Gongio Mcp

Gong MCP Server

[](https://www.npmjs.com/package/gongio-mcp) [](https://opensource.org/licenses/MIT)

An MCP (Model Context Protocol) server that provides access to your Gong.io data. Query calls, transcripts, users, keyword trackers, and more directly from Claude or any MCP-compatible client.

Tools Quick Reference

| Tool | Description | |------|-------------| | [list_calls](#listcalls) | List calls with date/workspace filtering | | [get_call](#getcall) | Get metadata for a specific call | | [get_call_summary](#getcallsummary) | AI summary: key points, topics, action items | | [get_call_transcript](#getcalltranscript) | Full speaker-attributed transcript (paginated) | | [search_calls](#searchcalls) | Rich call search — participant, customer, tracker, scope, duration, title, and more | | [search_calls_by_account](#searchcallsbyaccount) | Find calls involving a specific account/company by email domain | | [search_calls_by_opportunity](#searchcallsbyopportunity) | Find calls linked to specific CRM Opportunities | | [search_transcripts](#searchtranscripts) | Free-text keyword search across transcript sentences | | [get_trackers](#gettrackers) | List keyword trackers (competitors, topics, etc.) | | [list_workspaces](#listworkspaces) | List workspaces and get IDs for use in other tools | | [list_library_folders](#listlibraryfolders) | List public call library folders | | [get_library_folder_calls](#getlibraryfoldercalls) | Get calls saved in a specific library folder | | [get_user](#getuser) | Get a specific user's profile | | [search_users](#searchusers) | Search/filter users by IDs or creation date | | [list_users](#listusers) | List all workspace users |

Response Size & Context Limits

search_calls can return a lot of data. Under the hood it:

• Auto-paginates up to ~5000 calls (50 API pages) per query
• Applies client-side filters (participant, customer, tracker, duration, etc.) after pagination
• Returns a rich per-call format (metadata + summary + topics + participants) by default

Guardrails built in:

• If the formatted output would exceed MAX_MCP_OUTPUT_LENGTH (default 50000 chars, configurable via env var), the tool automatically falls back to a compact table with a warning. You still get every call ID and title — drill in with get_call_summary on specific ones.
• include: ["outline"] is expensive (~80KB per call). Avoid it in multi-call searches.
• Tracker data is filtered to only show trackers matching your trackers filter (or non-zero trackers if no filter) — no more walls of (0x) noise.

If your query hits the output cap, narrow it:

1. Tighten fromDateTime / toDateTime
2. Add scope: "External" or scope: "Internal"
3. Add minDuration: 600 to skip short no-shows
4. Add customerName or trackers filter
5. Drop heavy include options like outline

Prerequisites

• Node.js 18+ or Docker
• Gong API credentials (Access Key and Secret)

Getting API Credentials

1. Log into Gong as an admin
2. Go to Company Settings → Ecosystem → API
3. Click Create API Key
4. Save both the Access Key and Secret (the secret is only shown once)

Installation

Option 1: npx (no install required)

npx gongio-mcp

Option 2: Global npm install

npm install -g gongio-mcp
gongio-mcp

Option 3: From source

git clone https://github.com/JustinBeckwith/gongio-mcp.git
cd gongio-mcp
npm install
npm run build
node dist/index.js

Option 4: Docker (build locally)

git clone https://github.com/JustinBeckwith/gongio-mcp.git
cd gongio-mcp
docker build -t gongio-mcp .
docker run --rm -i \
  -e GONG_ACCESS_KEY=your-access-key \
  -e GONG_ACCESS_KEY_SECRET=your-secret-key \
  gongio-mcp

Configuration

Set your Gong credentials as environment variables:

export GONG_ACCESS_KEY="your-access-key"
export GONG_ACCESS_KEY_SECRET="your-secret-key"

Or pass them inline:

GONG_ACCESS_KEY=your-key GONG_ACCESS_KEY_SECRET=your-secret npx gongio-mcp

Client Setup

Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):

Using npx:

{
  "mcpServers": {
    "gong": {
      "command": "npx",
      "args": ["gongio-mcp"],
      "env": {
        "GONG_ACCESS_KEY": "your-access-key",
        "GONG_ACCESS_KEY_SECRET": "your-secret-key"
      }
    }
  }
}

Using Docker:

{
  "mcpServers": {
    "gong": {
      "command": "docker",
      "args": ["run", "--rm", "-i",
               "-e", "GONG_ACCESS_KEY",
               "-e", "GONG_ACCESS_KEY_SECRET",
               "gongio-mcp"],
      "env": {
        "GONG_ACCESS_KEY": "your-access-key",
        "GONG_ACCESS_KEY_SECRET": "your-secret-key"
      }
    }
  }
}

Claude Code

Using npx:

claude mcp add gong -e GONG_ACCESS_KEY=your-key -e GONG_ACCESS_KEY_SECRET=your-secret -- npx gongio-mcp

Using Docker (after docker build -t gongio-mcp .):

claude mcp add gong -e GONG_ACCESS_KEY=your-key -e GONG_ACCESS_KEY_SECRET=your-secret -- docker run --rm -i -e GONG_ACCESS_KEY -e GONG_ACCESS_KEY_SECRET gongio-mcp

Available Tools

list_calls — List Gong calls with date filtering

List calls with optional date range and workspace filters. Returns minimal call metadata (ID, title, date, duration).

Parameters:

| Parameter | Required | Description | |-----------|----------|-------------| | fromDateTime | No | Start date in ISO 8601 format (e.g., 2024-01-01T00:00:00Z) | | toDateTime | No | End date in ISO 8601 format (e.g., 2024-01-31T23:59:59Z) | | workspaceId | No | Filter calls by workspace ID (use list_workspaces to find IDs) | | cursor | No | Pagination cursor for next page |

get_call — Get metadata for a specific call

Get the URL, timing, direction, scope, system, and other metadata for one call. Faster than get_call_summary when you only need call metadata.

Parameters:

| Parameter | Required | Description | |-----------|----------|-------------| | callId | Yes | Gong call ID (numeric string) |

getcallsummary — AI-generated call summary

Get an AI-generated summary including brief overview, key points, topics, action items, and detailed outline. This is the recommended way to understand a call — use get_call_transcript only if you need exact quotes.

Parameters:

| Parameter | Required | Description | |-----------|----------|-------------| | callId | Yes | Gong call ID (numeric string) |

getcalltranscript — Full speaker-attributed transcript

Get the raw transcript with speaker attribution. Transcripts are paginated (default 10KB) to prevent context overflow — use maxLength and offset to navigate.

Parameters:

| Parameter | Required | Description | |-----------|----------|-------------| | callId | Yes | Gong call ID (numeric string) | | maxLength | No | Maximum characters to return (default: 10000, max: 100000) | | offset | No | Character offset to start from for pagination (default: 0) |

search_calls — Advanced call search

Search calls with advanced filters including participant lookup, customer name search, and rich content selection. Automatically paginates through all results and returns participant info, brief summary, and topics by default.

Parameters:

Date & workspace

| Parameter | Description | |-----------|-------------| | fromDateTime | Start date in ISO 8601 format | | toDateTime | End date in ISO 8601 format | | workspaceId | Filter by workspace ID (use list_workspaces to find IDs) | | callIds | Array of specific call IDs to retrieve |

Host / participant

| Parameter | Description | |-----------|-------------| | primaryUserIds | Host user IDs (server-side) | | primaryUserEmails | Host emails (case-insensitive) | | excludePrimaryUserIds | Exclude these host user IDs | | participantUserIds | Any participant (host/attendee/invitee) user IDs | | excludeParticipantUserIds | Exclude calls where any participant has these user IDs | | participantEmails | Any participant emails (case-insensitive) | | excludeParticipantEmails | Exclude calls where any participant has these emails |

Content & customer

| Parameter | Description | |-----------|-------------| | customerName | Fuzzy match against CRM account name, external email domains, and titles | | titleContains | Substring match on call title (case-insensitive) | | trackers | Calls where matching tracker(s) fired (count > 0). Workspace-specific — use get_trackers to discover |

Metadata

| Parameter | Description | |-----------|-------------| | scope | External, Internal, or Unknown | | direction | Inbound, Outbound, Conference, or Unknown | | system | Conferencing platform (e.g., Zoom) — case-insensitive substring | | language | Language code (e.g., eng) — case-insensitive exact match | | minDuration | Minimum duration in seconds | | maxDuration | Maximum duration in seconds |

Response shape

| Parameter | Description | |-----------|-------------| | include | Additional data to return — see table below |

include options:

| Value | What it adds | Size | |-------|-------------|------| | keyPoints | AI-extracted key points as bullets | ~5KB/call | | trackers | Keyword/smart tracker hits with counts | ~3KB/call | | highlights | AI-curated highlight clips grouped by theme | ~3KB/call | | speakers | Talk time per participant | ~1KB/call | | comments | Public comments left on the call | varies | | context | CRM account/opportunity linkage (HubSpot, Salesforce) | ~1KB/call | | outline | Full section-by-section outline with items | ~80KB/call (large) | | media | Audio/video URLs (valid 8 hours) | ~3KB/call |

Defaults (always returned): participants, brief summary, and topics — ~3KB per call.

Filter behavior notes:

• Filters combine with AND logic. primaryUserIds + participantUserIds compose: primary narrows server-side, participant post-filters.
• customerName matches any of: CRM account Name field, external participant email domain, or call title (case-insensitive substring).
• trackers names are workspace-specific — call get_trackers first to see what's configured. Match is case-insensitive substring (so "competitor" matches both "Competitors" and "Competitor Mentions").
• When trackers filter is set, the relevant tracker content is auto-included and the output shows only the trackers you asked about. Without a filter, only non-zero trackers are shown.
• An empty result returns "No calls found" rather than an error.

See [Response Size & Context Limits](#response-size--context-limits) for how large-result fallback works.

searchcallsby_account — Find calls by account/company (email domain)

Find calls involving a specific account or company by matching the email domains of external participants. The Gong API does not natively support filtering by account name (a known gap) — this tool fetches calls in the date range and post-filters on parties[].emailAddress. Auto-paginates the underlying /v2/calls/extensive endpoint up to maxCalls.

Use this when:

• A prospect has multiple email domains (acme.com, acme.io, regional TLDs) and you need them all
• You need to join external enrichment data (e.g., "all prospects on Klaviyo" from BuiltWith / Clearbit / a vendor-stack graph) — resolve to a domain list upstream and pass it here
• Domain-based matching is more reliable than CRM Account names that drift across systems

Parameters:

| Parameter | Required | Description | |-----------|----------|-------------| | domains | Yes | Email domains, e.g. ["acme.com", "acme.io"]. A call matches if any external participant has an email at one of these domains. | | fromDateTime | No | Start date in ISO 8601 format | | toDateTime | No | End date in ISO 8601 format | | workspaceId | No | Filter by workspace ID | | primaryUserIds | No | Pre-narrow by call host user IDs (faster, server-side) | | matchCrmAccount | No | Also match where a CRM Account context object name contains a domain root (e.g. "acme" from "acme.com"). Requires CRM integration. Default false. | | maxCalls | No | Max calls to fetch & filter (default: 500, max: 5000). Auto-paginates underlying API. | | cursor | No | Pagination cursor (advanced) |

Cost note: This is fetch-then-filter. A 90-day window with no other narrowing typically pages through 1–5 API calls. Combine with primaryUserIds to bound cost on long ranges.

searchcallsby_opportunity — Find calls linked to a CRM Opportunity

Find calls linked to specific CRM Opportunities by ID or name substring. Requires Gong-CRM integration (Salesforce / HubSpot) — calls without CRM linkage will not match.

Use this when:

• You want every call on a specific deal — opportunityIds: ["006xxxxx"] is the most precise option
• Opportunity names are descriptive (e.g. "Acme Q4 Renewal") and you want fuzzy matching across renamed/duplicated opportunities

Parameters:

| Parameter | Required | Description | |-----------|----------|-------------| | opportunityIds | At least one of opportunityIds or opportunityNames is required | CRM Opportunity IDs (e.g., Salesforce 18-character IDs) | | opportunityNames | At least one of opportunityIds or opportunityNames is required | Name substrings (case-insensitive) matched against the Name field of Opportunity context objects | | fromDateTime | No | Start date in ISO 8601 format | | toDateTime | No | End date in ISO 8601 format | | workspaceId | No | Filter by workspace ID | | primaryUserIds | No | Pre-narrow by call host user IDs | | maxCalls | No | Max calls to fetch & filter (default: 500, max: 5000) | | cursor | No | Pagination cursor (advanced) |

Cost note: Uses the same fetch-then-filter pattern as search_calls_by_account. CRM context lookup adds no extra API calls — it rides on the same /v2/calls/extensive request with context: "Extended".

search_transcripts — Free-text keyword search across transcripts

Free-text keyword search across call transcript sentences within a bounded date range. Two-phase: (1) /v2/calls/extensive narrows the call set by date + optional primaryUserIds / domains, (2) /v2/calls/transcript fetches transcripts for the narrowed set and returns sentence-level matches with speaker attribution and timestamps.

Prefer Gong Trackers for recurring terms. For competitor names, ESP/tech terms (Klaviyo, Braze, Iterable, Postscript, Attentive, Sendgrid, Customer.io, etc.), and other terms you'll search for repeatedly — set them up as Gong Trackers in the UI (one-time, ~30 minutes for ~20 terms). Then use get_trackers + search_calls + get_call_summary instead. Trackers are server-side, the cost is dramatically lower, and they surface counts and timestamps natively. Use search_transcripts for ad-hoc one-offs.

Cost guard: Date ranges greater than 30 days require additional narrowing via primaryUserIds or domains. A 6-month unbounded scan would burn API quota and is rejected at the schema level.

Parameters:

| Parameter | Required | Description | |-----------|----------|-------------| | keywords | Yes | Keywords to search for. Each must be at least 2 characters. | | fromDateTime | Yes | Start of date window (ISO 8601). | | toDateTime | Yes | End of date window (ISO 8601). | | primaryUserIds | Required if window > 30 days and domains not set | Narrow to calls hosted by these users before scanning | | domains | Required if window > 30 days and primaryUserIds not set | Narrow to calls with external parties from these domains before scanning | | workspaceId | No | Filter by workspace ID | | caseSensitive | No | Default

…

Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: JustinBeckwith
• Source: JustinBeckwith/gongio-mcp
• License: MIT

Install and usage instructions live in the source repository linked above.