---
title: Known Limitations
lastUpdated: '2026-05-31'
nextjs:
  metadata:
    title: Known Limitations - Hive MCP and REST API
    description: "Known provider gates, response-size guardrails, request/response boundaries, B2B subject-state limits, and troubleshooting guidance for Hive Intelligence."
    alternates:
      canonical: https://www.hiveintelligence.xyz/known-limitations
faq:
  - question: "Does every Hive tool return the full upstream dataset?"
    answer: "No. Hive keeps MCP and REST responses within agent-safe size limits. Large responses can include truncation metadata such as _truncated, _pagination, or _dropped_fields. Use the live schema to add pagination, cursor, limit, date, chain, or asset filters."
  - question: "What should I use for perpetual funding rates?"
    answer: "Use the CCXT-backed get_funding_rate, get_funding_rate_history, and get_funding_rates tools. Some DeFiLlama derivatives and perps surfaces are upstream-plan dependent, so CCXT is the documented fallback for exchange funding-rate workflows."
  - question: "Does Hive expose provider webhooks or streams?"
    answer: "Hive's MCP and REST surfaces are request/response tools. Use stateful monitoring for durable scheduled checks and reports, or call an upstream provider directly if your product requires provider-specific push streams or webhooks."
---

**Hive is a managed crypto data surface for agents, not an unlimited mirror of every upstream provider.** These limits are intentional: they keep tool discovery compact, responses usable inside MCP clients, and stateful writes scoped to the right user or B2B subject. {% .lead %}

{% ai-doc-actions path="/known-limitations" title="Known Limitations" /%}

---

## Start with runtime discovery

Static docs explain the product shape. Runtime discovery is the authority for what a key can call right now:

- Use MCP `tools/list`, `hive://tools`, and `hive://providers` inside MCP clients.
- Use `GET /api/v1/tools` for REST catalog discovery.
- Use `get_api_endpoint_schema` or the REST catalog schema before sending production requests.
- Check `meta.runtime_status`, `meta.fetched_at`, `_truncated`, `_pagination`, and provider error payloads before acting on a result.

Do not assume a static page, old prompt, or cached agent memory has the current schema.

---

## Provider and plan boundaries

Hive normalizes providers, but upstream products still have their own data availability, plan gates, rate limits, and deprecations.

| Area | What to know | Recommended path |
| --- | --- | --- |
| DeFiLlama derivatives and perps | Some DeFiLlama derivatives/perps surfaces are upstream-plan dependent or can vary by endpoint availability. | For exchange funding-rate workflows, use the CCXT-backed `get_funding_rate`, `get_funding_rate_history`, and `get_funding_rates` tools. |
| DeFiLlama large lists | Protocols, pools, fees, stablecoins, volumes, and bridge datasets can be too large for one agent response. | Use the live schema and pass `limit`, `offset`, cursor, chain, protocol, pool, date, or minimum-value filters where exposed. |
| Codex advanced surfaces | Codex token and DEX tools are exposed where the hosted runtime has upstream access. Prediction-market and advanced token workflows can still be affected by upstream availability or plan gates. | Inspect `hive://providers`, the live tool schema, and the returned runtime status before relying on a workflow. |
| Codex NFT/Prime holder tools | Hive does not expose Codex NFT/Prime holder tools because the current Codex SDK does not expose the required methods. | Use Alchemy, Helius, and Moralis NFT tools for NFT ownership, metadata, floors, sales, and Solana compressed NFT workflows. |
| Provider throttling | Hive quota errors are `HTTP 429`. Upstream provider throttling or provider failure generally surfaces as `HTTP 502` with a retryable provider error. | Follow `Retry-After` on `429`, and use the [Error Codes](/errors) and [Rate Limits](/rate-limits) guidance for provider errors. |

---

## Response-size guardrails

Hive response handling is designed for agent transports. The source runtime uses a 25,000-token response budget, estimated at roughly 100,000 characters, and adds truncation metadata when a result is too large.

When a response is truncated, look for:

- `_truncated: true`
- `_pagination` with the next page, offset, cursor, or suggested page size
- `_dropped_fields` for supplementary historical/chart fields removed to keep the answer usable
- `meta.truncated` or runtime status metadata on REST execution

Fix truncated calls by narrowing the request:

```json
{
  "tool": "get_yield_pools",
  "args": {
    "chain": "ethereum",
    "limit": 25,
    "offset": 50,
    "minTvl": 10000000
  }
}
```

Not every tool supports the same pagination shape. Inspect the live schema before assuming `limit`, `offset`, `cursor`, `page`, or `per_page`.

---

## Request/response boundaries

Hive MCP and REST tools are request/response interfaces. They do not replace every provider-native product surface.

- Hive does not expose provider webhooks or push streams through the standard MCP/REST execution path.
- Hive stateful monitoring can save monitors, run scheduled checks, list alerts, and generate reports when that workflow fits the use case.
- Latency-sensitive trading infrastructure should call the execution venue or low-level RPC provider directly and use Hive for context, risk, research, and monitoring.
- Hive data tools do not sign transactions or execute trades.

---

## Stateful and B2B boundaries

Stateful tools store monitors, alerts, memory, reports, and subject audit events under the authenticated Hive owner plus a subject boundary.

- Direct users use the default subject `self`.
- B2B partners should keep one Hive API key on a trusted backend and send signed subject headers for each downstream customer.
- Never put `HIVE_API_KEY` or `HIVE_SUBJECT_SIGNING_SECRET` in browser code.
- Before B2B stateful writes, call `/api/v1/b2b/readiness` or `checkHiveB2BReadiness()` and require `b2b_adapter_ready: true`.

See [B2B Partner Adapter](/b2b-adapter) and [Stateful Monitoring](/stateful-monitoring) for implementation details.

---

## Related

- [Live Catalog](/tools/live-catalog)
- [Response Formats](/response-formats)
- [Error Codes](/errors)
- [Rate Limits](/rate-limits)
- [Data Sources](/data-sources)