update_credential
Rename a credential and/or replace its auth. Omit a secret field (or the whole auth object) to keep the existing value — the vault can never show a secret back to confirm it, so leaving it out means "unchanged," not "cleared."
This record as markdown: /tools/dev-echorelay-management/update-credential.md
What update_credential does on EchoRelay
AI agents use update_credential to create or update resources in EchoRelay, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your EchoRelay environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
auth | object | — | Same shape as create_credential. Omit to keep the existing auth entirely. |
name | string | — | New name. Omit to keep the existing one. |
credentialId | string | Yes | UUID of the credential (from list_credentials). |
Parameters from the server's own tool schema.
Why update_credential is rated Medium
This tool modifies credential data reversibly—it changes metadata and authentication information without deletion. While the severity is high due to the sensitive nature of auth modifications (credential compromise could enable unauthorized access), it does not irreversibly delete data (ruling out Destructive), move money (ruling out Financial), or execute arbitrary code (ruling out Execute).
From the tool's definition Tool description states it can "Rename a credential and/or replace its auth". The capability to modify authentication secrets and credential metadata constitutes data modification.
Risk signalsHandles credentials or secrets (auth)
Attacks that exploit this kind of access
The rule that runs update_credential safely
PolicyLayer is an MCP gateway: it sits between your AI agents and EchoRelay, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For update_credential, this is the rule to start with:
update_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 EchoRelay, apply this rule, and every update_credential call is checked against it from then on.
Questions about update_credential
Rename a credential and/or replace its auth. Omit a secret field (or the whole auth object) to keep the existing value — the vault can never show a secret back to confirm it, so leaving it out means "unchanged," not "cleared.". It is categorised as a Write tool in the EchoRelay MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
update_credential accepts 3 parameters: auth, name, credentialId. Required: credentialId. The full parameter table on this page comes from the server's own tool schema.
Register the EchoRelay MCP server in PolicyLayer and add a rule for update_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 EchoRelay. Nothing to install.
update_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_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_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_credential is provided by the EchoRelay MCP server (https://mcp.echorelay.dev). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on EchoRelay, and thousands of servers like it.
This server
Across the catalogue