Does the Sprigr MCP server work with Claude Code?

Yes. Claude Code supports MCP servers through the same configuration format. Add the Sprigr server with claude mcp add and set your API key. All 16 search and storage tools are then available in your terminal coding sessions.

Search MCP Server for Claude Desktop & Claude Code

Q: How do I install the Sprigr MCP server for Claude?

Add the Sprigr MCP server entry to your claude_desktop_config.json file. On macOS this is at ~/Library/Application Support/Claude/claude_desktop_config.json. Then restart Claude Desktop. The agent can self-register for an API key on first use.

Set up Claude MCP search in 30 seconds

Three steps from zero to searchable agent memory.

1

Add the config

Paste the Sprigr MCP server entry into your claude_desktop_config.json. One JSON block, no dependencies to install, no build step.

2

Ask Claude to sign up

On first use, tell Claude to register. The agent calls the signup tool, receives an API key, and the key is stored in your config for all future sessions.

3

Store & search

Claude uses the import tool to push records and the search tool to query them. Notes, code snippets, research, anything you want the agent to remember.

Why Claude needs a search MCP server

Claude is powerful but stateless. Every conversation starts from zero unless you give it persistent storage.

Claude without Sprigr

No memory between conversations
Cannot store or retrieve structured data
Context window is the only “storage”
Must re-paste information every session
Cannot search across past work

Claude with Sprigr MCP

Persistent storage across every conversation
Full-text search over all stored records
Structured JSON data with filterable attributes
Agent self-manages its own knowledge base
Instant retrieval, no re-pasting needed

Built for Claude, designed for agents

Every feature is optimized for the way MCP tools work inside Claude Desktop and Claude Code.

One-line setup

A single JSON block in your MCP config file. No npm packages, no Docker containers, no Python environments. Paste, save, restart. Done.

Agent self-signup

Claude registers for a Sprigr account by calling the signup tool. No separate web portal, no copy-pasting API keys. The agent handles it in conversation.

Full-text & semantic search

Typo-tolerant keyword search plus optional hybrid semantic search. Claude can find records by meaning. A query for “frustrated customer” finds complaints even if those exact words aren’t in the record.

Faceted filtering

Tag records with attributes like category, project, date, or priority. Claude can filter search results by any combination of facets to find precisely the right data.

Persistent across conversations

Data lives in your Sprigr account, not in Claude’s context window. Close a conversation, start a new one tomorrow. Every record is still there and searchable.

Multi-index support

Create separate indexes for different projects or data types. Research notes in one index, code references in another, contacts in a third, all searchable from the same MCP server.

Claude Desktop configuration

Open your claude_desktop_config.json and add the Sprigr MCP server. On macOS, the file is at ~/Library/Application Support/Claude/claude_desktop_config.json.

claude_desktop_config.json

{
  "mcpServers": {
    "sprigr": {
      "command": "npx",
      "args": ["-y", "@sprigr/mcp-server"],
      "env": {
        "SPRIGR_API_KEY": "your-api-key"
      }
    }
  }
}

That is the entire installation. Restart Claude Desktop and 16 Sprigr tools are available in every conversation, including signup, create_index, import_objects, search, get_object, multi_search, export_objects, index management, and alias support.

What a session looks like

Here is a typical first interaction. Claude signs up, stores some data, and searches it, all within the conversation.

Sample conversation

You:  Sign up for a Sprigr account using my email chris@example.com

Claude:  I’ll create your Sprigr account now.
         [Calling tool: signup with email chris@example.com]
         Done. Your account is active and the API key has been stored.

You:  Save these meeting notes from today’s standup:
       - Deploy auth service by Friday
       - Review PR #412 for the billing module
       - Schedule load test for next Wednesday

Claude:  [Calling tool: import with index “meetings”]
         Saved 1 record to the “meetings” index.

You:  What did we say about billing in recent meetings?

Claude:  [Calling tool: search with query “billing” in index “meetings”]
         From your standup on Feb 17: “Review PR #412 for the billing module.”

In the next conversation, hours, days, or weeks later, Claude can search the same meetings index and retrieve every record you have stored.

What developers store in Sprigr

Any structured data that Claude should remember between sessions.

Research notes

Store articles, paper summaries, and reading notes. Search across weeks of research in a single query.

Code snippets

Save reusable patterns, configuration examples, and solutions to tricky bugs. Claude retrieves them when you hit the same problem again.

Meeting summaries

Capture decisions, action items, and key discussion points. Search across months of meetings by topic or participant.

Frequently asked questions

How do I install the Sprigr MCP server for Claude?

Add the Sprigr MCP server entry to your claude_desktop_config.json file. On macOS this is at ~/Library/Application Support/Claude/claude_desktop_config.json. On Windows it is at %APPDATA%Claudeclaude_desktop_config.json. Add the "sprigr" block inside the "mcpServers" object, save the file, and restart Claude Desktop. No packages to install, no build steps. The server runs remotely.

Does Claude remember my API key between conversations?

Yes. Your API key is stored in the MCP server configuration, not inside Claude’s context window. Every new conversation automatically connects to the same Sprigr account with the stored credentials. You never need to re-authenticate or paste an API key.

What data can I store and search?

Any structured JSON data. Common use cases include research notes, code snippets, bookmarks, meeting summaries, contact information, project documentation, and knowledge base articles. Each record can have searchable text fields and filterable attributes such as tags, categories, dates, or priority levels.

Does it work with Claude Code?

Yes. Claude Code supports MCP servers through the same configuration format. Add the Sprigr server with claude mcp add sprigr -- npx -y @sprigr/mcp-server and set your API key with claude mcp add-env sprigr SPRIGR_API_KEY your-api-key. All 16 search and storage tools are then available in your terminal coding sessions.

Is my data private?

Your data is stored in your own Sprigr account, isolated by a unique tenant ID. Sprigr does not train models on your data, share it with third parties, or use it for any purpose other than serving your search queries. All API communication is encrypted over HTTPS, and you can delete your data at any time through the API or admin panel.

Give Claude searchable memory in 30 seconds

Free forever for small projects. Add one line of config and start storing data today.

Start Free — No Credit Card