Add a new credential to the store
AI agents use add_credential to create or update resources in Credential Manager MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Credential Manager MCP Server environment.
This tool creates new credential records in the credential store. While not destructive (credentials can be updated or deleted), it is a Write operation because it irreversibly adds data to persistent storage.
From the tool's definition Tool description states 'Add a new credential to the store' — this creates new data in persistent storage. The server is described as managing credentials via 'JSON storage', confirming write operations modify stored data.
Attacks that exploit this kind of access
Add a new credential to the store. It is categorised as a Write tool in the Credential Manager MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Credential Manager MCP Server MCP server in PolicyLayer and add a rule for add_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 Credential Manager MCP Server. Nothing to install.
add_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 add_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 add_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.
add_credential is provided by the Credential Manager MCP Server MCP server (mclamee/credential-manager-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →