# deep_research

ACCOUNT REQUIRED (free — sign in via GitHub at https://pipeworx.io/signup; depth:"thorough" needs a paid plan). If you are not signed in, use ask_pipeworx instead — it works on every tier. Grounded multi-source research across Pipeworx's 1272 STRUCTURED data sources (SEC filings, FRED/BLS economics, FDA, USPTO patents, markets, science, government records, etc.) in ONE call — this is NOT open-web search. Decomposes your question into focused facets, routes each to the right one of 4,862 tools IN PARALLEL, and returns a findings packet: verbatim evidence + confidence + source + fetched_at + a stable pipeworx:// citation per finding, with explicit gaps[] for facets the data couldn't answer (never invented). Best for broad/multi-part questions over structured data ("compare X and Y's regulatory + financial exposure", "research the filings + market picture for ACME"). For a single lookup use ask_pipeworx (one LLM call, not many). For BREAKING or colloquial CURRENT-NEWS / "what's the world saying about X" topics, prefer ask_pipeworx — it routes to live news APIs and the *-news-feeds packs; deep_research returns mostly empty gaps[] when the topic isn't in the structured catalog. Second-hop iteration: depth:"standard" re-angles unanswered gaps (gap recovery); depth:"thorough" additionally chases the best leads from the first pass — so multi-step questions resolve in one call. Every finding carries a hop field and a citation_uri (record-level pipeworx:// when the source emits one, else source-level). "thorough" also returns contradictions[] flagging findings that disagree. Expect 15-60s (thorough with its follow-up + contradiction pass: up to ~90s).

Agent View of the PolicyLayer registry record for `deep_research`. HTML page: https://policylayer.com/tools/io-github-pipeworx-io-19hz/deep-research

## Facts

- Tool: `deep_research`
- Server: 19hz (`https://gateway.pipeworx.io/19hz/mcp`) — https://policylayer.com/tools/io-github-pipeworx-io-19hz.md
- Homepage: https://github.com/pipeworx-io/mcp-19hz
- Risk category: Read (Low risk)
- Registry record: grade F, identity unverified
- Server auth posture: open
- Server CORS policy: *
- Server rate-limited: yes
- Parameters: 2 (1 required)
- Recommended policy verdict: Allowed

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `depth` | string | no | How many facets to research in parallel: quick=3 (single hop), standard=5 (default; adds a gap-recovery hop that re-angles unanswered facets), thorough=8 (paid; |
| `question` | string | yes | The research question, in natural language. Broad/multi-part is fine — decomposition is the point. |

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": "deep_research",
    "arguments": {
      "question": "<question>"
    }
  }
}
```

## Why deep_research is rated Low

deep_research is fundamentally a data retrieval and aggregation tool. It decomposes queries, routes them to existing data sources (SEC filings, economic data, patents, markets, science records), and returns findings with citations. There is no indication of write, delete, execute, or financial operations.

From the tool's own definition: "'Grounded multi-source research across Pipeworx's 1272 STRUCTURED data sources' and 'routes each to the right one of 4,862 tools IN PARALLEL, and returns a findings packet: verbatim evidence + confidence + source + fetched_at' — this tool queries and…"

## Use case

AI agents call deep_research to retrieve information from 19hz 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 19hz:

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

## Other tools on 19hz (31)

- `forget` — Destructive — https://policylayer.com/tools/io-github-pipeworx-io-19hz/forget.md
- `polymarket_arbitrage` — Financial — https://policylayer.com/tools/io-github-pipeworx-io-19hz/polymarket-arbitrage.md
- `polymarket_edges` — Financial — https://policylayer.com/tools/io-github-pipeworx-io-19hz/polymarket-edges.md
- `ai_visibility_check` — Read — https://policylayer.com/tools/io-github-pipeworx-io-19hz/ai-visibility-check.md
- `ask_pipeworx` — Read — https://policylayer.com/tools/io-github-pipeworx-io-19hz/ask-pipeworx.md
- `ask_pipeworx_grounded` — Read — https://policylayer.com/tools/io-github-pipeworx-io-19hz/ask-pipeworx-grounded.md
- `bet_research` — Read — https://policylayer.com/tools/io-github-pipeworx-io-19hz/bet-research.md
- `compare_entities` — Read — https://policylayer.com/tools/io-github-pipeworx-io-19hz/compare-entities.md
- `discover_tools` — Read — https://policylayer.com/tools/io-github-pipeworx-io-19hz/discover-tools.md
- `entity_profile` — Read — https://policylayer.com/tools/io-github-pipeworx-io-19hz/entity-profile.md
- `events` — Read — https://policylayer.com/tools/io-github-pipeworx-io-19hz/events.md
- `list_subscriptions` — Read — https://policylayer.com/tools/io-github-pipeworx-io-19hz/list-subscriptions.md
- `pipeworx_trending` — Read — https://policylayer.com/tools/io-github-pipeworx-io-19hz/pipeworx-trending.md
- `polymarket_edge_tracker` — Read — https://policylayer.com/tools/io-github-pipeworx-io-19hz/polymarket-edge-tracker.md
- `polymarket_kalshi_spread` — Read — https://policylayer.com/tools/io-github-pipeworx-io-19hz/polymarket-kalshi-spread.md
- `recall` — Read — https://policylayer.com/tools/io-github-pipeworx-io-19hz/recall.md
- `recent_alerts` — Read — https://policylayer.com/tools/io-github-pipeworx-io-19hz/recent-alerts.md
- `recent_changes` — Read — https://policylayer.com/tools/io-github-pipeworx-io-19hz/recent-changes.md
- `regions` — Read — https://policylayer.com/tools/io-github-pipeworx-io-19hz/regions.md
- `resolve_entity` — Read — https://policylayer.com/tools/io-github-pipeworx-io-19hz/resolve-entity.md
- `scan_competitor_ai_presence` — Read — https://policylayer.com/tools/io-github-pipeworx-io-19hz/scan-competitor-ai-presence.md
- `scan_dependency` — Read — https://policylayer.com/tools/io-github-pipeworx-io-19hz/scan-dependency.md
- `search_within` — Read — https://policylayer.com/tools/io-github-pipeworx-io-19hz/search-within.md
- `suggest_questions` — Read — https://policylayer.com/tools/io-github-pipeworx-io-19hz/suggest-questions.md
- `validate_claim` — Read — https://policylayer.com/tools/io-github-pipeworx-io-19hz/validate-claim.md
- `generate_llms_txt` — Write — https://policylayer.com/tools/io-github-pipeworx-io-19hz/generate-llms-txt.md
- `pipeworx_feedback` — Write — https://policylayer.com/tools/io-github-pipeworx-io-19hz/pipeworx-feedback.md
- `polymarket_fill_risk` — Write — https://policylayer.com/tools/io-github-pipeworx-io-19hz/polymarket-fill-risk.md
- `remember` — Write — https://policylayer.com/tools/io-github-pipeworx-io-19hz/remember.md
- `subscribe` — Write — https://policylayer.com/tools/io-github-pipeworx-io-19hz/subscribe.md
- …and 1 more: https://policylayer.com/tools/io-github-pipeworx-io-19hz.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=io-github-pipeworx-io-19hz · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/io-github-pipeworx-io-19hz