MCP Server for AI Agents

Your search as tools for AI agents

opensolr-mcp is a Model Context Protocol server. Any MCP client, such as Cursor or Windsurf, gets 16 Opensolr tools: it can search your index, read your documents, index new files and answer from what it finds.

Set it up

Add the server to the MCP configuration of your client:

{
  "mcpServers": {
    "opensolr": {
      "command": "uvx",
      "args": ["opensolr-mcp"],
      "env": {
        "OPENSOLR_EMAIL": "you@example.com",
        "OPENSOLR_API_KEY": "YOUR_OPENSOLR_API_KEY"
      }
    }
  }
}

The agent can do whatever the API key allows. Give it a scoped key limited to the tools and indexes it needs.

The tools

• Search: opensolr_search (words and meaning, filters, a date range), opensolr_search_by_image (search with a photo).
• Read and answer: opensolr_read_document, opensolr_ai_answer (a grounded answer), opensolr_describe_image, opensolr_extract_text (local files read without indexing them).
• Write: opensolr_add_documents, opensolr_index_files (a local file or folder, a PDF page by page), opensolr_delete_documents, opensolr_ingest_status.
• Indexes: opensolr_list_indexes, opensolr_index_info, opensolr_create_index, opensolr_vector_regions, opensolr_check_schema, opensolr_apply_schema.

Links

• MCP product page
• PyPI and GitHub, with the full guide in the README.
• No account yet? Use the public demo account.