Headless Domains MCP Server
Enables checking domain availability, WHOIS lookup, domain registration, and bio syncing through the Headless Domains API.
README
Headless Domains MCP Server
Official Model Context Protocol (MCP) server for Headless Domains. This server exposes Headless Domains API operations to MCP-compatible clients such as Claude Desktop, Cursor, and Windsurf.
Features
search_domain: check whether a domain is availablelookup_whois: inspect a registered identityregister_domain: register a domain with an API keysync_bio: sync agent/profile bio content with an API key- Automatic transport selection:
stdiofor local MCP clientsssewhenPORTis present for hosted deployments
Requirements
- Python 3.10+
- Optional: a Headless Domains API key for authenticated tools
Local Setup
python3 -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt
Environment Variables
| Variable | Required | Default | Purpose |
|---|---|---|---|
HEADLESSDOMAINS_API_KEY |
No | unset | Sends X-API-Key for authenticated endpoints |
HEADLESSDOMAINS_API_BASE_URL |
No | https://headlessdomains.com/api/v1 |
Overrides the API base URL |
HEADLESSDOMAINS_TIMEOUT |
No | 20 |
HTTP timeout in seconds |
HEADLESSDOMAINS_REGISTER_PATH |
No | /domains/register |
Override register endpoint path if the API changes |
HEADLESSDOMAINS_SYNC_BIO_PATH |
No | /domains/{domain}/bio |
Override sync-bio endpoint path if the API changes |
MCP_TRANSPORT |
No | auto | Force a transport such as stdio or sse |
HOST |
No | 0.0.0.0 |
Bind host for SSE mode |
PORT |
No | unset | When present, starts the server in sse mode |
Run Locally
For a local MCP client, the server uses stdio by default:
python server.py
You can also run it through the MCP CLI:
mcp run server.py
Claude Desktop Configuration
Add a server entry to claude_desktop_config.json:
{
"mcpServers": {
"headlessdomains": {
"command": "mcp",
"args": [
"run",
"/absolute/path/to/headlessdomains-mcp/server.py"
],
"env": {
"HEADLESSDOMAINS_API_KEY": "your-api-key-here"
}
}
}
}
If you do not need authenticated tools yet, you can omit HEADLESSDOMAINS_API_KEY.
Hosted SSE Mode
When PORT is present, server.py starts an SSE transport automatically:
PORT=8080 python server.py
Typical Railway-style launch:
HOST=0.0.0.0 PORT=8080 python server.py
Tool Notes
register_domain
- Requires
HEADLESSDOMAINS_API_KEY - Sends a base payload containing
domain,namespace,years,agreed_to_terms(true), andpayment_method("gems") - Accepts
extra_payload_jsonfor API fields not hard-coded into the tool
Example:
{
"domain": "myagent.agent",
"years": 1,
"extra_payload_json": "{\"owner_email\":\"me@example.com\"}"
}
sync_bio
- Requires
HEADLESSDOMAINS_API_KEY - Syncs to the
/domains/<domain>/bioendpoint - Sends
domain,bio, andbio_markdown - Accepts
extra_payload_jsonfor any additional API fields (likename,x,github, etc.)
Example:
{
"domain": "myagent.agent",
"bio_markdown": "# About Me",
"extra_payload_json": "{\"name\":\"My Agent Name\", \"x\":\"twitter_handle\"}"
}
Docker
Build:
docker build -t headlessdomains-mcp .
Run:
docker run --rm -p 8080:8080 \
-e PORT=8080 \
-e HEADLESSDOMAINS_API_KEY=your-api-key-here \
headlessdomains-mcp
Smoke Testing
After installing dependencies:
python -m py_compile server.py
python - <<'PY'
import server
print(server.search_domain("example.agent"))
print(server.lookup_whois("test.agent"))
PY
Notes
/temp-specsis ignored in.gitignoreso local planning docs stay out of version control.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.