conv_configure_redaction
Set how inbound conversation text is treated when it contains a national identity number. Applies to messages ingested after the change — email, SMS, voice and widget alike — and rewrites every stored copy, including the HTML body, the conversation subject, and the quoted history and signature ca...
This record as markdown: /tools/com-getmunin-munin/conv-configure-redaction.md
What conv_configure_redaction does on Munin
AI agents use conv_configure_redaction to create or update resources in Munin, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Munin environment.
Why conv_configure_redaction is rated Medium
Configures redaction rules and rewrites stored message copies, which is a persistent write action.
From the tool's definition Set how inbound conversation text is treated...rewrites every stored copy
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
The rule that runs conv_configure_redaction safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Munin, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For conv_configure_redaction, this is the rule to start with:
conv_configure_redaction 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.
The button opens the PolicyLayer dashboard: create your workspace, connect Munin, apply this rule, and every conv_configure_redaction call is checked against it from then on.
Questions about conv_configure_redaction
Set how inbound conversation text is treated when it contains a national identity number. Applies to messages ingested after the change — email, SMS, voice and widget alike — and rewrites every stored copy, including the HTML body, the conversation subject, and the quoted history and signature captured in message metadata. Existing messages are untouched. Redaction is irreversible: with. It is categorised as a Write tool in the Munin MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Munin MCP server in PolicyLayer and add a rule for conv_configure_redaction: 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 Munin. Nothing to install.
conv_configure_redaction 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 conv_configure_redaction 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 conv_configure_redaction. 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.
conv_configure_redaction is provided by the Munin MCP server (https://mcp.getmunin.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Munin, and thousands of servers like it.
This server
Across the catalogue