AI agents use add to create or update resources in Arca MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Arca MCP environment.
The tool creates or modifies data (vector embeddings/memories) within the semantic storage system. No irreversible deletion occurs (that's 'delete'), nor does it execute arbitrary code or move financial assets. The empty description lowers confidence slightly, but the context of a memory storage service and the presence of sibling CRUD operations strongly suggest Write category.
From the tool's definition Tool named 'add' on a memory storage server (LanceDB/Gemini-based). Sibling tools include 'ingest', 'delete', 'get', and 'list_buckets', indicating CRUD operations. 'add' most naturally performs insertion or creation of memory records.
Attacks that exploit this kind of access
add. It is categorised as a Write tool in the Arca MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Arca MCP server in PolicyLayer and add a rule for add: 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 Arca MCP. Nothing to install.
add 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 add 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 add. 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.
add is provided by the Arca MCP server (m0nochr0me/arca-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 →