The request names II-Search-4B, which is a model rather than a software product; none of the candidate sources describe it. The candidates below are search and retrieval tools that fit a general 'what to use' for finding information, with official doors shown in their pages.
A question back: Did you mean a search model you want to run yourself (II-Search-4B is a model), or a search tool to call from an application?
- 1
Elastic: The search database for AIelastic.coverified and signed
Elasticsearch-based search platform offering vector search and agent search across data, with an official MCP server and SDKs 2.
official:MCP server · Elasticsearch MCP ServerSDK · elasticsearchlibrary · Elasticsearch.Netskill · elasticsearch-esql+29 community tools built for it
for agents: search · search · search
- 2
Firecrawl Web Data APIfirecrawl.devverified and signed
Web data API for AI agents that searches and scrapes web pages into agent-usable data, with an official MCP server and SDK 515.
official:MCP server · Firecrawl MCP ServerSDK · firecrawl-pyrepository · firecrawlskill · firecrawlskill · firecrawl-search+48 community tools built for it
for agents: search · firecrawl-search · firecrawl-search
- 3
Qdrantqdrant.techverified and signed
Open-source vector search engine with an official MCP server and client SDKs for similarity search 8.
official:MCP server · mcp-server-qdrantSDK · qdrant-clientskill · qdrant-clients-sdkSDK · @qdrant/js-client-restskill · qdrant-search-quality+45 community tools built for it
for agents: search · qdrant-search-quality · qdrant-skills
- 4
MongoDB Atlasmongodb.comverified and signed
Data platform that combines operational data with vector search for semantic search and retrieval 10.
official:SDK · mongodbskill · mongodb-query-optimizerskill · mongodb-schema-designskill · mongodb-connectionskill · mongodb-natural-language-querying+57 community tools built for it
for agents: find_documents · official · mongodb
- 5
Pineconepinecone.ioverified and signed
AI knowledge platform with vector database search, an official MCP server, and SDKs 717.
official:MCP server · @pinecone-database/mcpSDK · @pinecone-database/pineconeskill · pinecone+10 community tools built for it
for agents: search_index · search_vector · pinecone
Sources
- 2Elastic: The search database for AI | Search, AI agents, Observability, and Security | Elasticelastic.co · read 2026-10-29
- 5Firecrawl | Web Data API for AI Agentsfirecrawl.dev · read 2026-10-29
- 7The trusted AI knowledge company | Pineconepinecone.io · read 2026-10-29
- 8Qdrant - Vector Search Engineqdrant.tech · read 2026-10-29
- 10MongoDB | The Intelligent Data Platform for the AI Era | MongoDBmongodb.com · read 2026-10-29
- 15firecrawl-py: declares "search" (the record we read and signed)unfragile.ai · read 2026-10-24
- 17Pinecone (Activepieces): declares "search_index" (the record we read and signed)unfragile.ai · read 2026-10-24
For agents: the 10 actions behind this answer
GetProductsSearch · Stripe API verified and signed
Search products
search · Elasticsearch.Net verified and signed
spring-boot-testing · spring-boot-testing verified and signed
Expert Spring Boot 4 testing specialist that selects the best Spring Boot testing techniques for your situation with Junit 6 and AssertJ.
arxiv-search · arxiv-search verified and signed
Searches arXiv for preprints and academic papers, retrieves abstracts, and filters by topic. Use when the user asks to find research papers, search arXiv, look up preprints, find academic articles in physics, math, CS, biology, statistics, or related fields.
search · firecrawl-py verified and signed
ai-search-instance-search · Cloudflare API verified and signed
Search
search_index · Pinecone (Activepieces) verified and signed
Search Index — Search indexes by name or list all indexes in your project.
search · qdrant-client verified and signed
SearchSystemInstances · AWS IoT Things Graph verified and signed
Searches for system instances in the user's account.
find_documents · MongoDB (Activepieces) verified and signed
Find Documents — Find documents in a collection
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.