tl;dr: Gong MCP
- Gong’s documentation (7 October 2026) says Gong MCP returns AI-generated analysis of your calls, not the calls themselves, and that transcripts aren’t returned. Anthropic’s connector directory now lists a get_transcript tool for the same server. I couldn’t test which is current.
- Gong’s documentation lists three read-only tools: ask_account, ask_deal and generate_brief. Anthropic’s directory listing (19 October 2026) shows a fourth, get_transcript. Gong says private calls are excluded from all results.
- Every Gong MCP request consumes Gong credits, and asking the same question twice consumes them twice.
- Gong is now listed in Anthropic’s connector directory as a Community connector. A Gong tech admin still has to enable it, each user needs a paid Gong seat, and Claude users need Pro, Max, Team or Enterprise.
- Gong MCP is worth switching on if you already pay for Gong. It is not a reason to buy Gong.
- Checked by reading Gong’s documentation (rechecked 19 October 2026), Anthropic’s directory listing, and an unauthenticated inspection of the public mcp.gong.io endpoint on 1 September 2026. I have no Gong account, so nothing here is a hands-on test.
Gong MCP server allows your AI assistant to ask Gong detailed questions about all your sales deals, accounts, and pipeline. I bet if you’re a sales director, that sounds pretty good, right? Simply say, “Claude, what’s stopping the Acme deal from closing?” Ding, you have an answer without clicking directly into Gong. Well, it’s not quite that simple, I’m afraid.
For transparency, Gong is in the same category as tl;dv, and is known as an incredibly sales-focused product. It’s designed and created for revenue teams and those who sell, or manage those who sell. It’s also a bit secretive, with no self-serve trial, no free tier; the only way to find out if it’s any good, and how much Gong costs, is to go the sales route.
And there’s also been a bit of a kerfuffle over their pricing model lately. In June 2026, Gong switched to metered AI pricing. This means that each seat on your account has a credit allowance that AI features use. So you pay for the tool, you pay for the seat, and then you have a balance of how much you can ask it. There’s been, understandably, a bit of grumbling over this. Worth pointing out that because Gong is so private about numbers (believe me, I’ve tried hard over the years!), a lot of this is third-party information. If you want the fuller picture, Gong pricing covers what buyers report paying.
This means that Gong’s MCP server lands squarely in the AI credit usage, with one of the tools racking up those credit spends.
Again, full disclosure, I have no Gong account, and there is no way for me to test this firsthand without access. So I haven’t had access to poke around on the MCP server directly.
I did try to get a bit smart, though. On 1 September 2026, I did an unauthenticated endpoint inspection, which means I opened the terminal and looked at the public endpoint at mcp.gong.io without logging in. A server has to publish how to connect to it before anybody can connect, so that information is publicly reachable. Then I checked Gong’s own documentation against its partner pages and third-party listings of the same server, and rechecked it all on 19 October 2026.
What Is Gong MCP, and What Does It Do?
Gong MCP is a connector that allows an external AI assistant to query Gong and get answers. To use it, you connect it to Claude, ChatGPT, Microsoft Copilot or Salesforce Agentforce, the AI tools Gong supports, and Gong brings its read on a deal or account into your chat box.
The MCP is shorthand for Model Context Protocol, a shared way for AI assistants to communicate with other software without custom connectors for each pair. Gong runs its own server for this. Your assistant connects and it pulls the data.
But there’s one thing. Gong’s documentation says it has taken a different route from MCPs like tl;dv’s, which can pull transcripts when queried. According to Gong’s docs (updated 7 October 2026), the server returns AI-generated insights based on Gong data. It will take a look at and analyze calls and any communications within a specified time range and return a summarized response. So you’re getting the highlight reel effectively.
It’s read-only and that means it can’t change anything within Gong itself which is pretty standard.
So, on paper at least, Gong’s design choice is summarized responses rather than the raw data. More on why I say “on paper” below.
Gong also has something called the Gong MCP client, which is actually a separate product and works in reverse. This is Gong itself pulling in data from other products, using its AI features. For example, Gong says that AI briefer can reach into your support system so that it can flag up unresolved tickets prior to a renewal call.
What Can You Actually Ask Gong MCP?
Gong’s documentation lists three tools. Anthropic’s connector directory lists those three plus a fourth, get_transcript, which Gong doesn’t document anywhere I could find.
- ask_account
- ask_deal
- generate_brief
- get_transcript (directory listing only)
ask_account will answer a single question about one account. Gong says that this can be used for asking about customer concerns and pain points, digging into risk, and also for account review preparation. This is the kind of tool that can be used before your QBR when you want to know the status before you head into that meeting.
ask_deal is simply querying specific deals. What’s stopping it from closing, where is it in the sales journey, and what’s been promised? This is the one for sales reps that they can ask before a call with a client, or when prepping their pipeline to share.
generate_brief builds a summary of an account, deal or contact. This then generates an output, split into sections with stakeholders, themes, next steps, and whatever is needed to summarize the entire entity. It’s geared toward you if you’re a sales director and want a temperature check of any client or deal.
The mechanics of how each tool is selected, as stated by Gong, are that the AI should not use ask_account or ask_deal for anything broad, and should not use generate_brief for anything that is specific. So it’s largely dependent on how the prompt in the AI is worded.
Each documented tool returns a filtered answer, put through Gong’s own AI, and does not bring in raw activity. There’s a parameter called includeSources, but this is switched off by default and would add links into the calls and emails. This means that if you don’t specifically ask for sources, it won’t switch on, and you’ll be given an answer with no grounding.
Of the three tools Gong documents, there’s nothing to lay out what calls have happened, and nothing to read or fetch transcripts. The directory’s get_transcript suggests that may be changing, but I can’t confirm what it does without an account.
What Gong’s Documentation Says It Will Not Give You
According to Gong’s documentation, Gong MCP will not give you the exact words that someone has said. The docs describe it as an analysis of your calls, with no raw data and no email body text.
Gong’s documentation says its MCP gives you Gong’s own analysis of your call, and not the call itself.
The Gong REST API does offer this, and Gong’s docs describe the MCP as a question-and-answer tool.
So, hypothetically, you want to ask which accounts were negative about pricing last month. You’ll query the Gong MCP and will get back a paragraph naming accounts and giving more detail about the issues. You then ask for the verbatim transcript. Going by Gong’s documentation, it won’t be able to give it to you in the AI.
There’s the includeSources option. If it’s switched on, it gives you links to the source, but the documented tools can’t get that text into the assistant. So you can’t check the answer from inside your chat.
That’s where get_transcript matters. If it does return transcripts, this whole argument gets weaker, because you could pull the exact wording in and check Gong’s answer against it. I couldn’t test it, and Gong doesn’t document it, so for now I’m going with what Gong’s own docs say.
Now, on a slightly different note, we have undertaken a fair amount of testing of tools that offer transcription and summarization. This includes languages such as Japanese and Brazilian Portuguese. What I have found is that sometimes the transcription isn’t 100% on some tools, and sometimes the summaries can be a bit off the mark. This means that, if for any reason, the transcription or summary Gong has produced isn’t correct, then that will get pulled through. No tool is totally accurate, and being able to pull the exact wording into your AI, rather than relying on a summary, is a failsafe worth having.
Is Gong MCP Read-Only?
Yes. Gong clearly lays out that the MCP server only reads data; it cannot create, update, or delete anything in Gong or your CRM system.
One thing I do want to point out. When I did my unauthenticated endpoint inspection on 1 September 2026, the authorization metadata included a permission called mcp:write. Without having a full account to access it, I cannot state or know what this does. It could be a simple naming artifact rather than a hidden tool, but I can’t categorically confirm this either way.
How Much Does Gong MCP Cost to Run?
The million-dollar question, and one that is hard to answer fully. Each question that you ask the MCP server uses Gong credits.
Gong shows the mapping on its documentation. The two ask_ queries run on the ask-entity API; generate_brief runs on the get-brief API. APIs consume Gong credits because they use AI to generate insights, and they state clearly in the documentation that you must check that you have sufficient credits before querying.
Gong says running a request through the MCP costs the same credits as the equivalent API call. And asking a question or generating a brief inside Gong itself doesn’t spend MCP or API credits at all. Gong says nothing about get_transcript and credits, because it doesn’t document the tool.
What does that mean? Well, it means that every time you ask something, your credit goes down, and if you ask the same question twice, then you’re doubling your usage.
How much it uses depends on how much Gong has to read through. Gong names the time range and breadth as the things to pin down, and if you use a broad query with a large account, it’s going to eat up more of those credits.
This can mean… issues. Give ten reps access to this and tell them to ask it anything. The usage then depends on how much they want to know, and the more curious they are, the more it’s going to cost you. They actually publish a guide on how to reduce your credit consumption, so it’s clearly something that’s come up before.
Who Has To Set Up Gong MCP?
To get Gong MCP up and running, you’ll need the Gong tech admin. Tech admins are the people who enable the MCP server for the tools, and they’ll need to be the ones to flip the switch.
So someone with admin rights creates the connection; they then select which AI tools it communicates with and how it behaves. Then you get your sales reps to connect. This can be done in stages so that you can make sure it’s fit for purpose.
The admin is also the one who needs to choose access. Gong offers personal access, so the rep will only be able to see and query what is in their own Gong dash, or a single connection means that anything in Gong can be recalled for anybody.
There are gates on the user side too. Every user needs a paid Gong seat, and Collaborator accounts can’t connect at all.
When I first wrote this in September, Claude wasn’t on Gong’s list. It is now. Gong’s setup article, updated 16 September 2026, names Claude, ChatGPT and Microsoft Copilot, and there’s a separate guide for Salesforce Agentforce.
Gong has also turned up in Claude’s connector directory, where tl;dv is. It’s listed as a Community connector, made by Gong and added in August 2026. Community means it passed Anthropic’s automated review but hasn’t been verified by Anthropic.
That doesn’t skip the admin step. Your Gong tech admin still enables it in Gong, you sign in with your Gong account, and you need Claude Pro, Max, Team or Enterprise. You can also still add mcp.gong.io/mcp by hand as a custom connector, using the client ID and secret your admin gives you.
Is Gong MCP Good for a Sales Team?
If you already have Gong and know how Gong works, yes, switch it on. If you do not, Gong’s MCP is not the reason to choose Gong as your meeting recorder or your sales tool.
If your goal is pipeline awareness across lots of accounts, then yes. Anything that requires you to query the calls, dig into what was said and get more detail, no, at least going by Gong’s documentation.
It seems counterintuitive to have designed it this way, but there are two reasons as to why. The first is volume. If you have a large-scale operation with multiple teams of multiple reps, that is a lot of calls and data. Gong’s logic is that summarizing them within the system itself means it can prevent omissions or cuts when they are transferred elsewhere.
The second is governance. Call recordings can include sensitive data like pricing or customer complaints. By Gong sending answers rather than the source text, it means that detail doesn’t leave Gong.
Going by Gong’s docs, the same design that keeps your call data locked inside Gong is also what stops you spot-checking Gong’s answer in your AI. If get_transcript turns out to work, that changes.
If you’re a sales director tracking ten accounts, that’s fair, and you can still open Gong and check as you always have. But for a sales manager, fielding a team of many reps, coaching on things like objection handling, it makes it kind of tricky.
And if you’re not already a Gong customer, the cost of Gong itself is incredibly high before you even ask your first question. Gong doesn’t publish its pricing; it has no free trial, and each seat and platform costs money, onboarding costs money, and AI credits cost money. Each time the team asks a question, that costs money.
Gong MCP vs tl;dv MCP
Gong and tl;dv do very different things. Gong MCP is built for breadth. You can query your AI about an account and get a summary of what Gong’s read on it is. If you have a huge enterprise business, it’s a very quick way to get an answer fast.
tl;dv’s MCP server is built for retrieval. It can get the contents of the transcript when requested; its search can get into the body of the text rather than relying on a secondhand summary. You can ask what a buyer asked about an integration and get the exact sentence in their own words.
There are three practical areas where you’ll notice a difference.
You can check the answer. tl;dv’s MCP retrieves the body text of calls, so you can pull the exchange and read it. Gong’s docs say its MCP doesn’t return transcripts, and get_transcript is undocumented, so for now you’re relying on Gong’s summary.
Search works across the library. Say you remember the objection but not the customer. Gong’s documented tools each work on one named account, deal or contact, so you need to know which one to ask about. tl;dv can run a search across meetings, so ask it who mentioned this competitor last month and it’ll pull it.
Questions don’t cost extra. tl;dv doesn’t use AI credit each time you ask a question. That means if you ask the same question three times, then you’re not draining your allowance.
The difference is whether you can get back to what was actually said. Going by Gong’s documentation, Gong MCP tells you a customer raised a pricing objection. tl;dv shows you the sentence they said it in.
If you already run Gong, switch the connector on, and tell your team that, according to Gong’s docs, it returns Gong’s analysis rather than their calls, so nobody wastes an afternoon asking for quotes. If you are choosing a recorder now, decide on this: does your team need to know what is happening across accounts, or does it need to coach people on what was said? If it’s the second, then tl;dv is your answer, and it has a much more transparent pricing structure.
FAQs About Gong MCP
Does Gong have an MCP server?
Yes. Gong runs a hosted MCP server at mcp.gong.io/mcp, separate from its REST API. Gong’s documentation lists three read-only tools that return insights about accounts and deals, and Anthropic’s directory listing shows a fourth, get_transcript. A Gong tech admin has to switch it on before anyone can connect.
Does Gong MCP return call transcripts?
Gong’s documentation (7 October 2026) says no. Raw data, including call transcripts, message bodies and activity lists, isn’t returned. But Anthropic’s connector directory lists a get_transcript tool for Gong’s own server. Gong doesn’t document it, and without an account I couldn’t test whether it returns transcripts.
What tools does Gong MCP have?
Gong’s documentation lists three. ask_account and ask_deal answer questions about one account or one deal. generate_brief produces a structured summary of an account, deal or contact and doesn’t take a question. Anthropic’s directory listing adds a fourth, get_transcript, which Gong doesn’t document.
Does Gong MCP cost extra?
Yes, indirectly. Every request consumes Gong credits, at the same rate as the equivalent API call, and repeat questions consume them again. generate_brief costs more than the other two because each section of a brief adds to the total. Asking inside Gong’s own interface doesn’t spend MCP credits.
Can I connect Claude to Gong MCP?
Yes. Gong is listed in Anthropic’s connector directory as a Community connector, made by Gong. Your Gong tech admin still has to enable it, every user needs a paid Gong seat, Collaborator accounts can’t connect, and you need Claude Pro, Max, Team or Enterprise.
