yaver_auth_link_start
Connect an ADDITIONAL OAuth provider to the currently signed-in account — e.g., user signed up with Apple but wants to also sign in with GitHub, GitLab, Google, or Microsoft. Returns {url, qr_ascii, link_token, expires_at_ms}. Render the URL + QR; the user opens it, signs in with that provider, a...
This record as markdown: /tools/io-github-kivanccakmak-yaver/yaver-auth-link-start.md
What yaver_auth_link_start does on Yaver
AI agents use yaver_auth_link_start to create or update resources in Yaver, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Yaver environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
provider | string | Yes | Provider to link: apple | github | gitlab | google | microsoft |
Parameters from the server's own tool schema.
Why yaver_auth_link_start is rated Medium
This tool initiates linking a new OAuth provider to an existing account, which is a write operation that modifies account authentication settings. It starts an OAuth flow that results in persistent changes to account credentials/login methods. Misuse could allow an attacker to link an unauthorized OAuth provider to a victim's account, enabling account takeover — hence medium severity.
From the tool's definition Connect an ADDITIONAL OAuth provider to the currently signed-in account... Yaver binds the provider to the existing account
Attacks that exploit this kind of access
The rule that runs yaver_auth_link_start safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Yaver, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For yaver_auth_link_start, this is the rule to start with:
yaver_auth_link_start stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Yaver, apply this rule, and every yaver_auth_link_start call is checked against it from then on.
Questions about yaver_auth_link_start
Connect an ADDITIONAL OAuth provider to the currently signed-in account — e.g., user signed up with Apple but wants to also sign in with GitHub, GitLab, Google, or Microsoft. Returns {url, qr_ascii, link_token, expires_at_ms}. Render the URL + QR; the user opens it, signs in with that provider, and Yaver binds the provider to the existing account. Call yaver_auth_link_wait afterwards to confirm. It is categorised as a Write tool in the Yaver MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
yaver_auth_link_start accepts 1 parameter: provider. Required: provider. The full parameter table on this page comes from the server's own tool schema.
Register the Yaver MCP server in PolicyLayer and add a rule for yaver_auth_link_start: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Yaver. Nothing to install.
yaver_auth_link_start is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the yaver_auth_link_start rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for yaver_auth_link_start. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
yaver_auth_link_start is provided by the Yaver MCP server (yaver-cli). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Yaver, and thousands of servers like it.
This server
Across the catalogue