Where do I find my Upstash REST URL and Token?

Log in to the [**Upstash Console**](https://console.upstash.com), select your Redis database, and look for the **REST API** section. You'll find the HTTPS Endpoint (your REST URL, e.g. `https://xxx-yyy-12345.upstash.io`) and the **Token** value. Copy both and paste them here. There are two token types: Standard (full access) and Read-Only (read-only commands). Use Standard for full functionality.

What Redis commands are supported via the REST API?

The Upstash REST API supports most Redis commands including: Strings (GET, SET, DEL, EXISTS, EXPIRE, TTL, INCR, DECR), Hashes (HSET, HGET, HGETALL), Lists (LPUSH, RPUSH, LRANGE, LLEN), Sets (SADD, SMEMBERS, SISMEMBER, SREM), Keys (KEYS, TYPE, PING), and Pub/Sub (PUBLISH). The pipeline endpoint allows executing multiple commands in a single request. Blocking commands (BLPOP, BRPOP) and WATCH/UNWATCH are not supported.

Can I execute multiple commands atomically?

The `pipeline` tool sends multiple commands in a single HTTP request for efficiency, but it is NOT atomic — other commands may interleave between them. For atomic multi-command execution, Upstash supports the `/multi-exec` endpoint (same syntax as pipeline but guarantees atomicity). However, this MCP server currently exposes the standard pipeline tool for batch operations.

Is the Upstash REST API rate-limited?

Upstash does not enforce a fixed RPS limit. Instead, your plan defines a daily command limit. Each REST call counts as one command (or multiple commands if using pipeline). If you exceed your daily limit, commands will fail with a 400 error. Check your Upstash console for current usage. For high-throughput scenarios, consider using the pipeline endpoint to batch multiple commands into single HTTP requests.

Upstash MCP Server for LlamaIndex 23 tools — connect in under 2 minutes

Name: Upstash
Availability: InStock
Author: Vinkius

docs.llamaindex.ai/en/stable/module_guides/tools/mcp

Built by Vinkius GDPR 23 Tools Framework

LlamaIndex specializes in data-aware AI agents that connect LLMs to structured and unstructured sources. Add Upstash as an MCP tool provider through Vinkius and your agents can query, analyze, and act on live data alongside your existing indexes.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    mcp_client = BasicMCPClient("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
    mcp_tool_spec = McpToolSpec(client=mcp_client)
    tools = await mcp_tool_spec.to_tool_list_async()

    agent = FunctionAgent(
        tools=tools,
        llm=OpenAI(model="gpt-4o"),
        system_prompt=(
            "You are an assistant with access to Upstash. "
            "You have 23 tools available."
        ),
    )

    response = await agent.run(
        "What tools are available in Upstash?"
    )
    print(response)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Upstash MCP Server

Connect your Upstash Redis database to any AI agent and interact with your serverless data store through natural conversation — no Redis CLI needed.

LlamaIndex agents combine Upstash tool responses with indexed documents for comprehensive, grounded answers. Connect 23 tools through Vinkius and query live data alongside vector stores and SQL databases in a single turn. ideal for hybrid search, data enrichment, and analytical workflows.

What you can do

Health Checks — Ping your database to verify connectivity and inspect server health
String Operations — Get, set and delete key-value pairs with optional TTL management
Hash Management — Store and retrieve structured data as field-value pairs within hash keys
List Operations — Push, pop and range elements from Redis lists for queue and stack patterns
Set Operations — Add, remove and query set membership for unique collections
Key Discovery — List keys by pattern, check existence, inspect data types and view TTL values
Numeric Operations — Increment and decrement counters atomically
Pub/Sub Messaging — Publish messages to channels for event-driven architectures
Pipeline Execution — Execute multiple commands in a single HTTP request for batch operations

The Upstash MCP Server exposes 23 tools through the Vinkius. Connect it to LlamaIndex in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Upstash to LlamaIndex via MCP

Follow these steps to integrate the Upstash MCP Server with LlamaIndex.

Install dependencies

Run pip install llama-index-tools-mcp llama-index-llms-openai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 23 tools from Upstash

Why Use LlamaIndex with the Upstash MCP Server

LlamaIndex provides unique advantages when paired with Upstash through the Model Context Protocol.

Data-first architecture: LlamaIndex agents combine Upstash tool responses with indexed documents for comprehensive, grounded answers

Query pipeline framework lets you chain Upstash tool calls with transformations, filters, and re-rankers in a typed pipeline

Multi-source reasoning: agents can query Upstash, a vector store, and a SQL database in a single turn and synthesize results

Observability integrations show exactly what Upstash tools were called, what data was returned, and how it influenced the final answer

Upstash + LlamaIndex Use Cases

Practical scenarios where LlamaIndex combined with the Upstash MCP Server delivers measurable value.

Hybrid search: combine Upstash real-time data with embedded document indexes for answers that are both current and comprehensive

Data enrichment: query Upstash to augment indexed data with live information before generating user-facing responses

Knowledge base agents: build agents that maintain and update knowledge bases by periodically querying Upstash for fresh data

Analytical workflows: chain Upstash queries with LlamaIndex's data connectors to build multi-source analytical reports

Upstash MCP Tools for LlamaIndex (23)

These 23 tools become available when you connect Upstash to LlamaIndex via MCP:

decr

If the key does not exist, it is initialized to 0 before the operation. Returns the new value after decrementing. Decrement a numeric value in Upstash Redis

del

Returns 1 if the key was deleted, 0 if it did not exist. WARNING: this operation is irreversible. Delete a key from Upstash Redis

exists

This is a lightweight way to check key presence without retrieving the value. Check if a key exists in Upstash Redis

expire

The key will be automatically deleted when the TTL reaches zero. Returns 1 if the timeout was set, 0 if the key does not exist. Set a TTL on a key in Upstash Redis

get

Returns null if the key does not exist. This is the primary read operation for string data. Get a value from Upstash Redis

hget

Returns null if the key or field does not exist. Get a field value from a Redis hash

hgetall

Returns an object with all fields and their values. Returns an empty object if the key does not exist. Get all fields and values from a Redis hash

hset

If the key does not exist, a new hash is created. If the field already exists, its value is overwritten. Returns the number of fields added (1 for new, 0 for updated). Set a field in a Redis hash

incr

If the key does not exist, it is initialized to 0 before the operation. Returns the new value after incrementing. Increment a numeric value in Upstash Redis

key_type

Get the data type of a key in Upstash Redis

list_keys

Use "*" for all keys, "prefix:*" for keys with a prefix, or "*:suffix" for suffix matching. WARNING: KEYS can be slow on large databases — use sparingly. List keys in Upstash Redis

llen

Returns 0 if the key does not exist. Get the length of a Redis list

lpush

If the key does not exist, a new list is created. Returns the length of the list after the push. Push values to the left of a Redis list

lrange

Use 0 as start and -1 as stop to get all elements. Positive indices count from the head (0 = first), negative indices count from the tail (-1 = last). Get a range of elements from a Redis list

pipeline

Commands are sent as a JSON array of arrays, e.g. [["SET","k1","v1"],["GET","k1"],["INCR","counter"]]. Returns an array of results in the same order. Note: the pipeline is NOT atomic (other commands may interleave) — use /multi-exec for atomicity. WARNING: this is a powerful tool — review commands carefully before execution. Execute multiple commands atomically via Upstash pipeline

publish

Returns the number of subscribers that received the message. This is a fire-and-forget operation — subscribers must be actively listening. Publish a message to a Redis channel

rpush

If the key does not exist, a new list is created. Returns the length of the list after the push. Push values to the right of a Redis list

sadd

Duplicate members are ignored. If the key does not exist, a new set is created. Returns the number of members that were added. Add members to a Redis set

set

Optionally set an expiry time in seconds using the ex parameter. Overwrites any existing value at the key. Returns "OK" on success. This is the primary write operation for string data. Set a value in Upstash Redis

sismember

This is a fast O(1) membership check. Check if a member is in a Redis set

smembers

Returns an array of all unique members. Returns an empty array if the key does not exist. Get all members of a Redis set

srem

Non-existent members are ignored. Returns the number of members that were removed. Remove members from a Redis set

ttl

Returns -1 if the key has no expiry, -2 if the key does not exist. Get the TTL of a key in Upstash Redis

Example Prompts for Upstash in LlamaIndex

Ready-to-use prompts you can give your LlamaIndex agent to start working with Upstash immediately.

"Check if my Upstash Redis database is responding."

"Set a feature flag called 'dark_mode' to true for user 'user123' with a 1 hour expiry."

"Show me all keys matching the pattern 'session:*' and check their data types."

Troubleshooting Upstash MCP Server with LlamaIndex

Common issues when connecting Upstash to LlamaIndex through the Vinkius, and how to resolve them.

BasicMCPClient not found

Install: pip install llama-index-tools-mcp

Upstash + LlamaIndex FAQ

Common questions about integrating Upstash MCP Server with LlamaIndex.

How does LlamaIndex connect to MCP servers?

Use the MCP client adapter to create a connection. LlamaIndex discovers all tools and wraps them as query engine tools compatible with any LlamaIndex agent.

Can I combine MCP tools with vector stores?

Yes. LlamaIndex agents can query Upstash tools and vector store indexes in the same turn, combining real-time and embedded data for grounded responses.