Update pmpt.md: check off completed features, add progress notes, or backfill missing version summaries. Use after completing work OR before publishing to fill in empty Snapshot Log entries. To backfill: use pmpt_diff to understand what changed, then set snapshotVersion=
AI agents use pmpt_update_doc 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.
pmpt_update_doc modifies a project documentation file (pmpt.md) by updating content, marking completion states, and filling in version history. This is reversible—prior versions can be restored via the pmpt_history tool indicated as a sibling.
From the tool's definition Tool description explicitly states 'Update pmpt.md', 'check off completed features', 'add progress notes', and 'backfill missing version summaries'. These are all data modification operations.
Documented attack patterns abuse exactly the kind of access pmpt_update_doc 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_update_doc:
{
"version": "1",
"default": "deny",
"tools": {
"pmpt_update_doc": {
"limits": [
{
"counter": "pmpt_update_doc_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}pmpt_update_doc 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.
Update pmpt.md: check off completed features, add progress notes, or backfill missing version summaries. Use after completing work OR before publishing to fill in empty Snapshot Log entries. To backfill: use pmpt_diff to understand what changed, then set snapshotVersion=. 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_update_doc: 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_update_doc 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_update_doc 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_update_doc. 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_update_doc 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.