Edit existing plan fields (productIdea, coreFeatures, techStack, additionalContext, projectName). Use this to update plan content — e.g., translate productIdea to English, add new features, change tech stack. Only provided fields are updated; others stay unchanged. Regenerates plan.md and pmpt.ai...
AI agents use pmpt_edit_plan 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 modifies project metadata and documentation (plan fields, generated markdown files) but does not delete, execute arbitrary code, move funds, or trigger irreversible actions. The regeneration of markdown files is a side effect of content updates, not destructive replacement.
From the tool's definition Tool description explicitly states 'Edit existing plan fields' and 'Use this to update plan content' — creates or modifies data reversibly. Fields updated include productIdea, coreFeatures, techStack, additionalContext, projectName.
Documented attack patterns abuse exactly the kind of access pmpt_edit_plan 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_edit_plan:
{
"version": "1",
"default": "deny",
"tools": {
"pmpt_edit_plan": {
"limits": [
{
"counter": "pmpt_edit_plan_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}pmpt_edit_plan 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.
Edit existing plan fields (productIdea, coreFeatures, techStack, additionalContext, projectName). Use this to update plan content — e.g., translate productIdea to English, add new features, change tech stack. Only provided fields are updated; others stay unchanged. Regenerates plan.md and pmpt.ai.md automatically. pmpt.md progress/log sections are preserved — only the plan-derived sections (Product Idea, Features, Tech Stack, Additional Context) are updated. 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_edit_plan: 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_edit_plan 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_edit_plan 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_edit_plan. 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_edit_plan 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.