Skip to main content
MindBridge MCP uses your existing MindBridge identity and permissions. The connection is read-only, and an App Admin controls which users and applications can reach MindBridge through MCP. An App Admin is the MindBridge role with full access to the tenant. When you use MCP, information retrieved from MindBridge is sent to your connected AI assistant. Your organization should use an approved AI provider and review how that provider handles sensitive information. MindBridge’s data protections do not automatically extend to that assistant, and MindBridge does not operate or control third-party AI assistants. Use of MCP remains subject to your organization’s applicable agreement with MindBridge, including the Terms of Use and related service documentation. By enabling MCP access, you acknowledge that you have reviewed the considerations described on this page and are authorized by your organization to enable the connection. Use this page for a security or acceptable-use review. Connection steps are in Get Started. Retention and regional processing are in Data Processing and Retention.

How MindBridge protects access

MCP gives a compatible AI assistant read-only access to completed analyses the signed-in user can already see in MindBridge. The assistant cannot create, change, or delete MindBridge records, ingest data, run analyses, or perform Insights workflows. There is no write permission for this connection. MCP is not enabled by default. MindBridge must first make MCP available for the environment. An App Admin then enables the global toggle on Admin → MCP, chooses the scopes users may approve, and can add user overrides. Each user authorizes their own connection with OAuth 2.1, using their normal sign-in and your organization’s existing identity controls. You do not need API keys, service accounts, or shared credentials. Every request runs with that user’s MindBridge permissions. The assistant can access only the analyses available to that user. Restricting or removing their MindBridge access also restricts the connection. Users choose which read-only permissions to grant, within the limits an App Admin has set:
  • Analysis metadata to find analyses, describe their structure, and explain control points.
  • Analysis result data to query specific result rows or aggregates.
Granting only metadata access limits the assistant to structure and explanations. The assistant cannot retrieve underlying result rows. Revoking a connection in Admin → MCP stops further access through that application. See Manage or Revoke Access. MindBridge logging of MCP use is limited and depends on your contract. For customers on standard terms, MindBridge may retain anonymized tool call inputs for 30 days, such as analysis identifiers, keyword searches, and SQL generated by the assistant. If your organization has contracted out of section 5.2 of the standard terms, MindBridge logs tool names but not their inputs. See Data Processing and Retention. MindBridge is responsible for operating the MCP Server and enforcing access controls within MindBridge.

What to consider when using an AI assistant

Analysis data can leave your MindBridge environment and then be processed, stored, or shared in ways MindBridge does not control. The assistant queries results directly from your environment. Retrieved data may include sensitive customer, employee, journal, transaction, or vendor information, depending on the analysis. After that data is returned, the assistant provider’s terms govern that information. Those terms can include a different region, different retention, model training, or subprocessors. Before you allow a connection, ensure that the provider’s data retention, model training, processing locations, and sharing practices meet your organization’s requirements. Your organization’s approval to use an assistant is separate from the consent an individual grants when they connect. Read-only access in MindBridge still allows the assistant to retrieve and reproduce data. If the same assistant can create documents, publish content, or send email, the assistant may share retrieved information through those tools. Review the assistant’s other connections and do not pair MCP with tools that send or publish automatically unless your organization has approved that combination. Do not assume MindBridge logging is a complete record of what an assistant retrieved, stored, or shared. Copies in conversations, generated files, and the provider’s systems are outside MindBridge. Revoking a connection stops further access through that application. It does not delete information already retrieved. Manage those copies through the AI provider’s controls and your organization’s procedures. An assistant may misinterpret a field, apply an incorrect filter, summarize only part of an analysis, or generate conclusions that are not fully supported by the underlying analysis results. Before relying on an answer:
  • Confirm that the assistant used the intended analysis, risk score, and filters.
  • Check whether the result is a limited list or represents all relevant records.
  • Verify important figures and explanations against the analysis in MindBridge.
  • Review generated content before sharing it or using it in reports or audit documentation.
A high-risk score alone is not evidence of fraud, error, or non-compliance. Use MindBridge results alongside the analysis context and your professional judgment. Customers are responsible for selecting and governing their AI assistant and reviewing AI-generated responses for their intended use.