AI agents use misp_add_attributes_bulk to create or update resources in Misp — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Misp environment.
The tool adds (creates) new attributes within MISP events, which is a reversible write operation. It does not execute arbitrary code, delete data irreversibly, or move money. The bulk nature increases potential blast radius if an attacker injects false or malicious IOCs, but the effect is still Write-category.
From the tool's definition Tool name and description: 'Add multiple attributes (IOCs) to a MISP event at once' — this creates or modifies data by adding indicators of compromise to threat intelligence events in MISP.
Attacks that exploit this kind of access
Add multiple attributes (IOCs) to a MISP event at once. It is categorised as a Write tool in the Misp MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Misp MCP server in PolicyLayer and add a rule for misp_add_attributes_bulk: 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 Misp. Nothing to install.
misp_add_attributes_bulk 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 misp_add_attributes_bulk 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 misp_add_attributes_bulk. 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.
misp_add_attributes_bulk is provided by the Misp MCP server (solomonneas/misp-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →