evidence_perform_action
A execute tool on the AbraFlexi MCP server.
This record as markdown: /tools/abraflexi/evidence-perform-action.md
What evidence_perform_action does on AbraFlexi
AI agents invoke evidence_perform_action to trigger actions in AbraFlexi. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.
Why evidence_perform_action is rated High
With no description, classification is based solely on the name. 'perform_action' implies executing an operation rather than a simple read or write. Given the AbraFlexi context (an accounting/ERP system), an unspecified 'action' on 'evidence' could have significant consequences. Severity is high due to the unknown blast radius in a financial system, but confidence is low due to the empty description.
From the tool's definition Tool name 'evidence_perform_action' — the word 'perform_action' suggests execution of some operation, but the description is empty and provides no detail.
Attacks that exploit this kind of access
The rule that runs evidence_perform_action 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_perform_action, this is the rule to start with:
evidence_perform_action stays usable, but rate-capped: a runaway agent can't fire it dozens of times 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_perform_action call is checked against it from then on.
Questions about evidence_perform_action
evidence_perform_action is a execute tool on the AbraFlexi MCP server. It is categorised as a Execute tool in the AbraFlexi MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the AbraFlexi MCP server in PolicyLayer and add a rule for evidence_perform_action: 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_perform_action is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the evidence_perform_action 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_perform_action. 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_perform_action 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.
Across the catalogue