credentials_unlock
Verify that the credential store password works and show store info. Uses ARC_CREDS_PASSWORD env var. Creates a new empty store if none exists.
This record as markdown: /tools/io-github-aibtcdev-mcp-server/credentials-unlock.md
What credentials_unlock does on Aibtc
AI agents call credentials_unlock to retrieve information from Aibtc without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why credentials_unlock is rated Low
The primary action is verification and reading store info. However, it also 'Creates a new empty store if none exists', which is a Write side effect. Since the dominant described purpose is verification/read and store creation is a conditional minor side effect, Read is the most applicable category. Severity is medium because it involves credential store access and potential implicit store creation.
From the tool's definition Verify that the credential store password works and show store info
Attacks that exploit this kind of access
The rule that runs credentials_unlock safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Aibtc, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For credentials_unlock, this is the rule to start with:
credentials_unlock is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Aibtc, apply this rule, and every credentials_unlock call is checked against it from then on.
Questions about credentials_unlock
Verify that the credential store password works and show store info. Uses ARC_CREDS_PASSWORD env var. Creates a new empty store if none exists. It is categorised as a Read tool in the Aibtc MCP Server, which means it retrieves data without modifying state.
Register the Aibtc MCP server in PolicyLayer and add a rule for credentials_unlock: 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 Aibtc. Nothing to install.
credentials_unlock is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the credentials_unlock 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 credentials_unlock. 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.
credentials_unlock is provided by the Aibtc MCP server (aibtcdev/aibtc-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Aibtc, and thousands of servers like it.
This server
Across the catalogue