update_oauth_credential
Update an OAuth credential. Rotate the secret (client_secret/password/private key) by passing a new grant + secret field; this clears the cached token so the next invoke re-fetches. Leave grant fields out to edit only display_name/token_url/scopes. Grant type cannot be changed — delete and recrea...
This record as markdown: /tools/deloc-mcp/update-oauth-credential.md
What update_oauth_credential does on Deloc
AI agents use update_oauth_credential to create or update resources in Deloc, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Deloc environment.
Why update_oauth_credential is rated Medium
This tool modifies existing credentials reversibly — the operation can be undone by updating again with different values. It does not delete credentials (which would be Destructive) but changes them. The high severity reflects that misuse could redirect authentication flows, intercept tokens, or grant unauthorized access to third-party services, making this a significant security-relevant Write operation.
From the tool's definition Tool updates OAuth credentials and explicitly supports rotating secrets (client_secret/password/private key). The description states it 'clears the cached token so the next invoke re-fetches,' indicating modification of stored sensitive authentication data.
Attacks that exploit this kind of access
The rule that runs update_oauth_credential safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Deloc, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For update_oauth_credential, this is the rule to start with:
update_oauth_credential 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 Deloc, apply this rule, and every update_oauth_credential call is checked against it from then on.
Questions about update_oauth_credential
Update an OAuth credential. Rotate the secret (client_secret/password/private key) by passing a new grant + secret field; this clears the cached token so the next invoke re-fetches. Leave grant fields out to edit only display_name/token_url/scopes. Grant type cannot be changed — delete and recreate to switch. It is categorised as a Write tool in the Deloc MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Deloc MCP server in PolicyLayer and add a rule for update_oauth_credential: 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 Deloc. Nothing to install.
update_oauth_credential 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 update_oauth_credential 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 update_oauth_credential. 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.
update_oauth_credential is provided by the Deloc MCP server (delocdev/deloc-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Deloc, and thousands of servers like it.
This server
Across the catalogue