Sylgeo MCP Server — Check your brand's AI visibility across ChatGPT, Claude, Gemini & Perplexity
Project description
Sylgeo MCP Server
Check your brand's AI visibility across ChatGPT, Claude, Gemini & Perplexity — right from your coding workflow.
Sylgeo MCP is a Model Context Protocol server that gives AI coding assistants access to Sylgeo's Generative Engine Optimization (GEO) tools. Ask your assistant to scan your brand, analyze your website, compare competitors, and get actionable recommendations — all without leaving your editor.
Quick Start
1. Get Your API Key
Sign up and grab your key at sylgeo.com/dashboard/api-keys.
2. Install in Your AI Assistant
Claude Code
claude mcp add sylgeo-mcp -- uvx sylgeo-mcp
Then set your API key:
export SYLGEO_API_KEY="your-api-key-here"
Cursor
Add to .cursor/mcp.json in your project root:
{
"mcpServers": {
"sylgeo": {
"command": "uvx",
"args": ["sylgeo-mcp"],
"env": {
"SYLGEO_API_KEY": "your-api-key-here"
}
}
}
}
Windsurf
Add to your Windsurf MCP config:
{
"mcpServers": {
"sylgeo": {
"command": "uvx",
"args": ["sylgeo-mcp"],
"env": {
"SYLGEO_API_KEY": "your-api-key-here"
}
}
}
}
Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"sylgeo": {
"command": "uvx",
"args": ["sylgeo-mcp"],
"env": {
"SYLGEO_API_KEY": "your-api-key-here"
}
}
}
}
Available Tools
All tools require a valid SYLGEO_API_KEY.
| Tool | Description |
|---|---|
scan_brand_visibility |
Run a full AI visibility scan across ChatGPT, Claude, Gemini & Perplexity. Returns mention rates, rankings, and sentiment. |
check_visibility_score |
Get current GEO and AEO visibility scores with per-model breakdown. |
analyze_website_geo |
Analyze a website's GEO readiness — robots.txt, schema markup, content structure. |
get_geo_recommendations |
Get prioritized action items with estimated impact scores. |
compare_competitors |
Compare your AI visibility against tracked competitors. |
get_scan_history |
View historical scan data and score trends over time. |
get_tracked_prompts |
List the AI search prompts being tracked for your domain. |
Prompt Templates
| Prompt | Description |
|---|---|
geo_audit |
Full GEO audit — analyze website, run scan, check scores, provide recommendations. |
competitor_analysis |
Competitive AI visibility analysis with gap identification. |
content_optimization |
Content analysis with specific optimization recommendations. |
Resources
| URI | Description |
|---|---|
sylgeo://docs/getting-started |
Getting started guide |
sylgeo://docs/what-is-geo |
What is GEO (Generative Engine Optimization)? |
Example Usage
Once installed, just ask your AI assistant:
"Scan the AI visibility for my domain example.com"
The assistant will call scan_brand_visibility and then check_visibility_score to show your results.
"How does my site compare to competitors?"
The assistant will call compare_competitors and present a comparison table.
"Run a full GEO audit for example.com"
Using the geo_audit prompt template, the assistant will walk through a complete audit:
- Analyze website GEO readiness
- Run a visibility scan
- Check scores
- Provide recommendations
"What prompts are being tracked for my domain?"
The assistant will call get_tracked_prompts to show which AI search queries are being monitored.
Configuration
| Environment Variable | Required | Description |
|---|---|---|
SYLGEO_API_KEY |
Yes | Your Sylgeo API key (get one here) |
SYLGEO_API_URL |
No | Override the API base URL (default: https://api.sylgeo.com) |
Development
# Clone the repo
git clone https://github.com/sylgeo/sylgeo-mcp.git
cd sylgeo-mcp
# Install in development mode
pip install -e ".[dev]"
# Run the server locally
SYLGEO_API_KEY="your-key" python -m sylgeo_mcp.server
Testing with MCP Inspector
npx @modelcontextprotocol/inspector uvx sylgeo-mcp
What is GEO?
Generative Engine Optimization (GEO) is the practice of optimizing your brand's content to appear in AI-generated answers — the responses from ChatGPT, Claude, Gemini, Perplexity, and other LLM-powered search tools.
Traditional SEO focuses on Google's blue links. GEO focuses on getting your brand mentioned, recommended, and cited by AI assistants.
Learn more → sylgeo.com
License
MIT — see LICENSE for details.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file sylgeo_mcp-0.1.0.tar.gz.
File metadata
- Download URL: sylgeo_mcp-0.1.0.tar.gz
- Upload date:
- Size: 8.6 kB
- Tags: Source
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/6.1.0 CPython/3.13.12
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
7b4dbc50b2aa5f703aef3f40e121351dfaec13320da7e7a9d086c992b3a19494
|
|
| MD5 |
0466b699b83ae79fb08243a22d755f2a
|
|
| BLAKE2b-256 |
1d8ebd0e7372e5501fbf30e02f0095108757d5a22adc529eb3bbfbd6559ec658
|
Provenance
The following attestation bundles were made for sylgeo_mcp-0.1.0.tar.gz:
Publisher:
publish.yml on hitankshah/Sylgeo
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
sylgeo_mcp-0.1.0.tar.gz -
Subject digest:
7b4dbc50b2aa5f703aef3f40e121351dfaec13320da7e7a9d086c992b3a19494 - Sigstore transparency entry: 1992816547
- Sigstore integration time:
-
Permalink:
hitankshah/Sylgeo@d199308f52f9e5c077e652dfcb9c742ff75b8ce8 -
Branch / Tag:
refs/tags/v0.1.0 - Owner: https://github.com/hitankshah
-
Access:
private
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
github-hosted -
Publication workflow:
publish.yml@d199308f52f9e5c077e652dfcb9c742ff75b8ce8 -
Trigger Event:
release
-
Statement type:
File details
Details for the file sylgeo_mcp-0.1.0-py3-none-any.whl.
File metadata
- Download URL: sylgeo_mcp-0.1.0-py3-none-any.whl
- Upload date:
- Size: 10.5 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/6.1.0 CPython/3.13.12
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
98d668ae79cf0a765a6a8ae0a7de26f946f7693d2f7e9ca78740669aaa4b6f2d
|
|
| MD5 |
dd7e5349859de1ac78c7d22a828046f3
|
|
| BLAKE2b-256 |
7eca9592dc245cc65546016cfd839466d9ae8b735a5766a30aa64031b775eb12
|
Provenance
The following attestation bundles were made for sylgeo_mcp-0.1.0-py3-none-any.whl:
Publisher:
publish.yml on hitankshah/Sylgeo
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
sylgeo_mcp-0.1.0-py3-none-any.whl -
Subject digest:
98d668ae79cf0a765a6a8ae0a7de26f946f7693d2f7e9ca78740669aaa4b6f2d - Sigstore transparency entry: 1992816716
- Sigstore integration time:
-
Permalink:
hitankshah/Sylgeo@d199308f52f9e5c077e652dfcb9c742ff75b8ce8 -
Branch / Tag:
refs/tags/v0.1.0 - Owner: https://github.com/hitankshah
-
Access:
private
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
github-hosted -
Publication workflow:
publish.yml@d199308f52f9e5c077e652dfcb9c742ff75b8ce8 -
Trigger Event:
release
-
Statement type: