# compare

Return a comparison matrix for one category with common fields and buyer-relevant category fields.

Agent View of the PolicyLayer registry record for `compare`. HTML page: https://policylayer.com/tools/dev-agentpapers-agent-papers/compare

## Facts

- Tool: `compare`
- Server: Agent Papers (`https://agentpapers.dev/api/mcp`) — https://policylayer.com/tools/dev-agentpapers-agent-papers.md
- Homepage: https://github.com/https://agentpapers.dev/api/mcp
- Risk category: Read (Low risk)
- Registry record: grade D, identity unverified
- Server auth posture: open
- Server CORS policy: *
- Server rate-limited: no
- Parameters: 1 (1 required)
- Recommended policy verdict: Allowed

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `category` | string | yes | Category id to compare. |

Parameters from the server's own tool schema.

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "compare",
    "arguments": {
      "category": "<category>"
    }
  }
}
```

## Why compare is rated Low

The tool retrieves and presents structured data about AI agent companies in tabular form to facilitate comparison. There are no write operations, no code execution, no deletion, and no financial transactions. While the underlying data involves sensitive personal and business information (identity, phone, email, addresses, etc.), the tool itself only reads and displays information.

From the tool's own definition: "Tool returns a 'comparison matrix' for a category with 'common fields and buyer-relevant category fields.' The verb 'return' and the output format (matrix) indicate data retrieval with no modification or execution."

## Use case

AI agents call compare 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.

## Recommended policy (PolicyLayer)

Verdict: **Allowed**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Agent Papers:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "compare": {}
  }
}
```

## Other tools on Agent Papers (5)

- `get_company` — Read — https://policylayer.com/tools/dev-agentpapers-agent-papers/get-company.md
- `get_schema` — Read — https://policylayer.com/tools/dev-agentpapers-agent-papers/get-schema.md
- `list_categories` — Read — https://policylayer.com/tools/dev-agentpapers-agent-papers/list-categories.md
- `search` — Read — https://policylayer.com/tools/dev-agentpapers-agent-papers/search.md
- `whats_new` — Read — https://policylayer.com/tools/dev-agentpapers-agent-papers/whats-new.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=dev-agentpapers-agent-papers · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/dev-agentpapers-agent-papers