LLM provider intelligence: recommendations, pricing, and status
Inferred from the transports this listing declares (streamable-http). A client not listed here hasn’t been ruled out — it just isn’t something Forge can confirm.
Verification confirms publisher identity (repo ownership), not code safety. The security scan covers known CVEs and suspicious install scripts.
Read from a real MCP initialize → tools/list handshake against the declared endpoint. No tool was ever invoked — tools/list is the read-only introspection call the protocol defines for this. It reflects what the server advertised at that moment; a hosted endpoint is not pinned to any version and can change without notice.
https://intel.memoryapi.org/mcp3 tools · 683msrecommend_llmGet the best LLM provider for your specific agent task. Returns top 3 ranked recommendations with reasoning.Get the best LLM provider for your specific agent task. Returns top 3 ranked recommendations with reasoning.
| Parameter | Type | Description |
|---|---|---|
| task | string | Task type: tool_calling, reasoning, rag, summarization, high_volume, low_latency, general |
| priority | string | Optimize for: balanced, cost, speed, quality |
| require_tool_calling | boolean | Only return providers with tool calling support |
| min_context | number | Minimum context window needed in tokens |
| max_price_per_million | number | Maximum input price per million tokens (USD) |
list_providersList LLM providers with their capabilities, pricing, and agent scores. Filter by specific requirements.List LLM providers with their capabilities, pricing, and agent scores. Filter by specific requirements.
| Parameter | Type | Description |
|---|---|---|
| tool_calling | boolean | Only show providers with tool calling |
| x402_native | boolean | Only show x402-native providers |
| max_price | number | Max input price per million tokens |
| best_for | string | Filter by use case: tool_calling, reasoning, cost, speed, long_context, rag |
check_provider_statusCheck operational status and recent latency for one or all LLM providers.Check operational status and recent latency for one or all LLM providers.
| Parameter | Type | Description |
|---|---|---|
| provider | string | Specific provider slug (e.g. openai-gpt4o). Omit for all. |
3 of 3 tools published a description.
Tool names and descriptions are written by the publisher and shown verbatim as inert text. They are the strings an MCP client passes to a model, so Forge scans them for prompt-injection patterns — any finding appears with the security scan above. “Privileged” is a keyword match on the tool name, not an audit of what the tool does: a benign-sounding name can still do anything.
LLM provider intelligence: recommendations, pricing, and status
Linked names open Forge’s index of every entry observed exposing that tool. Browse all indexed tools.
This entry publishes no npm package, so Forge has no dependency tree for it. That is a gap in coverage — not a statement that it has no dependencies.