artifact_fetch
Fetch a file's bytes from an allowed location (a discovered project root, ~/.yaver/artifacts, or YAVER_ARTIFACT_ROOTS) so a compiled PDF, a .dwg, a screenshot or a build output can reach you. Images come back as a viewable image block; other files as base64 + mime + size + sha256, bounded at 12 MB.
This record as markdown: /tools/io-github-kivanccakmak-yaver/artifact-fetch.md
What artifact_fetch does on Yaver
AI agents call artifact_fetch to retrieve information from Yaver without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
path | string | Yes | Absolute path (or ~/…) inside an allowed root. |
machine | string | — | Owned device to read from (default: local). |
maxBytes | integer | — | Optional lower cap (hard max 12 MB). |
Parameters from the server's own tool schema.
Why artifact_fetch is rated Low
Retrieves file data from whitelisted directories with no side effects or destructive capabilities.
From the tool's definition Fetch a file's bytes from an allowed location, no modifications, bounded 12 MB.
Risk signalsAccepts file system path (path) · Admin/system-level operation
Attacks that exploit this kind of access
The rule that runs artifact_fetch safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Yaver, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For artifact_fetch, this is the rule to start with:
artifact_fetch is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Yaver, apply this rule, and every artifact_fetch call is checked against it from then on.
Questions about artifact_fetch
Fetch a file's bytes from an allowed location (a discovered project root, ~/.yaver/artifacts, or YAVER_ARTIFACT_ROOTS) so a compiled PDF, a .dwg, a screenshot or a build output can reach you. Images come back as a viewable image block; other files as base64 + mime + size + sha256, bounded at 12 MB. It is categorised as a Read tool in the Yaver MCP Server, which means it retrieves data without modifying state.
artifact_fetch accepts 3 parameters: path, machine, maxBytes. Required: path. The full parameter table on this page comes from the server's own tool schema.
Register the Yaver MCP server in PolicyLayer and add a rule for artifact_fetch: 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 Yaver. Nothing to install.
artifact_fetch is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the artifact_fetch 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 artifact_fetch. 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.
artifact_fetch is provided by the Yaver MCP server (yaver-cli). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Yaver, and thousands of servers like it.
This server
Across the catalogue