This record as markdown: /tools/54yyyu-zotero-mcp/fetch.md
What fetch does on Zotero MCP
AI agents call fetch to retrieve information from Zotero MCP without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why fetch is rated Low
Given the server's primary purpose is to query and access a research library, and the tool name 'fetch' is typically used for retrieval operations, this is classified as Read. The empty description reduces confidence slightly, but the Zotero context and sibling tools (search, various read-only access methods) strongly suggest data retrieval with no side effects.
From the tool's definition Tool named 'fetch' with no description provided. Based on context of Zotero MCP server which supports searching, accessing content, and retrieving library data, 'fetch' most likely retrieves research items or content from the library without modification.
Attacks that exploit this kind of access
The rule that runs fetch safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Zotero MCP, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For fetch, this is the rule to start with:
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 Zotero MCP, apply this rule, and every fetch call is checked against it from then on.
Questions about fetch
fetch is a read tool on the Zotero MCP server. It is categorised as a Read tool in the Zotero MCP MCP Server, which means it retrieves data without modifying state.
Register the Zotero MCP server in PolicyLayer and add a rule for 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 Zotero MCP. Nothing to install.
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 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 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.
fetch is provided by the Zotero MCP server (pypi:zotero-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Zotero, and thousands of servers like it.
This server
Across the catalogue