Add a new prompt to your gist-based prompts collection
AI agents use add_gist_prompt to create or update resources in GistPad MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your GistPad MCP environment.
The tool creates new data (a prompt) within a user's gist collection without deleting, executing code, or causing financial transactions. It is reversible through the sibling tool delete_gist_prompt. This is a straightforward Write operation with low severity since prompts are user-generated knowledge artifacts stored in GitHub Gists with no side effects beyond data creation.
From the tool's definition Tool description states 'Add a new prompt to your gist-based prompts collection' — this is a create/add operation that modifies data (the prompts collection) in a reversible manner.
Documented attack patterns abuse exactly the kind of access add_gist_prompt gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and GistPad MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for add_gist_prompt:
{
"version": "1",
"default": "deny",
"tools": {
"add_gist_prompt": {
"limits": [
{
"counter": "add_gist_prompt_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}add_gist_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 your gist-based prompts collection. It is categorised as a Write tool in the GistPad MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the GistPad MCP server in PolicyLayer and add a rule for add_gist_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 GistPad MCP. Nothing to install.
add_gist_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_gist_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_gist_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_gist_prompt is provided by the GistPad MCP server (lostintangent/gistpad-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from GistPad MCP, 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.
23 GistPad MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.