AI & Machine Learning
scanforai.com
Scores text for signs of AI/machine writing and strips AI-typical typography without rewriting content.
ENDPOINT 1
https://api.scanforai.com/api/mcp
MCP server metadata
- Name
- scanforai
- Version
- 1
Tools: scan_text (AI-writing score with reasons), cleanup_text (strip machine typography). Auth: Authorization: Bearer at_sk_... header (free key at https://app.scanforai.com). Signal, not a verdict: scores estimate how strongly text shows measurable machine-writing patterns and can be wrong in both directions. Never use a score alone to accuse a person.
Known tools 2
scan_textScore a text 0-100 for signs of AI/machine writing, with the band (low/moderate/elevated/high) and plain-English reasons.
Inferred read-onlycleanup_textStrip machine typography from text without rewriting a word: smart quotes, em dashes and the rare glyphs AI models overuse become plain keyboard characters.
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.scanforai]
url = "https://api.scanforai.com/api/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"scanforai": {
"type": "http",
"url": "https://api.scanforai.com/api/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: scanforai
Remote MCP URL: https://api.scanforai.com/api/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": {
"scanforai": {
"url": "https://api.scanforai.com/api/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"scanforai": {
"type": "http",
"url": "https://api.scanforai.com/api/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "scanforai",
"transport": "streamable-http",
"url": "https://api.scanforai.com/api/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.