Connect
Optimize
Secure
Gong MCP Server
for AI Agents
Production-ready Gong MCP server with 34 extensible actions — plus built-in authentication, security, and optimized execution.
Gong MCP Server
Built by 
StackOne
StackOne 
Coverage
34 Agent Actions
Create, read, update, and delete across Gong — and extend your agent's capabilities with custom actions.
Authentication
Agent Tool Authentication
Per-user OAuth in one call. Your Gong MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →
Security
Agent Protection
Every Gong tool response scanned for prompt injection in milliseconds — 88.7% accuracy, all running on CPU.
Prompt Injection Defense →
Performance
Max Agent Context. Min Cost.
Free up to 96% of your agent's context window to enhance reasoning and reduce cost, on every Gong call.
Tools Discovery →What is the Gong MCP Server?
A Gong MCP server lets AI agents read and write Gong data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Gong MCP server ships with 34 pre-built actions, fully extensible via the Connector Builder — plus managed authentication, prompt injection defense, and optimized agent context. Connect it from MCP clients like Claude Desktop, Cursor, and VS Code, or from agent frameworks like OpenAI Agents SDK, LangChain, and Vercel AI SDK.
All Gong MCP Tools and Actions
Every action from Gong's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Calls
- Add Call
Manually add a new call that has already occurred
- List Calls
List calls that took place during a specified date range
- Get Call
Get detailed information about a specific call
CRM Integrations
- Get CRM Integration
Returns the CRM integration details
- Delete CRM Integration
Asynchronously deletes a CRM integration and all its associated objects
Meetings
- Create Meeting
Create a new Gong meeting
- Update Meeting
Update an existing Gong meeting
- Delete Meeting
Delete a Gong meeting
Scorecards
- List Scorecards
List all scorecards in the Gong system
- Get Scorecards
Get answered scorecards for reviewed users or calls
Tasks
- List Tasks
List Engage tasks assigned to a specific user
- Update Task
Update an Engage task's status or due date
Users
- List Users
List all users in the Gong workspace
- Get User
Get a specific user by ID
- Search Users
Search users with filters
Other (19)
- Add Call Media
Upload a media file for an existing call
- Upload CRM Schema
Add, edit or remove fields to CRM entities
- Search Calls With Participant
Search for calls with extensive filtering and detailed data
- Get Call Transcript
Get transcripts for calls with optional filters
- List Call Outcomes
Retrieve the list of available call outcomes defined in Gong
- Get CRM Request Status
Returns the current status of asynchronous CRM requests
- Get CRM Objects
Returns CRM objects by their IDs (development phase only)
- List CRM Schema Fields
Retrieves a list of the object schema fields
- List Library Folders
Retrieve a list of public library folders
- Get Library Folder Content
Retrieve calls in a specific library folder
- Get Meeting Integration Status
Validate Gong meeting integration status for users
- List Trackers
List all keyword trackers in the system
- Get Aggregated Activity Statistics
Get aggregated activity statistics for users within a date range
- Get Activity Statistics By Period
Get aggregated activity statistics grouped by time period
- Get Daily Activity Statistics
Get daily activity statistics for users within a date range
- Get Interaction Statistics
Get interaction stats for users based on calls with Whisper enabled
- Get User Settings History
Get the settings history for a specific user
- List Workspaces
List all workspaces in Gong
- Register CRM Integration
Creates your CRM integration with Gong
Set Up Your Gong MCP Server in Minutes
One endpoint. Any framework. Your agent is talking to Gong in under 10 lines of code.
MCP Clients
Agent Frameworks
JSON{
"mcpServers": {
"stackone": {
"command": "npx",
"args": [
"-y",
"mcp-remote@latest",
"https://api.stackone.com/mcp?x-account-id=<account_id>",
"--header",
"Authorization: Basic <YOUR_BASE64_TOKEN>"
]
}
}
}More Sales MCP Servers
Lemlist
60+ actions
Apollo
45+ actions
Amplemarket
43+ actions
Salesloft
39+ actions
Reo.dev
8+ actions
Gong MCP Server Resources
MCP Code Mode: Keeping Tool Responses Out of Agent Context
Anthropic's code_execution processes data already in context. Custom MCP code mode keeps raw tool responses in a sandbox. 14K tokens vs 500.
11 min
Comparing BM25, TF-IDF, and Hybrid Search for MCP Tool Discovery
Benchmarking BM25, TF-IDF, and hybrid search for MCP tool discovery across 916 tools. The 80/20 TF-IDF/BM25 hybrid hits 21% Top-1 accuracy in under 1ms.
10 min
Indirect Prompt Injection Defense for MCP Tools: A Technical Guide
MCP tools that read emails, CRM records, and tickets are indirect prompt injection vectors. Here's how we built a two-tier defense that scans tool results in ~11ms.
12 min
Gong MCP Server FAQ
Gong MCP server vs direct API integration — what's the difference?
A Gong MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Gong. A Gong MCP server is for AI agents — MCP clients like Claude and Cursor, plus framework agents built with OpenAI, LangChain, or Vercel AI — discovering and calling Gong at runtime. StackOne provides both.
How does Gong authentication work for AI agents?
Gong authentication for AI agents works through a StackOne Connect Session. Create one via the dashboard or the SDK — you get an auth link and ready-to-paste config for Claude Desktop, Cursor, and other MCP clients. Your user authenticates their own Gong account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via
origin_owner_id.Are Gong MCP tools vulnerable to prompt injection?
Yes — Gong MCP tools can be vulnerable to indirect prompt injection. Any tool that reads user-written content — documents, messages, tickets, records, or free-text fields — is a potential vector. StackOne Defender scans every tool response before it enters the agent's context — regex patterns in ~1ms, then a MiniLM classifier in ~4ms. 88.7% accuracy, CPU-only.
What is the context bloat of a Gong agent and how do I avoid it?
Context bloat happens when Gong tool schemas and API responses eat your Gong agent's memory, preventing it from reasoning effectively. A single Gong query can return a massive JSON response, and connecting multiple tools compounds the problem. Tools Discovery and Code Mode reduce context bloat — loading only relevant tools per query and keeping raw responses out of the agent's context.
Can I limit which actions my Gong agent can access?
Yes — you can limit which actions your Gong agent can access directly from the StackOne dashboard. Toggle actions on or off, or restrict them to specific accounts, with no code changes to your agent. Session tokens can be scoped to exact actions so if one leaks, exposure stays contained.
Can I create custom agent actions for my Gong MCP server?
Yes — you can create custom agent actions for your Gong MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Gong's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Gong MCP server?
Skip a Gong MCP server if your integration is purely software-to-software — direct Gong API integration is simpler when no AI agent is involved. For deterministic, compliance-critical operations (financial transactions, regulatory reporting), direct API gives you predictable behavior without agent-driven decision-making. MCP shines when AI agents need to dynamically discover and call Gong actions at runtime.
What AI frameworks and AI clients does the StackOne Gong MCP server support?
The StackOne Gong MCP server supports both. MCP clients (paste-and-go apps): Claude Desktop, Claude Code, Cursor, VS Code, Goose. Agent frameworks (code SDKs you build with): OpenAI Agents SDK, Anthropic, Vercel AI, Google ADK, CrewAI, Pydantic AI, LangChain, LangGraph, Azure AI Foundry.
Put your AI agents to work
All the tools you need to build and scale AI agent integrations, with best-in-class connectivity, execution, and security.