create_oauth_credential
Create an OAuth credential that actions can reference by name to get a fresh access token at invoke time (injected as ${OAUTH_ACCESS_TOKEN}). Walk the user through: (1) which upstream API, (2) which grant type fits (client_credentials for M2M like Auth0/Okta; password for FreeWheel/legacy; jwt_be...
This record as markdown: /tools/deloc-mcp/create-oauth-credential.md
What create_oauth_credential does on Deloc
AI agents use create_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 create_oauth_credential is rated Medium
This tool creates and stores credentials used for authentication, which is a Write operation that modifies system state by adding new OAuth credentials. While it doesn't directly execute code or delete data, the high severity reflects that misconfigured or compromised credentials could be abused to access upstream APIs with side effects.
From the tool's definition Tool creates OAuth credentials that are stored and referenced by actions ('Create an OAuth credential that actions can reference by name').
Attacks that exploit this kind of access
The rule that runs create_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 create_oauth_credential, this is the rule to start with:
create_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 create_oauth_credential call is checked against it from then on.
Questions about create_oauth_credential
Create an OAuth credential that actions can reference by name to get a fresh access token at invoke time (injected as ${OAUTH_ACCESS_TOKEN}). Walk the user through: (1) which upstream API, (2) which grant type fits (client_credentials for M2M like Auth0/Okta; password for FreeWheel/legacy; jwt_bearer for Google Cloud). For Google, prefer google_service_account_json — ask them to paste the whole JSON. Do NOT echo client_secret, password, or private keys back to the user after they. 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 create_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.
create_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 create_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 create_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.
create_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