API Tools
apihub.io
Enables searching, discovering, and calling APIs from a marketplace, including those with payment requirements.
ENDPOINT 1
https://mcp.apihub.io/mcp
MCP server metadata
- Name
- apihub
- Version
- 1.0.0
APIHub - Discover and call paid APIs with USDC credits. No wallet required. Run `apihub_search` to find APIs, then `apihub_call` to invoke them. Sign up at https://apihub.io to get your API key.
Known tools 9
apihub_get_serviceGet full details for a specific API service including all endpoints, schemas, and pricing.
Inferred read-onlyapihub_search_externalSearch external x402-protected APIs (not operated by APIHub, but callable via credits).
Inferred read-onlyapihub_call_externalCall an external x402-protected URL (any provider in the marketplace or any x402 API).
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.apihub]
url = "https://mcp.apihub.io/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"apihub": {
"type": "http",
"url": "https://mcp.apihub.io/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: apihub
Remote MCP URL: https://mcp.apihub.io/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": {
"apihub": {
"url": "https://mcp.apihub.io/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"apihub": {
"type": "http",
"url": "https://mcp.apihub.io/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "apihub",
"transport": "streamable-http",
"url": "https://mcp.apihub.io/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Trust Data Available
BuiltWith Trust API v2 evidence for apihub.io was fetched 2026-09-25T10:12:39.185Z.
apihub.io is assessed as Trusted: Domain has an established technology history spanning over a year.
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.