
Wraps Gong's v2 API via OAuth so you can pull conversation intelligence data into Claude. Right now it exposes a single tool to list workspace users with their roles, emails, and activity status. Part of the Pipeworx gateway ecosystem, which means you can either use this standalone or tap into their broader collection of 673+ data sources. The ask_pipeworx interface lets you query in natural language instead of calling tools directly. Useful if you're building workflows that need to correlate Gong call data with team structure, or if you want conversational access to your sales intelligence platform without switching contexts.
Gong MCP — wraps the Gong API v2 (OAuth)
Part of Pipeworx — an MCP gateway connecting AI agents to 1476+ live data sources.
| Tool | Description |
|---|---|
gong_list_calls | List recorded calls from your workspace with optional date filtering. Returns call IDs, dates, participants, duration, and engagement metrics. Supports pagination for large result sets. |
gong_get_call | Get full details for a specific call by ID. Returns participants, duration, call metadata, engagement metrics, and key moments. |
gong_get_transcript | Retrieve the full conversation transcript for a call with speaker names, timestamps, and dialogue. Use after gong_get_call to analyze specific conversations. |
gong_list_users | List all users in your workspace. Returns user names, IDs, email addresses, roles, and activity status. |
gong_search_calls | Search calls by keyword or phrase (e.g., 'pricing', 'objection', 'budget'). Returns matching calls ranked by relevance. |
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"gong": {
"url": "https://gateway.pipeworx.io/gong/mcp"
}
}
}
tools/list at https://gateway.pipeworx.io/gong/mcp returns the tools in the table
above plus the shared Pipeworx meta-tools — ask_pipeworx,
discover_tools, search_within, remember/recall and the rest of the
gateway-wide set. So the tool count you see is larger than this table: a
single-pack endpoint currently lists roughly 30 shared tools alongside the
pack's own. The connection's initialize response states its exact scope, and
is the authoritative answer for a given day.
This is deliberate, not multiplexing by accident. The meta-tools are what let a
scoped connection answer a question this pack does not cover — via
ask_pipeworx, which routes across the whole catalog — without you adding a
second MCP server. There is currently no way to mount a pack endpoint without
them; if the extra schemas cost you more context than the routing is worth,
connect to the full gateway once rather than to several pack endpoints.
Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:
{
"mcpServers": {
"pipeworx": {
"url": "https://gateway.pipeworx.io/mcp"
}
}
}
Both URLs reach the same gateway and the same 1476+ data sources. The
only difference is which pack's tools are listed directly; ask_pipeworx
reaches all of them from either one.
Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:
ask_pipeworx({ question: "your question about Gong data" })
The gateway picks the right tool and fills the arguments automatically.
MIT