# oe_collections_create

Create a new collection. By convention, agent-managed names start with

Agent View of the PolicyLayer registry record for `oe_collections_create`. HTML page: https://policylayer.com/tools/htlin222-openevidence-mcp/oe-collections-create

## Facts

- Tool: `oe_collections_create`
- Server: : (`htlin222/openevidence-mcp`) — https://policylayer.com/tools/htlin222-openevidence-mcp.md
- Homepage: https://github.com/htlin222/openevidence-mcp
- Risk category: Write (Medium risk)
- Registry record: grade C, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Rate-limited

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

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "oe_collections_create",
    "arguments": {}
  }
}
```

## Why oe_collections_create is rated Medium

This tool creates a new collection, which is a reversible write operation. It modifies the state of the system by adding a new collection but does not delete or irreversibly destroy data, nor does it execute arbitrary code or move financial resources.

From the tool's own definition: "Tool name 'oe_collections_create' and description 'Create a new collection' directly indicate creation of new data."

## Use case

AI agents use oe_collections_create to create or update resources in :, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your : environment.

## Recommended policy (PolicyLayer)

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

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "oe_collections_create": {
      "limits": [
        {
          "counter": "oe_collections_create_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on : (18)

- `oe_collections_sync_db` — Destructive — https://policylayer.com/tools/htlin222-openevidence-mcp/oe-collections-sync-db.md
- `oe_answers_search` — Read — https://policylayer.com/tools/htlin222-openevidence-mcp/oe-answers-search.md
- `oe_article_get` — Read — https://policylayer.com/tools/htlin222-openevidence-mcp/oe-article-get.md
- `oe_auth_status` — Read — https://policylayer.com/tools/htlin222-openevidence-mcp/oe-auth-status.md
- `oe_collections_classify` — Read — https://policylayer.com/tools/htlin222-openevidence-mcp/oe-collections-classify.md
- `oe_collections_get` — Read — https://policylayer.com/tools/htlin222-openevidence-mcp/oe-collections-get.md
- `oe_collections_list` — Read — https://policylayer.com/tools/htlin222-openevidence-mcp/oe-collections-list.md
- `oe_collections_summary` — Read — https://policylayer.com/tools/htlin222-openevidence-mcp/oe-collections-summary.md
- `oe_collections_unsorted` — Read — https://policylayer.com/tools/htlin222-openevidence-mcp/oe-collections-unsorted.md
- `oe_health` — Read — https://policylayer.com/tools/htlin222-openevidence-mcp/oe-health.md
- `oe_history_list` — Read — https://policylayer.com/tools/htlin222-openevidence-mcp/oe-history-list.md
- `oe_public_get` — Read — https://policylayer.com/tools/htlin222-openevidence-mcp/oe-public-get.md
- `oe_article_set_access` — Write — https://policylayer.com/tools/htlin222-openevidence-mcp/oe-article-set-access.md
- `oe_ask` — Write — https://policylayer.com/tools/htlin222-openevidence-mcp/oe-ask.md
- `oe_collections_add_article` — Write — https://policylayer.com/tools/htlin222-openevidence-mcp/oe-collections-add-article.md
- `oe_collections_bulk_apply` — Write — https://policylayer.com/tools/htlin222-openevidence-mcp/oe-collections-bulk-apply.md
- `oe_collections_db_init` — Write — https://policylayer.com/tools/htlin222-openevidence-mcp/oe-collections-db-init.md
- `oe_collections_sync_history` — Write — https://policylayer.com/tools/htlin222-openevidence-mcp/oe-collections-sync-history.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=htlin222-openevidence-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/htlin222-openevidence-mcp