search
Search Agent Papers companies by name or tagline, optionally constrained by category and status. Returns compact vendor records for ranking.
This record as markdown: /tools/dev-agentpapers-agent-papers/search.md
What search does on Agent Papers
AI agents call search to retrieve information from Agent Papers without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
query | string | Yes | Substring to match against company name and tagline. |
status | string | — | Optional company or offering status filter. |
category | string | — | Optional category filter. |
Parameters from the server's own tool schema.
Why search is rated Low
The tool performs a query/search operation characteristic of Read category tools. It retrieves and returns data without creating, modifying, or deleting records. The elevated severity (medium vs. low) reflects that the underlying data is highly sensitive personal and financial information about companies; unrestricted search access could enable reconnaissance for social engineering, targeting, or fraud schemes.
From the tool's definition Tool description states it 'Search Agent Papers companies by name or tagline' and 'Returns compact vendor records for ranking' — pure retrieval operation with no modification or deletion.
Attacks that exploit this kind of access
The rule that runs search safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Agent Papers, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For search, this is the rule to start with:
search 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 Agent Papers, apply this rule, and every search call is checked against it from then on.
Questions about search
Search Agent Papers companies by name or tagline, optionally constrained by category and status. Returns compact vendor records for ranking. It is categorised as a Read tool in the Agent Papers MCP Server, which means it retrieves data without modifying state.
search accepts 3 parameters: query, status, category. Required: query. The full parameter table on this page comes from the server's own tool schema.
Register the Agent Papers MCP server in PolicyLayer and add a rule for search: 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 Agent Papers. Nothing to install.
search 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 search 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 search. 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.
search is provided by the Agent Papers MCP server (https://agentpapers.dev/api/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Agent Papers, and thousands of servers like it.
This server
Across the catalogue