store_artifact
Store text/bytes and get a durable public URL for your output — something a stateless agent can't host itself. Returns {id, url}.
This record as markdown: /tools/com-wingmanprotocol-agent-gateway/store-artifact.md
What store_artifact does on Gateway
AI agents use store_artifact to create or update resources in Gateway, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Gateway environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
handle | string | — | attribute to your registered handle |
secret | string | — | your agent secret, if using handle |
content | string | Yes | UTF-8 text, or base64 if encoding=base64 |
encoding | string | — | default utf8 |
ttl_seconds | integer | — | lifetime (max 7 days) |
content_type | string | — | MIME type to store + serve as |
Parameters from the server's own tool schema.
Why store_artifact is rated Medium
This tool writes data to external storage and creates a publicly accessible URL. It is a Write operation (create/upload) with no indication of irreversible deletion or financial action. Medium severity because it publishes data publicly, which could be misused to host malicious content or leak sensitive information, but the action is reversible (artifacts can typically be deleted).
From the tool's definition 'Store text/bytes and get a durable public URL for your output' — creates/uploads data and returns a persistent URL
Risk signalsHandles credentials or secrets (secret) · Accepts raw HTML/template content (content)
Attacks that exploit this kind of access
The rule that runs store_artifact safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Gateway, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For store_artifact, this is the rule to start with:
store_artifact 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 Gateway, apply this rule, and every store_artifact call is checked against it from then on.
Questions about store_artifact
Store text/bytes and get a durable public URL for your output — something a stateless agent can't host itself. Returns {id, url}. It is categorised as a Write tool in the Gateway MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
store_artifact accepts 6 parameters: handle, secret, content, encoding, ttl_seconds, content_type. Required: content. The full parameter table on this page comes from the server's own tool schema.
Register the Gateway MCP server in PolicyLayer and add a rule for store_artifact: 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 Gateway. Nothing to install.
store_artifact 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 store_artifact 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 store_artifact. 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.
store_artifact is provided by the Gateway MCP server (https://wingmanprotocol.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Gateway, and thousands of servers like it.
This server
Across the catalogue