Infino

AnMCPserver forInfino— it lets an AI agent runkeyword,semantic,hybrid, andSQLretrieval over your data on object storage, from any MCP-compatible client (Claude Code, Claude Desktop, Cursor, VS Code, and others). Published on npm as@infino-ai/mcp-serverand listed on theofficial MCP Registryasio.github.infino-ai/mcp-server(which propagates to catalogs like Smithery, Glama, and PulseMCP).

- Requirements
- Quick start
- Claude Code plugin (one-step install)
- Client setup

- Claude Code
- Claude Desktop
- Cursor
- VS Code
- Other MCP clients

- Node.js ≥ 18(the server runs as a Node process over stdio).
- An MCP-compatible client(Claude Code, Claude Desktop, Cursor, VS Code, …).
- Data reachable by Infino— a local directory, a bucket with credentials available in the environment, or a hosted Infino Cloud endpoint with an API key (seeStorage backends).
- On first run the server downloads the local embedding model (~90 MB) once and caches it; subsequent runs are offline for embedding.

{ "command": "npx", "args": ["-y", "@infino-ai/mcp-server"], "env": { "INFINO_MCP_URI": "/Users/me/.infino/memory" } }

To serve ahosted Infino Clouddatabase instead, pointINFINO_MCP_URIat thehttps://<host>/<database>endpoint and supply your API key — everything else (the tools, the read-only default) is identical:

{ "command": "npx", "args": ["-y", "@infino-ai/mcp-server"], "env": { "INFINO_MCP_URI": "https://api.platform.infino.ai/my-database", "INFINO_API_KEY": "inf_…" } }

The sections below show the exact place each client expects this block.

ForClaude Code, this repo is also a plugin marketplace. Installing the plugin wires up the MCP serverplusa how-to-use skill and an/infino-searchcommand in one step — no JSON to edit. Inside Claude Code:

/plugin marketplace add infino-ai/infino-mcp /plugin install infino@infino-ai

On enable you'll be prompted for yourInfino data URI(INFINO_MCP_URI) and whether toenable writes. That's it — theinfino_tools, theusing-infinoskill, and/infino-search <query>are then available. (Other clients: use theClient setupconfigs below.)

claude mcp add infino \ --scope user \ -e INFINO_MCP_URI=/Users/me/.infino/memory \ -- npx -y @infino-ai/mcp-server

{ "mcpServers": { "infino": { "command": "npx", "args": ["-y", "@infino-ai/mcp-server"], "env": { "INFINO_MCP_URI": "/Users/me/.infino/memory" } } } }

{ "mcpServers": { "infino": { "command": "npx", "args": ["-y", "@infino-ai/mcp-server"], "env": { "INFINO_MCP_URI": "/Users/me/.infino/memory" } } } }

VS Code (1.102+) reads MCP servers from.vscode/mcp.jsonin the workspace (or your usermcp.jsonvia the command palette →MCP: Open User Configuration). Note the top-level key isserversand each entry declares"type": "stdio":

{ "servers": { "infino": { "type": "stdio", "command": "npx", "args": ["-y", "@infino-ai/mcp-server"], "env": { "INFINO_MCP_URI": "/Users/me/.infino/memory" } } } }

command: npx args: -y @infino-ai/mcp-server env: INFINO_MCP_URI=<path-or-bucket-uri> (plus any options below)

"env": { "INFINO_MCP_URI": "s3://my-bucket/infino", "INFINO_MCP_EMBED_PROVIDER": "openai", "INFINO_MCP_EMBED_BASE_URL": "https://my-resource.openai.azure.com/openai/v1", "INFINO_MCP_EMBED_API_KEY": "…", "INFINO_MCP_EMBED_MODEL": "text-embedding-3-small" }

// Local directory "env": { "INFINO_MCP_URI": "/Users/me/.infino/memory" } // AWS S3 — ambient AWS_ credentials, default endpoint "env": { "INFINO_MCP_URI": "s3://my-bucket/infino", "AWS_ACCESS_KEY_ID": "…", "AWS_SECRET_ACCESS_KEY": "…" } // S3-compatible (Cloudflare R2 / MinIO / Backblaze B2) — custom endpoint "env": { "INFINO_MCP_URI": "s3://my-bucket/infino", "AWS_ENDPOINT_URL": "https://<account>.r2.cloudflarestorage.com", "AWS_ACCESS_KEY_ID": "…", "AWS_SECRET_ACCESS_KEY": "…" } // Azure Blob "env": { "INFINO_MCP_URI": "az://my-container/infino", "AZURE_STORAGE_ACCOUNT": "…", "AZURE_STORAGE_KEY": "…" } // Infino Cloud (hosted) — the database is the last path segment "env": { "INFINO_MCP_URI": "https://api.platform.infino.ai/my-database", "INFINO_API_KEY": "inf_…" }

On a hosted connection the search, SQL, and (when enabled) write tools all behave exactly as they do locally — the only difference is where the data lives. Compaction and garbage collection are handled server-side, so they are not exposed as client operations. Note that semantic and hybrid search still embed querieslocallyin this server, soINFINO_MCP_EMBED_MODELmust match the model that produced the hosted table's stored vectors (see the OpenAI / Azure OpenAI note above) — this matters especially when someone else ingested the data.

The engine's search table functions (bm25_search,vector_search,hybrid_search, …) are not callable frominfino_sql— retrieval goes through the dedicated search tools above, which embed and project for you.infino_sqlis for filters, joins, and aggregates.

This server runs locally, beside the client, and keeps data and credentials on the user's machine.

- Local execution, no inbound listener.It runs as a subprocess of your MCP client over stdio and opens no network listener. In the default local/bucket mode it contacts no remote service. WhenINFINO_MCP_URIis a hostedhttps://endpoint, it makesoutboundTLS calls to that endpoint to serve searches, SQL, and (if enabled) writes — so the data in those requests reaches the hosted service you configured, and nothing else.
- No data sent for embedding.Query and document embedding uses a local model — text is never sent to a third-party embedding API. There is no embedding API key to provision or leak. (This holds in both local and hosted mode: only the resulting query vector, not the raw text of the embed input, is sent to a hosted endpoint.)
- Credentials stay in the environment.Storage credentials (AWS_/AZURE_) and the hosted API key (INFINO_API_KEY) are read from environment variables and used only to reach the store or endpoint you configured. They are never logged or returned in tool output.
- Read-only by default.WithoutINFINO_MCP_ENABLE_WRITES, the write tool is not even advertised to the agent, andinfino_sqlrejects anything but a singleSELECT/WITH. Enable writes deliberately, and prefer scoping the server to data the agent is allowed to modify.
- Least privilege.PointINFINO_MCP_URIat the narrowest dataset the task needs, and supply storage credentials scoped to that bucket/prefix.

Semantic search embeds locally with Hugging Face transformers.js (all-MiniLM-L6-v2, 384-dim by default; override withINFINO_MCP_EMBED_MODEL). The server embedsboththe documents it ingests (viainfino_add_documents) and your queries with the same model, so they align in the same vector space.

If you changeINFINO_MCP_EMBED_MODEL, the table's vector index must match the new model's dimension — embeddings produced by different models are not comparable, and a dimension mismatch will fail at search time.

The server depends on the published@infino-ai/infinoNode binding, which resolves from public npm like any other dependency.

npm install npm run build INFINO_MCP_URI=/path/to/data node dist/index.js # runs on stdio

Point a client atnode /absolute/path/dist/index.jsover stdio to dogfood a local build, or use theMCP Inspector:

npx @modelcontextprotocol/inspector node dist/index.js

Allow your agent to connect to Pocketbase with ease.