Enterpret MCP Server

The Enterpret MCP server brings your customer feedback — themes, accounts, sentiment, verbatim quotes — into Claude, Cursor, Notion, and Glean. This article covers what it can do, how to set it up, and how to troubleshoot a connection.

Key capabilities:

• Query the customer feedback available to the authenticated Enterpret connection.

• Request answers with source links and verify the underlying records; citation availability can depend on the tool and rollout.

• Retrieve customer quotes with available source and speaker attribution; check the quote and attribution against its source.

• Discover entities, taxonomy values, and source-specific metadata fields on demand

Setup Instructions

Claude (Web & Desktop)

Note: Connector availability and limits depend on your Claude plan and organization settings. Follow the options shown in Claude and its current connector documentation.

Pro and Max

Click here to add Enterpret to Claude, then click Connect to authorize access.

...or, find it manually:

1. Open Claude and click Customize in the sidebar

2. Click Connectors

3. Click the + button

4. Search "Enterpret"

5. Click Connect to authorize access

Ask your question directly — no initialization step is required.

Team and Enterprise

Setting up Enterpret for your team is a two-step process: an admin adds the connector for the organization, then each team member connects individually.

Step 1: Admin adds the connector

Click here to add Enterpret to Claude, then click Add to enable it for your organization.

...or, find it manually:

1. Navigate to Admin settings > Connectors

2. Search for "Enterpret" in the Connectors Directory and click Add

Then:

1. Navigate to Settings > Connectors

2. Find Enterpret in the list and click "Connect" to authorize access

Adding the connector makes it available to the team. In the individual sign-in flow described here, each member still connects and authorizes their own account; organization enablement alone does not grant data access.

Step 2: Members connect individually

Click here to add Enterpret to Claude, then click Connect to authorize access.

...or, find it manually:

1. Navigate to Settings > Connectors

2. Find Enterpret in the list of available connectors

3. Click "Connect" to authorize access

Ask your question directly — no initialization step is required.

Each member authenticates with their own account — queries and usage are tracked individually.

Claude Code

1. Open Terminal (or Command Prompt on Windows) and run:

   claude mcp add --transport http --scope user enterpret https://wisdom-api.enterpret.com/server/mcp

2. Start Claude Code:

   claude

3. Run the /mcp command, select Enterpret from the list of MCP servers, then click "Authenticate" to complete the authentication flow

Ask your question directly — no initialization step is required.

Cursor

Quick Install (Recommended)

1. In your Enterpret dashboard, navigate to Settings > Enterpret MCP

2. Click the Connect button next to Cursor

3. This will start the configuration process in Cursor with your organization's MCP settings prefilled

Ask your question directly — no initialization step is required.

ChatGPT

Use the Enterpret plugin to query customer feedback directly from ChatGPT.

1. Open the Enterpret plugin in ChatGPT. You can also get there from your Enterpret dashboard: go to Settings > Enterpret MCP and click Connect next to ChatGPT.

2. Install the plugin and follow the prompts to sign in to Enterpret and authorize the connection.

3. Start a new chat. Type @ to select Enterpret, or ask ChatGPT to use Enterpret to answer your customer-feedback question.

For installation and workspace controls, see OpenAI's plugins guide.

Codex App

Use the Enterpret plugin in the Codex desktop app to query customer feedback from your workspace.

1. In your Enterpret dashboard, go to Settings > Enterpret MCP.

2. Click Connect next to ChatGPT Codex. Allow your browser to open the Codex desktop app.

3. Install the Enterpret plugin and follow the prompts to connect your Enterpret account.

4. Start a new chat and ask Codex to use Enterpret to answer your customer-feedback question.

For command-line setup, follow the Codex CLI instructions below.

Codex CLI

Open Terminal and run:

codex mcp add enterpret --url https://wisdom-api.enterpret.com/server/mcp

Ask your question directly — no initialization step is required.

Notion Custom Agents

Where enabled, connect Enterpret to a Notion Custom Agent to research feedback in a configured workflow. Authenticate the connection and select the tools that agent may use; support depends on the host and connection settings.

Follow the step-by-step setup in Enterpret in Notion Custom Agents.

Note: Notion currently documents MCP connections for Business and Enterprise plans. For a custom server, a workspace admin enables custom MCP servers in Settings → Connections → Manage and controls which connections members may install. Authenticate the connection for each Custom Agent.

Glean

Connect Enterpret to Glean so users can query customer feedback from the Glean Assistant and wire Enterpret tools into Glean Agent Builder workflows. Glean is admin-managed — a Glean workspace admin sets up the connection once in the Admin Console, and every authorized user gets access to it.

In Glean, go to Admin Console → Platform → Actions, click Add, and choose Import tools from MCP server. Use the following configuration:

• MCP server URL: https://wisdom-api.enterpret.com/server/mcp

• Transport type: Streaming HTTP

• Authentication: OAuth (recommended) or Bearer token from Settings → MCP in your Enterpret dashboard

Once connected, an admin can enable individual Enterpret tools for the Glean Assistant and for Agent Builder, and apply role-based access to control which creators can use them in agents. For the full admin walkthrough, see Glean's documentation: Connect Remote MCP Servers to Glean.

Other AI Tools

For MCP-compatible AI tools not listed above, use this URL to connect to the Enterpret MCP: https://wisdom-api.enterpret.com/server/mcp

Ask your question directly — no initialization step is required.

--header "Authorization: Bearer YOUR_AUTH_TOKEN_HERE"

{
  "mcpServers": {
    "enterpret": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://wisdom-api.enterpret.com/server/mcp",
        "--header",
        "Authorization: Bearer YOUR_AUTH_TOKEN_HERE"
      ]
    }
  }
}

Available Tools

Your AI assistant can choose from the tools exposed by the connection. The names below describe the newer catalog; available names depend on the current rollout and your connection. Follow the tool list your client actually receives.

1. get_organization_details — Identifies your Enterpret organization, so answers link back to your dashboard.

2. get_graph_schema — Lets the assistant see what kinds of feedback you track and how it's organized.

3. get_query_examples — Gives the assistant reference patterns for common kinds of feedback questions before it answers.

4. search_graph_fields — Surfaces integration-specific data points like Zendesk tags, App Store ratings, or Gong call metadata.

5. search_graph_values — Looks up the exact themes, accounts, sources, or taxonomy values in your data, so the assistant searches and filters on real labels.

6. run_graph_query — Pulls the feedback that answers your question, with citation links back to source records.

7. find_user_quote — Surfaces verbatim customer quotes from the records behind your answer.

Migrating from older tool names? Depending on availability, you may see get_schema, execute_cypher_query, and search_knowledge_graph or the newer names above. Supported legacy names remain callable. Refreshing or reconnecting updates a cached tool list, but does not by itself enable a catalog that is unavailable to your connection.

Citations and quotes

Enterpret MCP provides tools for researching the underlying feedback and retrieving supporting evidence. The host AI assistant writes the answer, so review its scope, claims, and source links.

Citations on every claim

When a result includes a count or percentage citation, open it to inspect the supporting records and check the population, filters, and time window. Citation coverage can be incomplete, and not every computed value has a record link. Verify unsupported numbers before relying on them.

Customer quotes in their own words

Request verbatim customer quotes with source links. Check the returned wording and available speaker or company attribution against the original feedback. Quote coverage can be incomplete; an AI assistant's response is not a guarantee that suitable quotes exist or that every attribution is present.

Frequently asked questions