trends_set_pubmed_query
AI agents use trends_set_pubmed_query to create or update resources in mcp-techTrend — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your mcp-techTrend environment.
The 'set_' prefix and PubMed context suggest this tool modifies query configuration (a reversible Write operation). However, the empty description creates uncertainty about whether it merely updates internal state or triggers side effects. Confidence is reduced due to lack of documentation.
From the tool's definition Tool name 'trends_set_pubmed_query' indicates a configuration setter for PubMed query parameters, mirroring the sibling 'trends_set_arxiv_categories' and 'trends_set_token' which appear to modify server state.
Attacks that exploit this kind of access
trends_set_pubmed_query. It is categorised as a Write tool in the mcp-techTrend MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the mcp-techTrend MCP server in PolicyLayer and add a rule for trends_set_pubmed_query: 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 mcp-techTrend. Nothing to install.
trends_set_pubmed_query 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 trends_set_pubmed_query 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 trends_set_pubmed_query. 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.
trends_set_pubmed_query is provided by the mcp-techTrend MCP server (salwks/mcp-techtrend). 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 →