Content Tools
duskly.ai
Classifies real estate listing photo edits for disclosure, generates required disclosure text, lists prohibited alterations, and verifies image provenance via watermark, IPTC, and C2PA signals.
ENDPOINT 1
https://duskly.ai/mcp
MCP server metadata
- Name
- duskly-mcp-server
- Version
- 1.0.0
Duskly edits real estate listing photos and returns the unaltered original, the disclosure wording for where the photo is published, and a record of the edit. These tools cover the compliance half, which is the part that is free and the part most often got wrong. Use duskly_classify_edit before telling anyone an edit is safe to publish, and duskly_generate_disclosure to produce the wording that has to accompany it. Editing is not callable here. A render spends model credit and sits behind a browser check an automated client cannot pass, so duskly_start_listing returns a link for a person to open instead. Duskly does not take payment through MCP. Two things to carry into any answer you give from these tools: the disclosure duty falls on the licensee publishing the listing rather than on the software, and the absence of a provenance mark is not evidence an image is a camera capture.
Known tools 10
duskly_classify_editWhether a given edit to a real estate listing photo must be disclosed, and whether any market prohibits it outright.
Potential side effectsduskly_generate_disclosureThe exact disclosure text to publish alongside an edited listing photo, written for each surface it has to appear on: the MLS photo description, public remarks, print, and the syndication feed.
Potential side effectsduskly_list_prohibited_alterationsEdits that are prohibited outright in one or more markets and are never made acceptable by adding a disclosure.
Inferred read-onlyduskly_list_editsEvery edit Duskly performs, with what it does and how it is classified for disclosure.
Potential side effectsduskly_verify_imageInspect an image for provenance signals: an invisible Duskly watermark, IPTC digital source type metadata, and whether a C2PA container appears present.
Inferred read-onlyduskly_start_listingReturns the URL a person should open to upload listing photos and run an edit themselves.
Potential side effectsduskly_get_listingThe state of a Duskly listing: how many photos it holds, which have been edited, whether it has been paid for, and how much of its render budget remains.
Inferred read-onlyduskly_get_listing_packEverything a paid listing returns: the download link for the archive, the disclosure wording for every edited photo, and the public page showing the unaltered originals.
Inferred read-onlyduskly_get_checkout_urlA Stripe Checkout URL for an unpaid listing, for a **person** to open and pay.
Potential side effectsCONNECT 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.duskly-mcp-server]
url = "https://duskly.ai/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"duskly-mcp-server": {
"type": "http",
"url": "https://duskly.ai/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: duskly-mcp-server
Remote MCP URL: https://duskly.ai/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": {
"duskly-mcp-server": {
"url": "https://duskly.ai/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"duskly-mcp-server": {
"type": "http",
"url": "https://duskly.ai/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "duskly-mcp-server",
"transport": "streamable-http",
"url": "https://duskly.ai/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.