AI & Machine Learning
intentsite.com
An AI-powered Q&A server that gives grounded answers to natural language questions and exposes an intent map of supported queries.
ENDPOINT 1
https://mcp.intentsite.com/mcp
MCP server metadata
- Name
- intentsite-mcp
- Version
- 1.0.0
Public IntentSite assistant. Use `ask_intentsite` to ask questions in natural language; use `list_intents` to discover what it can answer. No authentication required; per-caller rate limits apply.
Known tools 2
ask_intentsiteAsk IntentSite's assistant a question in natural language and get a curated, grounded answer.
Inferred read-onlylist_intentsDiscover what IntentSite's assistant can answer: returns the IntentMap — every curated question, tagged with category and language.
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.intentsite-mcp]
url = "https://mcp.intentsite.com/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"intentsite-mcp": {
"type": "http",
"url": "https://mcp.intentsite.com/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: intentsite-mcp
Remote MCP URL: https://mcp.intentsite.com/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": {
"intentsite-mcp": {
"url": "https://mcp.intentsite.com/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"intentsite-mcp": {
"type": "http",
"url": "https://mcp.intentsite.com/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "intentsite-mcp",
"transport": "streamable-http",
"url": "https://mcp.intentsite.com/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.