Bitsight MCP: AI Governance and Data Handling

The Bitsight Model Context Protocol (MCP) server enables AI assistants to call Bitsight's APIs on your behalf. This article explains how your data is handled, what Bitsight stores and logs, and the safeguards in place to protect your information. For Bitsight's broader AI use policy, see the Bitsight AI use policy.

At a glance

Does Bitsight train AI models on my data or API calls?

No. Nothing flowing through the MCP is used to train, fine-tune, or improve any AI or machine learning model. Your API calls, prompts, and responses are never added to any training set.

Does the MCP store my data?

Bitsight does not store the data returned to you. Your ratings, findings, and other API responses pass through the MCP without being saved. To support debugging and security, the MCP logs the parameters of API calls your assistant makes (for example, a company GUID or a search term). Bitsight retains these logs in accordance with its data retention practices.

Can the MCP see data I'm not already entitled to?

No. The MCP uses your own identity and respects your Bitsight access controls, access groups, and product subscriptions. It can only access the data you're already authorized to view.

Are my requests and responses logged?

Not by default. Bitsight logs operational metadata only — tool name, timestamps, session IDs, account identifiers, and service metrics. The contents of your requests and responses are not logged.

Is there a safeguard before an AI changes my data?

Yes. By default, every operation that modifies data requires explicit confirmation before it executes. You can choose to waive confirmation for a limited time. See Data modification and confirmation.

How the MCP works

The MCP operates as a proxy. When your AI assistant makes a request, the MCP validates your credentials, forwards your authentication token to the appropriate Bitsight API, and returns the response. The MCP does not store API responses. It keeps only operational logs, call parameters, and a short-lived encrypted credential cache, as described in Data storage and logging.

Because the MCP uses your credentials, it adds no new data access. You can only reach data you're already entitled to see. A small set of generic tools allows the assistant to discover and call any of Bitsight's 1,000+ API operations, with all calls routed strictly against Bitsight's official API schemas.

Data modification and confirmation

Any operation that modifies data is blocked on the first attempt and only executes after an explicit, single-use confirmation that is valid for five minutes. This prevents an AI from silently changing your data.

You can also waive confirmation yourself. If you tell your assistant you trust it to make changes, the MCP temporarily skips confirmation, for no more than 24 hours.

Service accounts and automation you provision can be allowlisted to skip this confirmation requirement for specific pre-approved operations.

Data storage and logging

What Bitsight stores permanently

Only public documentation — API schemas and help-center articles — and their search index for performance optimization.

What Bitsight never stores

Your ratings, findings, Cyber Threat Intelligence data, or other Bitsight API responses.

How the MCP handles credentials

To avoid re-validating on every request, the MCP temporarily caches your credentials in encrypted form. It caches OAuth sign-ins longer than API token sessions so you do not need to sign in repeatedly. The MCP never writes your raw token to logs.

What Bitsight logs (operational telemetry and call parameter)

Tool name, timestamps, session and request IDs, your account identifier, upstream status and latency, usage counts, a one-way hash of your token (never the token itself), and API call parameters.

What Bitsight does not log

Responses returned by Bitsight APIs, including your ratings, findings, and other data.

What Bitsight sees, and why

Bitsight's operators can see operational telemetry and call parameters: That a call happened, which tool was used, what parameters were sent, which account made the call, when it occurred, and whether it succeeded. This telemetry is tied to your account and session IDs.

Bitsight uses this data only for three purposes: debugging, service monitoring, and over-utilization detection and rate limiting (60 requests per minute per user). The telemetry is not used for model training, and it does not inform data-access decisions. Those decisions are enforced entirely by your existing Bitsight entitlements.

Security and the AI boundary

Traffic between the MCP and Bitsight is encrypted using TLS 1.2 and 1.3. Databases are encrypted at rest. Secrets are managed through AWS Secrets Manager. The public MCP endpoint sits behind Cloudflare with rate limiting enabled.

Your prompts and results also pass through your chosen AI client — for example, the Anthropic API if you're using Claude, or your IDE vendor's servers if you're using an IDE extension. That boundary is outside Bitsight and governed by your AI provider's terms of service.

No model training

Bitsight does not use your API calls, prompts, or responses to train any AI or machine learning model. The MCP is a gateway, not a learning system. Its only machine learning feature is semantic search over public content: Bitsight's published API documentation and help-center articles. Your data is never embedded, indexed, or added to any training set.