Gong MCP server: what it exposes, how to connect Claude, and what it costs

Gong holds the best record most sales teams have of what customers actually said. The Gong MCP server lets Claude, ChatGPT, Microsoft Copilot and other MCP clients ask questions of that record without opening Gong. It is deliberately narrow, though: it does not hand your AI client transcripts, it hands it Gong's own analysis. This guide covers the admin setup, each client, the credit cost, and when another recorder's server fits better. For what else a sales team can connect, see AI for sales.

What the Gong MCP server exposes

The server lives at https://mcp.gong.io/mcp and exposes three tools:

Each tool analyses calls and emails within a time range and returns AI-generated text. A few properties shape everything else:

• Read-only. Gong states that the server does not create, update or delete data in Gong or the CRM.
• No raw data. Transcripts, email bodies and activity lists are not returned. You get Gong's synthesis, not the material.
• Sources on request. Each tool has an includeSources parameter, off by default. When on, the answer includes links to the calls and emails it was built from. Gong turns it on automatically when the prompt asks for sources.
• Private calls are excluded from every result.
• One entity per call. Accounts and deals can be looked up by name. For a contact brief you need the CRM contact ID.

That is a sensible design. Read-only removes the worst failure mode, an agent rewriting deal stages, and without transcripts a prompt injection in a customer email has less to work with. The trade-off is that you cannot ask the model to quote the exact sentence a buyer said, or run your own analysis across a hundred calls. If that is what you want, see the alternatives below.

Admin setup in Gong

Only a Gong tech admin can enable the server, and each person who connects needs a paid Gong seat. Collaborator seats cannot use it. The integration is created under Admin center, Settings, Ecosystem, MCP, MCP servers, New MCP server integration.

Two choices on that screen are permanent. Gong does not let you change them after saving, so you delete and recreate the integration if you get them wrong.

Registration type

• Automatic: no credentials. Any matching client, for example the ChatGPT Apps directory or the Microsoft Copilot marketplace, can connect after the user signs in to Gong. Gong notes that people may connect from personal AI accounts as well as company ones.
• Manual: Gong issues a client ID and secret that the admin installs in one specific AI client, such as a company Claude or ChatGPT workspace. Only that credential can connect, which blocks marketplace and personal-account connections for the company.

Authorization context

• Personal access (default): each user sees only what their Gong permissions already allow. Gong recommends this for Claude, ChatGPT and Copilot.
• Shared access: one token with organisation-wide access, and every user of the integration sees the same data. Gong positions it for backend or reporting agents.

For a team rolling this out to sellers, manual plus personal access is the right default. It keeps Gong data out of personal ChatGPT accounts and keeps a rep from querying deals they could not open in Gong. You can create several integrations for the same client if you also need a shared-access one for a RevOps agent.

Disabling an integration revokes all its tokens at once, which is the kill switch to know about.

Connecting your AI client

Claude (web and desktop). Gong is not in Claude's connector directory, so it goes in as a custom connector. In the Gong integration, add both redirect URIs:

https://claude.ai/api/mcp/auth_callback
https://claude.com/api/mcp/auth_callback

Then in Claude, add a custom connector with the URL https://mcp.gong.io/mcp, paste the client ID and secret into the advanced settings, and sign in to Gong when prompted. Custom connectors need a Pro, Max, Team or Enterprise plan. On Team and Enterprise an owner adds the connector for the organisation.

ChatGPT and Microsoft Copilot. These are the two clients Gong lists as available connectors. With an automatic integration, users find Gong in the ChatGPT Apps directory or the Copilot marketplace and sign in. Copilot Studio is supported too.

Claude Code. Gong does not document Claude Code, but its server uses standard OAuth with client credentials, which Claude Code supports. Because Gong matches the redirect URI you register, give Claude Code a fixed callback port and register http://localhost:8080/callback in the Gong integration:

claude mcp add --transport http \
  --client-id YOUR_GONG_CLIENT_ID --client-secret --callback-port 8080 \
  gong https://mcp.gong.io/mcp

--client-secret prompts for the secret. Then run /mcp in a session to complete the Gong sign-in. General client instructions are in adding an MCP server to Claude Code.

What sales teams actually ask it

The tools are built for one account or deal at a time, so the useful prompts are scoped the same way:

• Pre-call prep. "Brief me on the Acme deal: stakeholders, open risks and what we promised last time. Include sources."
• Deal review. "What is blocking the Northwind deal from closing, based on the last 30 days?"
• Objection mining per account. "Which objections and competitors came up on this account this quarter?"
• Handoffs. A generate_brief on the account when it moves from sales to customer success.
• Combined with the CRM. With the HubSpot MCP server or Salesforce MCP server in the same session: "List my open opportunities closing this month from Salesforce, then ask Gong for the main risk on each." The CRM gives the list, Gong gives the context.

What it does not do well: pipeline-wide questions such as "what are the top objections across all deals". Each tool works on one entity, and Gong's own advice is to use its AI trackers and reports for recurring cross-deal analysis.

Credits: the part people miss

Every call consumes Gong credits. Consumption depends on how much data is analysed, and it is the same whether the request comes through MCP or Gong's API. Gong's own guidance boils down to a few rules worth putting in your team's prompts, or better in a shared skill:

• Give a date range. "Last 30 days" or "this quarter". An unscoped question can analyse hundreds of emails on a large account.
• Ask about the deal, not the account, when the question is about one opportunity. Account queries cover every deal and contact under it.
• Combine related questions. Four questions about the same account analyse the same calls four times. One question asking for stakeholders, risks, priorities and competitors analyses them once.
• Keep briefs short. generate_brief analyses the conversations once per open-ended section. Gong suggests creating dedicated, slimmer briefs for MCP use, and using web search sections only when needed.
• Watch autonomous agents. An agent that loops over stakeholders or accounts one question at a time multiplies consumption fast. Scheduled briefs nobody reads still cost credits.

Alternatives for call notes: Fireflies and Fathom

If your team records calls in something other than Gong, or you need the transcript itself, two meeting tools ship official servers:

Fireflies gives the model far more raw material: search across meetings, full transcripts and summaries. That makes it better for cross-meeting questions like "what objections came up in this week's sales calls", and riskier, since customer words flow straight into the model's context. Fathom is in Claude's connector directory and has a ChatGPT app, so setup is a click (on Claude Team and Enterprise an owner enables it first). For Claude Code, Fathom documents a bridge through mcp-remote, which needs Node.js:

claude mcp add fathom -- npx mcp-remote@latest https://api.fathom.ai/mcp

Fathom's MCP docs cover setup but not the tool list, so check what the model can see after connecting before you decide what it may read.

Gong's design is the most conservative of the three. For a large sales org that is a feature: less data leaves Gong.

Running it for a whole sales team

The Gong admin controls cover who can connect and what they see. They do not cover the AI client side: which models a seller uses, what else is connected in the same session, or where prompts and answers are stored. A seller with Gong and an email-sending tool in one session is the combination that MCP security best practices warns about.

That is the gap an MCP gateway fills. Walma AI Hub runs Gong next to the CRM and the other approved servers behind one policy and one log, with every model available, inside the customer's own Azure tenant in an EU region. The sales-specific version of that setup is on AI for sales.