# Opensolr MCP

> Opensolr MCP is a freemium MCP server for knowledge and memory. Hybrid keyword and semantic search, indexing and RAG answers over Opensolr Solr indexes. It runs locally on your machine and is started by your AI client.

- **Kind:** MCP server
- **Pricing:** Freemium
- **Platforms:** CLI, API
- **Website:** https://opensolr.com/mcp
- **Repository:** https://github.com/phpcip/opensolr-mcp
- **MCP Registry name:** com.opensolr/opensolr-mcp
- **Categories:** knowledge and memory, databases, web search and scraping
- **Listing updated:** 2026-11-15

## About

Opensolr's MCP server turns a managed Apache Solr index into tools an agent can call with plain text. Embeddings are computed server-side, so there is no embedding model to configure and no vector database to run. Search blends BM25 keyword and kNN semantic retrieval, supports Solr filters and date ranges, and a matching PDF comes back as its best page with a link that opens at that page.

It goes beyond text queries. An agent can search with a photo, since Opensolr reads the picture's labels, OCR text and any barcode or QR code and searches on those words. Local files and folders can be indexed, with PDFs split one document per page and scans and pictures read through OCR, or read without indexing at all. The opensolr_ai_answer tool builds a grounded answer from the top hybrid hits.

The package is opensolr-mcp on PyPI, started with uvx over stdio and needing an account email and API key. A shared public demo account exists with a preloaded news index, but anything created there is deleted after 3 days and visible to others, so keep real data out of it.

## Features

- **Hybrid search:** BM25 plus kNN retrieval with filters and date ranges.
- **Search by image:** Uses a photo's labels, OCR text and barcodes as the query.
- **Grounded RAG answers:** Top hybrid hits feed an LLM answer.
- **File indexing and OCR:** Index PDFs page by page, Office-style documents and scans.
- **Index management:** Create indexes in a vector region, check and apply the schema.
- **Server-side embeddings:** No embedding model or vector store to run yourself.

## Good for

- Give an agent search over your own documents
- Answer questions from a folder of PDFs with citations to pages
- Find products or documents from a photo
- Prototype RAG without hosting a vector database
- Index and query scanned files through OCR

## Install

### Claude Code (Terminal)

```sh
claude mcp add opensolr-mcp --env OPENSOLR_EMAIL='<OPENSOLR_EMAIL>' --env OPENSOLR_API_KEY='<OPENSOLR_API_KEY>' -- uvx opensolr-mcp
```

### Claude Desktop (claude_desktop_config.json)

```json
{
  "mcpServers": {
    "opensolr-mcp": {
      "command": "uvx",
      "args": [
        "opensolr-mcp"
      ],
      "env": {
        "OPENSOLR_EMAIL": "<OPENSOLR_EMAIL>",
        "OPENSOLR_API_KEY": "<OPENSOLR_API_KEY>"
      }
    }
  }
}
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "opensolr-mcp": {
      "command": "uvx",
      "args": [
        "opensolr-mcp"
      ],
      "env": {
        "OPENSOLR_EMAIL": "<OPENSOLR_EMAIL>",
        "OPENSOLR_API_KEY": "<OPENSOLR_API_KEY>"
      }
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "opensolr-mcp": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "opensolr-mcp"
      ],
      "env": {
        "OPENSOLR_EMAIL": "<OPENSOLR_EMAIL>",
        "OPENSOLR_API_KEY": "<OPENSOLR_API_KEY>"
      }
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "opensolr-mcp": {
      "command": "uvx",
      "args": [
        "opensolr-mcp"
      ],
      "env": {
        "OPENSOLR_EMAIL": "<OPENSOLR_EMAIL>",
        "OPENSOLR_API_KEY": "<OPENSOLR_API_KEY>"
      }
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "opensolr-mcp": {
      "command": "uvx",
      "args": [
        "opensolr-mcp"
      ],
      "env": {
        "OPENSOLR_EMAIL": "<OPENSOLR_EMAIL>",
        "OPENSOLR_API_KEY": "<OPENSOLR_API_KEY>"
      }
    }
  }
}
```

## Tools

- `opensolr_search`: Hybrid or semantic search with filters and date range
- `opensolr_search_by_image`: Search with a photo using its labels, OCR and barcodes
- `opensolr_read_document`: Read a result in full
- `opensolr_ai_answer`: Grounded RAG answer from the top hybrid hits
- `opensolr_index_files`: Index a local file or folder
- `opensolr_extract_text`: Read local files without indexing them
- `opensolr_describe_image`: Describe a picture, its text and labels
- `opensolr_add_documents`: Index plain text with metadata
- `opensolr_delete_documents`: Remove documents by id
- `opensolr_list_indexes`: List the account's indexes
- `opensolr_index_info`: Inspect an index
- `opensolr_create_index`: Provision a vector index in a region
- `opensolr_vector_regions`: List vector-enabled regions
- `opensolr_check_schema`: Check whether an index supports each tool
- `opensolr_apply_schema`: Install the Opensolr vector schema on an index

## FAQ

### How do I run it?

With uvx opensolr-mcp over stdio, setting OPENSOLR_EMAIL and OPENSOLR_API_KEY.

### Is there a free way to try it?

Yes, a free-forever Opensolr plan without a card, or a shared demo account whose data is deleted after 3 days.

### Is the demo account private?

No. It is shared with everyone and has 200 MB bandwidth and 50 MB disk limits per index.

### Which clients work?

Claude Desktop, Claude Code, Cursor, Windsurf and other MCP clients.

### Is Opensolr MCP free?

Opensolr MCP has a free plan, with paid plans for more usage or features.

### How do I add Opensolr MCP to Claude Code?

Run this command in your terminal: claude mcp add opensolr-mcp --env OPENSOLR_EMAIL='<OPENSOLR_EMAIL>' --env OPENSOLR_API_KEY='<OPENSOLR_API_KEY>' -- uvx opensolr-mcp

### What are the best alternatives to Opensolr MCP?

The closest alternatives to Opensolr MCP are Scrapling MCP Server, Codebase Memory, XERJ, Firecrawl MCP Server and Claude Code Ultimate Guide.

## Alternatives

- [Scrapling MCP Server](https://ai-powered.com/mcp/scrapling-mcp-server): Scrapling MCP Server is an open-source MCP server for web search and scraping.
- [Codebase Memory](https://ai-powered.com/mcp/codebase-memory): Codebase Memory is an open-source MCP server for knowledge and memory.
- [XERJ](https://ai-powered.com/mcp/xerj): XERJ is an open-source MCP server for knowledge and memory.
- [Firecrawl MCP Server](https://ai-powered.com/mcp/firecrawl-mcp-server): Firecrawl MCP Server is a freemium MCP server for web search and scraping.
- [Claude Code Ultimate Guide](https://ai-powered.com/mcp/claude-code-ultimate-guide): Claude Code Ultimate Guide is an open-source MCP server for ai models and llm tooling.
- [SearXNG Search](https://ai-powered.com/mcp/searxng-search): SearXNG Search is an open-source MCP server for web search and scraping.
- [Nautilus Compass Memory](https://ai-powered.com/mcp/nautilus-compass-memory): Nautilus Compass Memory is an open-source MCP server for knowledge and memory.
- [Midplane](https://ai-powered.com/mcp/midplane): Midplane is an open-source MCP server for databases.

---
Source: https://ai-powered.com/mcp/opensolr-mcp
