publish_upload
Alias of publish_run for MCP clients that think in terms of an uploader. The target still archives/registers through Yaver first, then submits locally.
This record as markdown: /tools/io-github-kivanccakmak-yaver/publish-upload.md
What publish_upload does on Yaver
AI agents use publish_upload to create or update resources in Yaver, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Yaver environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
dir | string | — | Project directory. Defaults to the agent work dir. |
target | string | — | Target ID from .yaver/publish.yaml. Defaults to defaultTarget. |
allow_github_fallback | boolean | — | Allow explicit GitHub workflow_dispatch fallback if the target/project permits it. |
Parameters from the server's own tool schema.
Why publish_upload is rated Medium
This tool creates or registers artifacts (archives/registers through Yaver, submits locally). While 'publish_run' might suggest Execute category, the description focuses on uploading and registering data through Yaver infrastructure, which is reversible (content can be unpublished or re-registered). The tool does not appear to delete data irreversibly, execute arbitrary commands, or move money.
From the tool's definition Tool description states 'archives/registers through Yaver first, then submits locally' - language indicating data creation/registration. Named 'publish_upload' suggesting content submission.
Risk signalsAccepts file system path (dir)
Attacks that exploit this kind of access
The rule that runs publish_upload 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 publish_upload, this is the rule to start with:
publish_upload 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 Yaver, apply this rule, and every publish_upload call is checked against it from then on.
Questions about publish_upload
Alias of publish_run for MCP clients that think in terms of an uploader. The target still archives/registers through Yaver first, then submits locally. It is categorised as a Write tool in the Yaver MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
publish_upload accepts 3 parameters: dir, target, allow_github_fallback. 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 publish_upload: 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.
publish_upload 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 publish_upload 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 publish_upload. 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.
publish_upload 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