send_push
AI agents use send_push to create or update resources in Paper Distill MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Paper Distill MCP environment.
The term 'push' in academic research tools typically means exporting or sending data to external destinations like Zotero or Obsidian. This is a write operation that modifies state in those external systems, creating new records or collections. The empty description lowers confidence slightly, but the context of a paper curation tool with explicit Zotero/Obsidian integration makes the write classification clear.
From the tool's definition Tool name 'send_push' combined with server context of 'ranked push' and 'Zotero and Obsidian support' indicates it sends or pushes data (papers/research) to external applications.
Attacks that exploit this kind of access
send_push. It is categorised as a Write tool in the Paper Distill MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Paper Distill MCP server in PolicyLayer and add a rule for send_push: 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 Paper Distill MCP. Nothing to install.
send_push 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 send_push 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 send_push. 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.
send_push is provided by the Paper Distill MCP server (pypi:paper-distill-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 →