AI & Machine Learning
flaex.ai
An MCP server for Flaex that enables semantic search of AI tools and intent-based discovery of recommended AI tool stacks based on problem, budget, and skill level.
ENDPOINT 1
https://www.flaex.ai/api/mcp
MCP server metadata
- Name
- flaex-ai-discovery
- Version
- 1.0.0
Use flaex_search_tools to find AI tools by natural-language query, or flaex_intent_discovery for full stack recommendations from a problem description.
Known tools 2
flaex_search_toolsSearch the Flaex AI directory of 600+ AI tools using semantic search.
Inferred read-onlyflaex_intent_discoveryThe Flaex "Detective": describe a problem with budget and skill level and get a recommended stack of AI tools with reasoning.
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.flaex-ai-discovery]
url = "https://www.flaex.ai/api/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"flaex-ai-discovery": {
"type": "http",
"url": "https://www.flaex.ai/api/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: flaex-ai-discovery
Remote MCP URL: https://www.flaex.ai/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": {
"flaex-ai-discovery": {
"url": "https://www.flaex.ai/api/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"flaex-ai-discovery": {
"type": "http",
"url": "https://www.flaex.ai/api/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "flaex-ai-discovery",
"transport": "streamable-http",
"url": "https://www.flaex.ai/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.