# oe_collections_summary

Counts (chats, collections, hashtag, memberships, unsorted) + last sync timestamps.

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

## Facts

- Tool: `oe_collections_summary`
- 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_summary",
    "arguments": {}
  }
}
```

## Why oe_collections_summary is rated Low

This tool performs read-only queries to count and retrieve metadata about collections and related entities. It has no side effects, creates no data, executes no code, and makes no destructive or financial operations. It is a simple retrieval/reporting function with minimal blast radius if misused.

From the tool's own definition: "Tool description states it 'Counts (chats, collections, hashtag, memberships, unsorted) + last sync timestamps' — retrieves aggregated statistics and metadata without modifying any data."

## Use case

AI agents call oe_collections_summary 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_summary": {}
  }
}
```

## 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_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