Mcp Server
- Updated July 9, 2026
- infino-ai/infino-mcp
Infino MCP is a Model Context Protocol server that provides keyword, vector, hybrid, and SQL retrieval over data on object storage so AI agents can query large datasets without custom retrieval pipelines.
About
Infino MCP is a Model Context Protocol server that exposes keyword, vector, hybrid, and SQL retrieval over datasets stored on object storage. Developers reach for it when building AI agents that must query large file-backed corpora without standing up a separate search stack. It centralizes retrieval modes behind MCP tools so agents can run structured and semantic queries in one integration.
- Keyword, vector, hybrid, and SQL search modes
- Queries data directly on object storage
- Built for AI agent consumption via MCP
- Reduces custom RAG pipeline work
Mcp Server by the numbers
- Data as of Jul 10, 2026 (Skillselion catalog sync)
claude mcp add --env INFINO_MCP_URI=YOUR_INFINO_MCP_URI --env INFINO_MCP_ENABLE_WRITES=YOUR_INFINO_MCP_ENABLE_WRITES --env INFINO_MCP_EMBED_MODEL=YOUR_INFINO_MCP_EMBED_MODEL --env INFINO_MCP_S3_ENDPOINT=YOUR_INFINO_MCP_S3_ENDPOINT --env INFINO_MCP_S3_REGION=YOUR_INFINO_MCP_S3_REGION mcp-server -- npx -y @infino-ai/mcp-serverAdd your badge
Show developers this MCP server is listed on Skillselion. Paste this into your README.
| Package | @infino-ai/mcp-server |
|---|---|
| Transport | STDIO |
| Auth | None |
| Last updated | July 9, 2026 |
| Repository | infino-ai/infino-mcp ↗ |
How do I let an AI agent search and query files in object storage with both semantic and SQL-style retrieval?
Expose keyword, vector, hybrid, and SQL retrieval over object-storage datasets to AI agents via MCP.
Who is it for?
Developers building agent features that need hybrid search and SQL over object-storage-backed data.
Skip if: Teams that only need simple file reads or already run a dedicated managed vector database with native SDKs.
What you get
The agent receives ranked or structured query results from object-storage data through MCP tool calls.
Recommended MCP Servers
A2dbSafe, read-only database access for AI agents.2
AdoMcpDatabase MCP server for schema discovery, comments, and SQL queries.1
Afgong Sqlite Mcp ServerExplore your Messages SQLite database to browse tables and inspect schemas with ease.
AI ERDAI-powered ERD design tool.
AirtableCreate, read, update, and delete records in Airtable bases and tables29
AirtableRead and write access to Airtable database schemas, tables, and records.455FAQ
What retrieval modes does Infino MCP support?
It supports keyword, vector, hybrid, and SQL retrieval over data stored on object storage.
Who is Infino MCP designed for?
It is designed for AI agents that need programmatic access to search and query object-storage datasets via MCP.
Does Infino MCP replace a full database?
It focuses on retrieval over object-storage data for agents; it is not a general-purpose transactional database replacement.