MCP Search Server for AI Agents

Give your AI agent searchable cloud storage in one config block. Sprigr connects via the Model Context Protocol so agents can store JSON objects, build indexes, and run full-text or hybrid semantic search queries. No custom code, no vector database, no infrastructure to manage.

Start Free — No Credit Card

How MCP search works with Sprigr

Three steps from zero to searchable data inside your AI agent.

1

Connect

Add Sprigr to your AI client’s MCP config. One JSON block with your API key and endpoint. No SDK to install, no server to run.

2

Store

Your agent pushes JSON objects to Sprigr via MCP tool calls. Define searchable attributes and filterable fields. Data is indexed automatically on write.

3

Search

Run full-text queries with typo tolerance, field filters, and pagination. Results return in milliseconds from the nearest edge node.

Why agents need a dedicated search server

Most AI agents lose context between sessions. Bolting on storage usually means writing glue code or managing infrastructure.

Typical approaches

  • Local SQLite: data trapped on one machine, no MCP interface
  • Vector databases: require embedding models, high latency, unpredictable costs
  • Custom REST APIs: weeks of boilerplate before your agent can store a single record
  • In-context stuffing: token limits force you to drop older data
  • File-based memory: no search, no filters, breaks at scale

Sprigr MCP server

  • Cloud-hosted: data available from any machine or session
  • Full-text search with optional hybrid semantic search, keyword precision plus AI-powered meaning matching
  • Zero code: add one MCP config block and your agent has storage
  • Unlimited queries, flat monthly pricing, no per-search fees
  • Multi-tenant: isolated indexes per project with API key scoping and index-level ACLs

Built for agents, not afterthoughts

Every feature is designed for how AI agents actually work with data.

Zero-config cloud storage

No provisioning, no database setup, no migrations. Sign up, get an API key, paste the MCP config. Your agent can start storing and searching data within seconds.

Full-text & hybrid semantic search

Deterministic keyword search with typo tolerance, prefix matching, and field-level boosting. Enable semantic_search on any index to add AI-powered vector search. Results are merged via Reciprocal Rank Fusion for the best of both worlds.

Multi-tenant isolation & ACL

Each API key scopes access to its own data, with optional index-level ACLs to restrict keys to specific indexes. Run separate indexes for different projects, clients, or environments, all from one account. No cross-contamination, no shared state.

Flat, predictable pricing

No per-query fees, no per-token surcharges, no surprise bills when your agent runs a hundred searches in one session. One monthly price based on record count.

REST API + MCP

The same data is accessible via both MCP tool calls and a standard REST API. Use MCP for agent workflows, REST for dashboards, scripts, or non-MCP integrations.

Edge-deployed Rust backend

Sprigr runs across 300+ edge locations globally. The backend is compiled from Rust for native performance wherever your agent runs.

Set up in under a minute

Add Sprigr to your AI client’s MCP configuration file. Here is the claude_desktop_config.json entry:

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

Once connected, your AI agent can create indexes, push records, and search, all through natural conversation. Here is an example session:

Example conversation
You:   Create a Sprigr index called "meeting-notes" with
        searchable attributes title and content, and a
        filterable attribute date.

Agent: Done. Index "meeting-notes" created with 2 searchable
        attributes and 1 filter.

You:   Store this meeting note. Title: "Q1 Planning",
        content: "Agreed to launch MCP integration by March.
        Budget approved for two new hires.", date: "2025-01-15"

Agent: Record stored in "meeting-notes" (id: rec_a1b2c3).

You:   Search meeting notes for "MCP integration"

Agent: Found 1 result:
        • "Q1 Planning" (2025-01-15): "...launch
          MCP integration by March..."

No code written. No database provisioned. The agent handles everything through MCP tool calls, and Sprigr handles storage, indexing, and search on the backend.

What agents build with MCP search

Common patterns from teams using Sprigr as their agent’s memory layer.

Knowledge base agents

Store documentation, SOPs, and reference material. The agent searches its own knowledge base to answer questions accurately instead of guessing from training data.

Conversation memory

Persist key facts and decisions across sessions. Search past conversations by topic, date, or participant instead of re-reading entire transcripts.

Multi-agent coordination

Multiple agents share a Sprigr index as a coordination layer. One agent writes research findings; another searches them to draft reports. Same API key, same data.

Frequently asked questions

What is MCP and why does it matter for search?

MCP (Model Context Protocol) is an open standard created by Anthropic that lets AI assistants connect to external tools and data sources through a uniform interface. Instead of writing a custom API integration for every service, an AI agent can use MCP tool calls to interact with any MCP-compatible server. Sprigr exposes search, indexing, and storage as MCP tools, so your agent gets persistent, searchable memory without any custom code.

Do I need embeddings or a vector database?

No external embedding infrastructure is needed. Sprigr provides full-text search with typo tolerance, prefix matching, and field-level filtering out of the box. For indexes where you want semantic understanding, enable semantic_search and Sprigr generates and stores embeddings automatically. No separate embedding API, no vector database to manage. Results are merged via Reciprocal Rank Fusion for the best of keyword and semantic matching.

How is data stored?

Records are stored in a distributed database running at the edge. Each record is a JSON object with attributes you define when creating the index. Searchable attributes are full-text indexed; filterable attributes support exact-match and range queries. All data is scoped to your API key, ensuring tenant isolation.

Which AI clients work with Sprigr?

Any client that supports the Model Context Protocol. This includes Claude Desktop, Claude Code (Anthropic’s CLI), Cursor, Windsurf, Cline, and custom agents built with the MCP SDK in TypeScript or Python. For clients that do not support MCP, Sprigr also offers a standard REST API with identical functionality.

Is there a free tier?

Yes. The free plan supports up to 1,000 records and unlimited search queries. It includes full MCP and REST API access with no time limit. Paid plans start at $49 per month for higher record limits, additional indexes, and priority support.

Give your AI agent searchable memory

Free for up to 1,000 records. No credit card required.

Start Free — No Credit Card
Related Claude MCP Search AI Agent Storage Documentation Pricing