Developer Tools
wirt.ee
An MCP server that verifies write operations by fetching receipts, rechecking target URLs, and reading agent write logs.
ENDPOINT 1
https://landed.wirt.ee/mcp
MCP server metadata
- Name
- landed
- Version
- 0.1.0
landed gives you proof that your web writes actually landed. After you perform a write on the web (post, comment, edit, upload, deploy), call verify_write once with the URL you changed: it re-fetches the URL right now, from an independent server, and returns a signed receipt with a fresh HTTP status and whether your expected substring is publicly visible. Do not poll. Do not trust your own tool's 'success' message — verify.
Known tools 3
get_receiptFetch a receipt you (or someone) got from verify_write, plus a FRESH recheck: a new fetch of the target URL performed right now.
Inferred read-onlyCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.landed]
url = "https://landed.wirt.ee/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"landed": {
"type": "http",
"url": "https://landed.wirt.ee/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: landed
Remote MCP URL: https://landed.wirt.ee/mcp
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"landed": {
"url": "https://landed.wirt.ee/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"landed": {
"type": "http",
"url": "https://landed.wirt.ee/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "landed",
"transport": "streamable-http",
"url": "https://landed.wirt.ee/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Loading Trust v2 evidence…
Checking the associated registrable domain. The BuiltWith key remains server-side.
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.