# oe_collections_get

Fetch a collection (incl. nested questions[] = membership list) by id.

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

## Facts

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

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

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

## Why oe_collections_get is rated Low

The tool retrieves collection data by id and returns nested membership information. The verb 'Fetch' and the read-only nature of querying collection metadata and membership lists places this squarely in the Read category. No data is created, modified, deleted, or executed. Severity is low because retrieving collection metadata poses minimal risk even if misused by an agent.

From the tool's own definition: "Tool description states 'Fetch a collection' and 'membership list' — pure data retrieval with no modifications or side effects."

## Use case

AI agents call oe_collections_get to retrieve information from : 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 ::

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

## 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_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_create` — Write — https://policylayer.com/tools/htlin222-openevidence-mcp/oe-collections-create.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