Save a snapshot of .pmpt/docs/ files. Call after completing features, fixes, or milestones. CRITICAL: Always provide a detailed summary parameter — it becomes the version description shown publicly on pmptwiki.com. Without a summary, the version appears empty on the project page. Write a DETAILED...
AI agents use pmpt_save to create or update resources in Pmpt — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Pmpt environment.
This tool creates and modifies project milestone snapshots with associated metadata (summaries) that are persistently stored and published to pmptwiki.com. While it stores data reversibly (new versions can be created but previous ones remain accessible as history), the core operation is creating/writing new snapshot records.
From the tool's definition Tool description explicitly states 'Save a snapshot' and 'becomes the version description shown publicly on pmptwiki.com', indicating creation/modification of versioned project data.
Documented attack patterns abuse exactly the kind of access pmpt_save gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Pmpt, and nothing reaches the server without passing your rules. This is the rule we recommend for pmpt_save:
{
"version": "1",
"default": "deny",
"tools": {
"pmpt_save": {
"limits": [
{
"counter": "pmpt_save_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}pmpt_save 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.
Save a snapshot of .pmpt/docs/ files. Call after completing features, fixes, or milestones. CRITICAL: Always provide a detailed summary parameter — it becomes the version description shown publicly on pmptwiki.com. Without a summary, the version appears empty on the project page. Write a DETAILED summary (3-5 sentences) that explains: (1) WHAT was built or changed, (2) WHY it matters, (3) key technical decisions made. Think of it as a mini dev blog entry that helps others learn from your journey. It is categorised as a Write tool in the Pmpt MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Pmpt MCP server in PolicyLayer and add a rule for pmpt_save: 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 Pmpt. Nothing to install.
pmpt_save 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 pmpt_save 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 pmpt_save. 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.
pmpt_save is provided by the Pmpt MCP server (pmptwiki/pmpt-cli). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Pmpt, 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.
14 Pmpt tools catalogued and risk-classified — across an index of 43,000+ MCP servers.