API Tools
integrations.sh
Detects and maps a domain's agent-readiness and public integration surface, including MCP servers, REST/OpenAPI, GraphQL, CLIs, SDKs, webhooks, and authentication methods.
ENDPOINT 1
https://integrations.sh/mcp
MCP server metadata
- Name
- integrations.sh
- Version
- 0.1.0
Known tools 2
detectDetect a domain's agent-readiness: well-known manifests (integrations.json, api-catalog, MCP server-card, agent-card, agent-skills, llms.txt) plus live capability detection — MCP self-onboarding (DCR/CIMD) and the live OpenAPI schema.
Inferred read-onlydiscoverMap a domain's complete public integration surface for agents — MCP servers, REST/OpenAPI, GraphQL, CLIs, SDKs, webhooks — plus how to authenticate (per method: where to get the credential and how to pass it).
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.integrations-sh]
url = "https://integrations.sh/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"integrations-sh": {
"type": "http",
"url": "https://integrations.sh/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: integrations-sh
Remote MCP URL: https://integrations.sh/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": {
"integrations-sh": {
"url": "https://integrations.sh/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"integrations-sh": {
"type": "http",
"url": "https://integrations.sh/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "integrations-sh",
"transport": "streamable-http",
"url": "https://integrations.sh/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.