Add a single keyword (prompt) to a project. SurfRank will query every configured AI
AI agents use add_keyword to create or update resources in SurfRank MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your SurfRank MCP Server environment.
This tool creates a new keyword entry in a project, modifying data in a controlled manner. It is a Write operation because it creates/modifies data (adding a keyword to a project) reversibly—the keyword can be later removed via delete_keyword.
From the tool's definition Tool description states 'Add a single keyword (prompt) to a project', which is a reversible creation action that modifies project state without deleting or executing arbitrary code.
Attacks that exploit this kind of access
Add a single keyword (prompt) to a project. SurfRank will query every configured AI. It is categorised as a Write tool in the SurfRank MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the SurfRank MCP Server MCP server in PolicyLayer and add a rule for add_keyword: 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 SurfRank MCP Server. Nothing to install.
add_keyword 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_keyword 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_keyword. 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_keyword is provided by the SurfRank MCP Server MCP server (surfrankai/mcp-server). 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 →