AI agents use via_memory_add to create or update resources in Via — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Via environment.
This tool creates or modifies data in a shared memory store, which is reversible (facts can be updated or overwritten). It is Write rather than Read because it has a side effect (persistence).
From the tool's definition 'Store a fact in Via memory' — persists data to a shared memory system that is retrievable and modifiable by other AI agents and tools.
Documented attack patterns abuse exactly the kind of access via_memory_add gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Via, and nothing reaches the server without passing your rules. This is the rule we recommend for via_memory_add:
{
"version": "1",
"default": "deny",
"tools": {
"via_memory_add": {
"limits": [
{
"counter": "via_memory_add_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}via_memory_add 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.
Free to start. No card required.
Store a fact in Via memory. It is categorised as a Write tool in the Via MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Via MCP server in PolicyLayer and add a rule for via_memory_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 Via. Nothing to install.
via_memory_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 via_memory_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 via_memory_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.
via_memory_add is provided by the Via MCP server (vektor-memory/via). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Via, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
8 Via tools catalogued and risk-classified — across an index of 43,000+ MCP servers.