evidence_unset_label
Remove specific label(s) from a record, keeping the rest.
This record as markdown: /tools/abraflexi/evidence-unset-label.md
What evidence_unset_label does on AbraFlexi
AI agents use evidence_unset_label to create or update resources in AbraFlexi, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your AbraFlexi environment.
Why evidence_unset_label is rated Medium
The tool modifies a record by removing labels but keeps the rest of the record intact. This is a reversible modification (labels can be re-added), placing it in the Write category rather than Destructive. Misuse could cause mislabeling or loss of categorization metadata, which has medium blast radius.
From the tool's definition Remove specific label(s) from a record, keeping the rest.
Attacks that exploit this kind of access
The rule that runs evidence_unset_label safely
PolicyLayer is an MCP gateway: it sits between your AI agents and AbraFlexi, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For evidence_unset_label, this is the rule to start with:
evidence_unset_label 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 AbraFlexi, apply this rule, and every evidence_unset_label call is checked against it from then on.
Questions about evidence_unset_label
Remove specific label(s) from a record, keeping the rest. It is categorised as a Write tool in the AbraFlexi MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the AbraFlexi MCP server in PolicyLayer and add a rule for evidence_unset_label: 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 AbraFlexi. Nothing to install.
evidence_unset_label 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 evidence_unset_label 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 evidence_unset_label. 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.
evidence_unset_label is provided by the AbraFlexi MCP server (abraflexi-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on AbraFlexi, and thousands of servers like it.
This server
Across the catalogue