version of the package serves yet.
- [functional] Package version: 0.3.6 → 0.3.11
- [functional] Package version: 0.3.6 → 0.3.10
- [functional] Package version: 0.3.2 → 0.3.9
- [functional] Package version: 0.3.6 → 0.3.9
- [functional] Package version: 0.3.6 → 0.3.8
- [functional] Package version: 0.3.6 → 0.3.7

### 2026-09-18 (score 70, −14)

- [security regression] Malware scan: pass → unverified
- [functional] Package version: 0.3.5 → 0.3.6

### 2026-09-17 (score 84, 0)

- [security regression] Tool safety: pass → unverified
- [security regression] Stability: 0.20 → unverified
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional] Schema quality: Schema quality not yet verified: we do not have a sandbox capture of the MCP schema this version of the package serves yet.
- [functional] Package version: 0.3.4 → 0.3.5

### 2026-09-16 (score 84, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-09-15 (score 69, −12)

- [security regression] Malware scan: pass → unverified
- [functional improvement] Stability: unverified → 0.17
- [functional] Package version: 0.3.3 → 0.3.4

### 2026-09-12 (score 81, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-09-11 (score 66, 0)

- [functional] Package version: 0.3.2 → 0.3.3

## MCP tools (10)

### `check_visibility` (~135 tokens)

Check AI visibility

Get the latest AI visibility data for a tracked brand: which AI assistants (ChatGPT, Claude, Perplexity, Gemini, Google AI Overviews) cite this brand, for which prompts, and how it compares to competitors. Use when the user asks 'how visible am I on AI?', 'who's citing my brand?', or 'show me my AI visibility score'. Returns stored data — for fresh data, call refresh_brand.

Input parameters:

- `brand_id` (string, required): Stable identifier of the tracked brand to inspect.
- `engines` (array): Optional engine filter. If omitted or empty, return results for every engine with stored data.

Output parameters:

- `brand` (object)
- `overall_score` (number)
- `per_engine` (array)
- `refreshed_at` (string)
- `top_losing_prompts` (array)
- `top_winning_prompts` (array)

### `get_visibility_history` (~106 tokens)

Get AI visibility history

Get the time-series history of a brand's AI visibility score, broken down per engine. Use when the user asks 'how has my AI visibility changed over time?', 'is my visibility growing or shrinking?', or 'show me the trend for the last month'.

Input parameters:

- `brand_id` (string, required): Stable identifier of the tracked brand to inspect.
- `days` (number): Number of previous calendar days to include.
- `granularity` (string): Time bucket for the returned visibility series.

Output parameters:

- `brand_id` (string)
- `days` (number)
- `granularity` (string)
- `series` (array)

### `compare_competitors` (~127 tokens)

Compare competitor AI visibility

Compare a brand's AI visibility against competitors for the same category. Returns share-of-voice percentages, prompts the user wins, and prompts where competitors win. Use when the user asks 'who beats me in AI search?', 'compare me to my competitors', or 'why does [competitor] get cited more?'.

Input parameters:

- `brand_id` (string, required): Stable identifier of the tracked brand to compare.
- `competitor_domains` (array): Optional competitor domains to compare; otherwise use the brand's configured competitors.
- `days` (number): Number of previous days to include in the comparison.

Output parameters:

- `brand_id` (string)
- `competitors` (array)
- `days` (number)
- `prompts_you_win` (array)
- `requested_competitor_domains`
- `your_mentions` (number)
- `your_share_of_voice_pct` (number)

### `get_citations` (~143 tokens)

Get AI citation evidence

Get citation events where AI assistants mention the brand. Each event includes the prompt that triggered it, the LLM's response excerpt, whether the brand was mentioned with or without a link, and the matched brand URL from engine-native citation data when available. Use when the user asks 'show me where I'm cited', 'what are ChatGPT/Claude/Perplexity actually saying about my brand?', or 'give me proof of AI citations'.

Input parameters:

- `brand_id` (string, required): Stable identifier of the tracked brand to inspect.
- `days` (number): Number of previous days from which to return citations.
- `engine` (string): Optional engine filter for the citation events.

Output parameters:

- `brand_id` (string)
- `citations` (array)
- `days` (number)
- `engine` (string|null)

### `get_content_gaps` (~109 tokens)

Find AI visibility content gaps

Get actionable content recommendations based on AI visibility gaps. Returns prioritized topics and content formats that would close the gap between this brand and competitors winning the same prompts. Use when the user asks 'what should I write to improve AI visibility?', 'what content gaps do I have?', or 'how do I get cited more by AI?'.

Input parameters:

- `brand_id` (string, required): Stable identifier of the tracked brand to analyze.
- `max_recommendations` (number): Maximum number of content recommendations to return.

Output parameters:

- `brand_id` (string)
- `prompt_source` (string)
- `reason` (string)
- `recommendations` (array)

### `refresh_brand` (~121 tokens)

Refresh AI visibility scan

Manually trigger a fresh AI visibility scan for a tracked brand. Runs every selected configured engine (ChatGPT, Claude, Perplexity, Gemini, Google AI Overviews) against the brand's current prompt set sequentially. Use when the user asks 'refresh my data', 'rerun the scan', or 'I want fresh data right now'. Returns only after all selected engine scans finish.

Input parameters:

- `brand_id` (string, required): Stable identifier of the tracked brand to refresh.
- `engines` (array): Optional engine filter. If omitted, refresh every configured engine.

Output parameters:

- `brand_id` (string)
- `estimated_completion_seconds` (number)
- `message` (string)
- `run_ids` (object)

### `track_brand` (~289 tokens)

Track a brand

Start tracking a brand's AI visibility. Creates the brand in the local database and generates buyer-intent prompts for it — via Claude Haiku when ANTHROPIC_API_KEY is configured, otherwise three generic starter prompts (upgrade later with generate_prompts). Use when the user says 'track my brand', 'add my site', 'start monitoring acme.com', or when another tool reported the brand doesn't exist. After tracking, call refresh_brand to run the first scan.

Input parameters:

- `aliases` (array): Extra terms that always count as a brand mention (product names, abbreviations).
- `brand_id` (string, required): Stable identifier to assign to the new tracked brand.
- `category` (string): Optional product or market category for prompt generation.
- `competitors` (array): Optional competitor domains to include in visibility analysis.
- `domain` (string, required): Primary domain of the brand, such as acme.com.
- `exclude_terms` (array): Terms suppressed from bare-word matching — for brand names that are everyday words ("Monday", "Notion"). The full domain still matches.
- `name` (string, required): Display name of the brand to track.
- `prompt_count` (integer): Number of buyer-intent prompts to generate for the brand.
- `refresh_frequency` (string): Refresh cadence used by self-hosted Worker cron scheduling. Local stdio stores this setting but does not run a background scheduler.

Output parameters:

- `brand_id` (string)
- `competitors` (array)
- `domain` (string)
- `next_steps` (string)
- `prompt_source` (string)
- `prompts_inserted` (number)
- `reason` (string)
- `refresh_frequency` (string)
- `seeded` (boolean)

### `list_brands` (~59 tokens)

List tracked brands

List every brand tracked in the local database, with domain, category, competitors, refresh frequency, and how many prompts are active. Use when the user asks 'which brands am I tracking?' or to look up the brand_id the other tools need.

Output parameters:

- `brands` (array)
- `hint` (string)

### `list_prompts` (~72 tokens)

List active prompts

List the exact active buyer-intent prompts for one tracked brand without changing them. Use before a scan or audit when the user wants to inspect the measurement set, verify prompt coverage, or review what generate_prompts produced.

Input parameters:

- `brand_id` (string, required): Stable identifier of the tracked brand whose active prompts to inspect.

Output parameters:

- `brand_id` (string)
- `count` (number)
- `prompts` (array)

### `generate_prompts` (~104 tokens)

Generate brand prompts

Regenerate the buyer-intent prompt set for a tracked brand using Claude Haiku (requires ANTHROPIC_API_KEY). Replaces the brand's active prompts; historical run data is preserved. Use when the user wants better or more prompts, or to upgrade from the generic starter prompts after adding an Anthropic key.

Input parameters:

- `brand_id` (string, required): Stable identifier of the tracked brand to update.
- `count` (integer): Number of buyer-intent prompts to generate.

Output parameters:

- `brand_id` (string)
- `next_steps` (string)
- `prompt_source` (string)
- `prompts` (array)
- `prompts_inserted` (number)

## Diagnostics

Captured diagnostic sections: Provenance. The full working is on the page: https://verifymcp.io/servers/akzar1el-mcp-geo/digestseo-mcp-geo#diagnostics

## Score history

- 2026-09-20: 75
- 2026-09-19: 85
- 2026-09-18: 70
- 2026-09-17: 84
- 2026-09-16: 84
- 2026-09-15: 69
- 2026-09-14: 81
- 2026-09-13: 81
- 2026-09-12: 81
- 2026-09-11: 66
- 2026-09-10: 66
- 2026-09-09: 39
- 2026-09-08: 39
- 2026-09-07: 39
- 2026-09-06: 39
- 2026-09-05: 39
- 2026-09-04: 39
- 2026-09-03: 39
- 2026-09-02: 39
- 2026-09-01: 39
- 2026-08-31: 39
- 2026-08-30: 24

## Common questions

### What is the GEO Tracker by DigestSEO MCP server?

GEO Tracker by DigestSEO is an MCP server listed in the public MCP registry as io.github.AKzar1el/mcp-geo. Track brand citations across five AI search engines. Free OSS; optional EUR 99 client-ready audit. This page covers its npm package (@digestseo/mcp-geo).

### Is the GEO Tracker by DigestSEO MCP server safe to use?

GEO Tracker by DigestSEO scores 75 out of 100 on VerifyMCP. It declares no install or post-install scripts. Its build provenance is signed and verified. 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 GEO Tracker by DigestSEO MCP server expose?

GEO Tracker by DigestSEO exposes 10 tools: check_visibility, get_visibility_history, compare_competitors, get_citations, get_content_gaps, and 5 more. Their descriptions and schemas cost roughly 1,265 tokens of context every time the server is loaded.

### Is the GEO Tracker by DigestSEO MCP server still maintained?

GEO Tracker by DigestSEO is still listed as active in the MCP registry. We last reached this channel on 20 September 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 GEO Tracker by DigestSEO MCP server under?

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

## Links

- npm package: https://www.npmjs.com/package/@digestseo/mcp-geo
- Socket report: https://socket.dev/npm/package/@digestseo/mcp-geo
- Repository: https://github.com/AKzar1el/mcp-geo
- Website: https://digestseo.com/geo-mcp/
- Changelog RSS feed: https://verifymcp.io/servers/akzar1el-mcp-geo/digestseo-mcp-geo.xml
- Changelog JSON feed: https://verifymcp.io/servers/akzar1el-mcp-geo/digestseo-mcp-geo.json
- HTML version of this page: https://verifymcp.io/servers/akzar1el-mcp-geo/digestseo-mcp-geo