add_web_search_evidence
AI agents use add_web_search_evidence to create or update resources in Professor Fit MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Professor Fit MCP environment.
The name implies a write operation — adding web search evidence to a professor profile or ranking record. Without a description, confidence is low, but 'add_' prefix strongly implies creating/modifying data rather than purely reading it. Severity is medium because misuse could corrupt professor profiles or rankings used by PhD applicants.
From the tool's definition Tool name 'add_web_search_evidence' suggests adding/writing evidence data; description is empty and uninformative.
Attacks that exploit this kind of access
add_web_search_evidence. It is categorised as a Write tool in the Professor Fit MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Professor Fit MCP server in PolicyLayer and add a rule for add_web_search_evidence: 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 Professor Fit MCP. Nothing to install.
add_web_search_evidence 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 add_web_search_evidence 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 add_web_search_evidence. 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.
add_web_search_evidence is provided by the Professor Fit MCP server (wrennnn2/professorfitmcp). 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 →