AI agents use add_prompt to create or update resources in Prompts MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Prompts MCP Server environment.
This tool creates new prompt templates as markdown files with YAML frontmatter. Creating data is a Write operation. The action is reversible (prompts can be deleted via the sibling delete_prompt tool), so it does not rise to Destructive level. The blast radius is minimal—a misused tool could add unwanted prompts but causes no financial, system-level, or irreversible harm.
From the tool's definition Tool description states "Add a new prompt to the collection", which creates new data (prompt templates) in a reversible manner.
Documented attack patterns abuse exactly the kind of access add_prompt gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Prompts MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for add_prompt:
{
"version": "1",
"default": "deny",
"tools": {
"add_prompt": {
"limits": [
{
"counter": "add_prompt_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}add_prompt 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.
Free to start. No card required.
Add a new prompt to the collection. It is categorised as a Write tool in the Prompts MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Prompts MCP Server MCP server in PolicyLayer and add a rule for add_prompt: 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 Prompts MCP Server. Nothing to install.
add_prompt 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_prompt 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_prompt. 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_prompt is provided by the Prompts MCP Server MCP server (tanker327/prompts-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Prompts MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
5 Prompts MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.