Confident AI Red Teaming (BYOK)

Confident AI Red Teaming (BYOK) — connector documentation

• MCP endpoint: https://byok-confident-ai-redteam.connectorbay.com/mcp
• REST API: POST https://byok-confident-ai-redteam.connectorbay.com/v1/tools/{tool_name}, described by the OpenAPI 3.1 spec at https://byok-confident-ai-redteam.connectorbay.com/openapi.json
• Transport: Streamable HTTP, stateless, MCP specification 2025-06-18 or later
• Authentication: your own Confident AI Red Teaming Confident AI project API key, sent in the X-Upstream-Key header of every request (never stored, logged or cached)
• Health: https://byok-confident-ai-redteam.connectorbay.com/health · Tool schemas: https://byok-confident-ai-redteam.connectorbay.com/tools.json
• Publisher: Unify Dynamics LLC · connectorbay.com/byok-confident-ai-redteam · agent@connectorbay.com

What Confident AI Red Teaming (BYOK) is for

Confident AI Red Teaming (BYOK) lets an AI assistant read your own Confident AI Red Teaming data through the Confident AI Red Teaming API with a key you supply (Confident AI project API key). Read-only: 6 tools (list_rt_frameworks, get_rt_framework, list_risk_categories, list_attack_methods, list_vulnerabilities, get_vulnerability). The BYOK key travels with each request, is used for that one call only and is never stored, logged or cached; it is only ever sent to api.confident-ai.com. Unofficial connector by Unify Dynamics LLC: not affiliated with, endorsed by or sponsored by Confident AI Red Teaming. Confident AI Red Teaming and its logos are trademarks of their owners and are used only to say which service the connector works with.

Ask your assistant things like:

• "Which red teaming frameworks are set up in my Confident AI project?"
• "Show the details of the Confident AI red teaming framework fw_1"
• "Which risk categories does the Confident AI framework fw_1 have?"
• "Which attack methods can Confident AI red teaming use?"
• "Which vulnerabilities can my Confident AI project red team for?"
• "Show how Confident AI evaluates the vulnerability Prompt Leakage"

What it does

• list_rt_frameworks: List the red teaming frameworks of the project (id, name, description) with each framework's risk categories and how many vulnerability types and attack methods they select.
• get_rt_framework: Get one red teaming framework with each risk category resolved to the vulnerabilities it probes for (criteria, guidelines) and the attack methods it uses.
• list_risk_categories: List the risk categories of one framework (id, name, description, number of vulnerability types and attack methods), ordered by name.
• list_attack_methods: List the catalog of attack methods (name, description, single or multi-turn, exploitability, configurable), ordered by name.
• list_vulnerabilities: List the vulnerabilities probed for, built-in and your own (id, name, description, category, number of types).
• get_vulnerability: Get one vulnerability with the evaluator criteria, guidelines, worked examples and the types it breaks down into.

BYOK key

You bring your own Confident AI Red Teaming Confident AI project API key (https://www.confident-ai.com/docs/settings/project/api-keys). Your assistant sends it in the X-Upstream-Key header with each request. ConnectorBay uses it for that one call only: it is never stored, logged or cached, never shown in an answer, and it is only sent to api.confident-ai.com over https, with no redirects followed. Create a key with the fewest permissions the tools need (read-only if the provider offers it), and revoke it at the provider whenever you like.

Notices

Reads the red teaming catalog and framework configuration only (names, descriptions, evaluator criteria). Assessment runs, attack transcripts and findings are not read. Uses the US region host; EU-region projects use a different host that this connector does not call.

Data sources

• https://www.confident-ai.com/docs/reference/api/v2/rt-frameworks/list-rt-frameworks (the API this connector calls, with a BYOK key)

Live from the Confident AI Red Teaming API (api.confident-ai.com) with a BYOK key; documentation: https://www.confident-ai.com/docs/reference/api/v2/rt-frameworks/list-rt-frameworks. Endpoints checked against that documentation on 2026-10-16.

What it is not

Unofficial connector by Unify Dynamics LLC: not affiliated with, endorsed by or sponsored by Confident AI Red Teaming. Confident AI Red Teaming and its logos are trademarks of their owners and are used only to say which service the connector works with. It is read-only: it never creates, changes, sends or deletes anything in your Confident AI Red Teaming account.

Built for: Worldwide. Languages: English.

Confident AI Red Teaming (BYOK) — Privacy Policy

Effective 24 October 2026. Unify Dynamics LLC ("we", "us"), Menlo Park, California.

What Confident AI Red Teaming (BYOK) is. Confident AI Red Teaming (BYOK) is a connector (an MCP server and REST API) that an AI assistant calls on your behalf to read your own Confident AI Red Teaming data: Read the red teaming frameworks, risk categories, vulnerabilities and attack methods of your Confident AI project with your own project API key. You bring your own Confident AI Red Teaming Confident AI project API key; the assistant sends it to us with each request.

BYOK key. The key you supply is used to make the one Confident AI Red Teaming call you asked for. Our application does not store it, write it to a log, put it in a cache, or share it. It is sent only to api.confident-ai.com, over https, and is removed from any text we return to you or your assistant. We do not follow redirects with your key. If Confident AI Red Teaming rejects it, we say so without repeating it.

What we receive. The arguments of each tool call, the BYOK key (for that call only), the technical headers needed to serve the request (an IP address or a client identifier supplied by the assistant) and standard server logs. What Confident AI Red Teaming receives. The request we make on your behalf, including the key and the arguments, under Confident AI Red Teaming's own terms and privacy policy. Confident AI Red Teaming acts at your direction and is the only recipient of the data of your request besides our hosting provider.

What we return. The answer Confident AI Red Teaming gives for your request, trimmed to the fields the tool documents. We do not keep it: it is returned to your assistant and not stored, cached or used to train anything.

What we do not do. We do not build a profile, sell or share personal information, or keep your Confident AI Red Teaming data. Rate-limit counters (a client identifier and timestamps) are held in memory for at most 24 hours. Hosting access logs (IP addresses, request paths and status codes) are kept for up to 30 days for security and abuse prevention; our application adds no request headers or bodies to them.

Sub-processors. Confident AI Red Teaming (the API you call with a BYOK key, at your direction). Hosting: Vercel (United States regions).

Your rights. Because we store no personal data beyond short-lived logs, requests to access, correct or delete data are usually satisfied automatically; you can still contact agent@connectorbay.com and we will respond within 30 days. Revoke your key at Confident AI Red Teaming at any time to end all access.

Children. Confident AI Red Teaming (BYOK) is a general-audience service operated by the adult using the assistant, under Confident AI Red Teaming's own age rules.

Changes. We will post changes here with a new effective date.

Confident AI Red Teaming (BYOK) — Terms of Service

Effective 24 October 2026. These terms govern use of the Confident AI Red Teaming (BYOK) connector ("the Service") operated by Unify Dynamics LLC ("we", "us").

1. The Service. Confident AI Red Teaming (BYOK) provides: Read the red teaming frameworks, risk categories, vulnerabilities and attack methods of your Confident AI project with your own project API key. It is accessed through an AI assistant or directly over MCP or HTTP, and is read-only.
2. Your own key, your own account. You must use your own Confident AI Red Teaming credentials and only access data you are allowed to access. Confident AI Red Teaming's terms apply to your use of Confident AI Red Teaming; you are responsible for complying with them, including any rate limits and permitted uses. Do not share a key you do not own.
3. Independent. Unofficial connector by Unify Dynamics LLC: not affiliated with, endorsed by or sponsored by Confident AI Red Teaming. Confident AI Red Teaming and its logos are trademarks of their owners and are used only to say which service the connector works with.
4. No advice, no guarantees. Output is the data Confident AI Red Teaming returns, lightly trimmed; it may be incomplete, delayed or changed by Confident AI Red Teaming. Check important facts at the source.
5. Read-only. The Service does not create, change, send or delete anything in your Confident AI Red Teaming account.
6. Acceptable use. Automated use within the published rate limits is welcome. Do not use the Service to access data you are not entitled to, to circumvent Confident AI Red Teaming's controls, or to attack any system.
7. Availability. The Service is provided "as is" without warranty. We may change, limit or discontinue it at any time; Confident AI Red Teaming may change or end its API at any time.
8. Data. Our Privacy Policy describes what we process. In short: the BYOK key is used for the one call and not stored or logged.
9. Pro keys. Optional ConnectorBay Pro API keys are issued at our discretion and are separate from your Confident AI Red Teaming key.
10. Liability. To the fullest extent permitted by law, Unify Dynamics LLC is not liable for any loss arising from use of or reliance on the Service, including any action Confident AI Red Teaming takes on your account. Our total liability is limited to US $100.
11. Governing law. California law; venue in San Mateo County, California.
12. Contact. Unify Dynamics LLC · agent@connectorbay.com · https://connectorbay.com/byok-confident-ai-redteam

Confident AI Red Teaming (BYOK) support

Email agent@connectorbay.com. We answer within two business days.

• MCP endpoint: https://byok-confident-ai-redteam.connectorbay.com/mcp
• REST API: https://byok-confident-ai-redteam.connectorbay.com/openapi.json
• Live status: https://byok-confident-ai-redteam.connectorbay.com/health

When you report a problem, include the question you asked your agent, roughly when, and which agent you used (for example Claude, ChatGPT or Gemini). Never send us passwords, account numbers or ID numbers. Confident AI Red Teaming (BYOK) never asks for them.