Run of Show deck from GraphSummit Bengaluru held on Oct 7, 2025.
Contains: Agenda, Keynote, Customer Stories & Product Vision & Roadmap from Neo4j
Speakers: Jim Webber, Sunil Thakur, Shalabh Garg, Anurag Tandon
Agenda
09:30 Welcome fromNeo4j
Ish Thukral, Country Head-India, Neo4j
09:40 Graphs + AI: Transform Your Data Into Knowledge
Jim Webber, Chief Scientist, Neo4j
10:10 Connected Data, Smarter AI: The AWS -Neo4j Advantage
Biswajit Das, Head of Data & AI, AWS
10:30 Graph-Driven Digital Twin of Enterprise IS: The Infosys Approach
Sunil Thakur, Associate Vice President–Data & Analytics at Infosys
10:50 Morning Break & Networking
11:10 How OpenText Leverages Neo4j Graphs to Modernize IAM
Shalabh Garg, Principal Product Manager, OpenText
11:30 Neo4j: Product Vision & Roadmap
Anurag Tandon, VP of Product Management
& User Experience Neo4j
8.
Agenda
12:00 Q&A Panel
12:30Lunch
14:00 Concurrent Hands-On Workshops
Option A: Create a Graph-Backed App from Scratch | Level 1, Junior Ballroom
Option B: Building Smarter GenAI Apps with Knowledge Graphs | Level 1, Grand Ballroom
16:30 Networking Drinks & Snacks
9.
Graphs + AI:
YourEnterprise
Advantage
Dr. Jim Webber | Chief Scientist | Neo4j
The power of
thegraph model
Relationships
connect nodes
:LOCATED_IN
Relationships can
have properties
(key-value pairs)
name: Lakshmi Kumar
date_of_birth: 1984-03-01
employee_ID: 1
City Company Employee
Nodes represent
entities
Relationships
are directional
:CEO_OF
start_date:
2022-11
toponym: Bengaluru
nickname: Garden City
org: Ajeya AI
type: Pvt. Ltd. Company
founded: 2018
Nodes typically
have properties too
Nodes usually have
one or more labels
23
Trusted by 84of the
9 / 10
Top Telcos
9 /10
Top Aerospace & Defense
20 / 20
Top US banks
10 / 10
Top Automakers
9 / 10
Top Pharmaceuticals
10 / 10
Top Technology & Software
8 / 10
Top Insurance Companies
8 / 10
Top Retailers
What is this?
●Has been extensively
trained on a wide-range of
eclectic subjects
● Answers confidently, even
when making things up
● Opaque about reasoning
● Expensive
25
● LLMs area lossy compression of the
internet as it was
● Knowledge graphs provide lossless
information you care about now
30.
AI is changinghow we develop applications.
Quickly.
"AI is fundamentally disrupting
software development ...”
-Innovation Endeavors (VC) / Axios, June 2025
“...AI pipelines need dynamic schemas
to [handle] evolving sources.”
-2025 Future Enterprise Resiliency & Spending, IDC
“A business data fabric reduces
latency and powers advanced AI…”
-Venture Beat, Enhancing business agility with rapid
data integration and advanced AI, 2025
"Organizations with rich, [connected]
knowledge graphs will have a
significant competitive advantage…”
-Gartner Perception is the New Superpower For the
Future of Analytics and BI, 2025
"[GenAI]…will disrupt the very
software that enabled the last wave
of transformation."
-Harvard Business Review, May 2025
31.
Why we buildapplications is
NOT changing
Problem to Solve
Business Process to Map
Questions to Answer
Where
When
How
Who
What
?
From Static Logicto Dynamic Reasoning
1
Hardcoded
rules defined at
compile-time
Create
(Create, Read,
Update, Delete)
Upload
Read
Update
Delete
CRUD
Reason, adapt & make
decisions in real time
based on goals, context
& changing inputs
Real time
decisions
Proactive
Connected
context
Agents working in
coordination
Behavior by code,
prompts & models
Agentic AI
34.
From Request-Response toGoal-Oriented
2
React to user
input
Create
(Create, Read,
Update, Delete)
Upload
Read
Update
Delete
CRUD
Proactively pursue goals,
orchestrate tasks, and
learn from feedback
Real time
decisions
Proactive
Connected
context
Agents working in
coordination
Behavior by code,
prompts & models
Agentic AI
35.
From Monoliths toComposable Systems
3
Tightly coupled
architecture
Create
(Create, Read,
Update, Delete)
Upload
Read
Update
Delete
CRUD
Multiple specialized
agents working in
coordination
Real time
decisions
Proactive
Connected
context
Agents working in
coordination
Behavior by code,
prompts & models
Agentic AI
36.
From Code-Centric toPrompt-Driven
4
Behavior defined
exclusively by
code
Create
(Create, Read,
Update, Delete)
Upload
Read
Update
Delete
CRUD
Behavior defined by a
combination of code,
prompts and AI models
Real time
decisions
Proactive
Connected
context
Agents working in
coordination
Behavior by code,
prompts & models
Agentic AI
37.
From CRUD toContext
5
Logic centered
around
Create Read
Update Delete
Create
(Create, Read,
Update, Delete)
Upload
Read
Update
Delete
CRUD
Logic set by reasoning,
goals & rich, connected
context (users, tasks,
history, environment)
Real time
decisions
Proactive
Connected
context
Agents working in
coordination
Behavior by code,
prompts & models
Agentic AI
38.
1 From StaticLogic to Dynamic Reasoning
From Request-Response to Goal-Oriented
2
From Monoliths to Composable Systems
3
From Code-Centric to Prompt-Driven
4
From CRUD to Context
5
The Application Architecture is Changing
39.
Most data isstill stored
in rows & columns
Structured for fixed
questions and static data
Relationships are implied,
or even lost
Apps will
change.
So must the
data layer.
Kiruna Table
Chat HistoryHi, I'm ABK the carpenter and I fixed this problem by applying 2 drops of
glue to the table legs before step 8.
Product
Bill-of-materials
Product Issue
Tracker
Kiruna Table
Assembly Guides
42.
Kiruna Table
Chat HistoryHi, I'm ABK the carpenter and I fixed this problem by applying 2 drops of
glue to the table legs before step 8.
Product
Bill-of-materials
Product Issue
Tracker
Kiruna Table
Assembly Guides
43.
Kiruna Table
Chat HistoryHi, I'm ABK the carpenter and I fixed this problem by applying 2 drops of
glue to the table legs before step 8.
Product
Bill-of-materials
Product Issue
Tracker
Kiruna Table
Assembly Guides
Unified
RAG corpus
and agentic
memory
44.
Properties of anamazing knowledge layer for AI
Efficient Storage of
Structured, Semi-structured
and Unstructured data
1
Connects Enterprise Data
Within and Across Silos to
Provide Context for AI
2
Stores RAG Corpus and
Agentic Memory in a Unified
Platform
3
Enterprise Strength
Governance & Explainability
for trust, transparency and
compliance
4
45.
Powerful, but it
doesn’tsupport
relationships
And relationships
are crucial for
context
Data Platforms
Apps Agents Tools
Application Layer
Shopping Cart Fraud Catalog Sales
But what about my existing data platform?
We have learnedbuilding RAG apps that
you need a more sophisticated retrieval
system. It's not good enough to have
just vector search and some
embeddings.” Satya Nadella @
Microsoft BUILD 2025 keynote
“Models are just part of the equation. For
anyone building an agent you need to be
able to have truly great access to the real
time web as well as the entire enterprise
knowledge graph.
47
53
So what dopeople do?
Leading video game co.
● 150+ non-technical analysts need real-time access to
data using natural language
● No holistic view across silos
● Get answers to complex questions, e.g. “How do
competitor launches impact our sales?”
CHALLENGE
Reduction in analyst time spent on routine requests.
Time-to-insight vs. traditional analytics. Time for analysis
reduced from weeks to seconds
Since 2019
Infosys KnowledgeGraph
Journey with Neo4j
Learning
Recommendations
2020
2024 - now
IS Graph
hAIreNxt
2020 and early 2021
Talent/Hiring
Recommendations
Publish Content
Recommendations
2022
2022
Account Marketing
Recommendations
Skill and other
ontologies
2023 - 2024
19 Use cases 15 m Nodes 191 m Relationships
62.
Dependencies
Are you toodependent on specific individuals to
manage your code?
Do you lack clear visibility into application
dependencies, lineage, and code explainability?
Are your technical documents outdated?
Hidden cost & complexity of legacy systems
Why is this application down?
Who are the impacted users?
Who is the owner of this code / server / process / …
What does this piece of code do?
If I make this change, what else will get impacted?
How does this process work
63.
IS Graph
Digital Twinfor IT Systems
Centralized lineage solution built to know cross application
code, data, process, Infrastructure and human
dependencies – how are they interconnected, impact of one
to another & quick analysis
64.
Discovery & Parsing(Gen AI)
Legacy Landscape Code,
System data, Documents
IS Graph
Digital Twin for IT Systems
Automation of Information extraction, processing and
inference
Modeling & integration (Neo4j)
Network schema of Nodes & Edges
Inference & Action (Gen AI)
Agentic AI, RAG and Natural
Language Querying
Impact
Analysis
Use graph toget
impact application
and objects for any
SP, SSIS, Cube, K8
Service and many
more
Key Capabilities
Monitoring
& Alerts
Monitor the uptime
of all system and
infrastructure
components
GenAI
RCA
Automated error
identification and
analysis
Gen AI
Chatbot
Use Gen AI to
query about
domain, process
and system
implementation
Access
Validations
Monitor the uptime
of all system and
infrastructure
components
S/PII
Data Lineage,
archival and
GDPR
compliance
IS Graph
Digital Twin for IT Systems
Productivity & Efficiency
40%effort saving for
developers in impacted role
Code parsing & explainability –
quickly know the impact of change
in your code cross application,
understand your code
Inspirational
Infosys inhouse solution
with capability to visualize and
analyze the impact across the
organization using Neo4j
Targeted reach,
Quick Turn around
Helps to effectively collaborate
via identified impacted
application, SPOCs and not
spam each other.
What are we achieving?
69.
Key Takeaways
Power ofKnowledge Graph + Generative AI
Complexity is now navigable
Treat your entire IT environment as a single unified graph
Gen AI is your Data Translator
Gen AI efficiently parses and interprets unstructured data,
including code, configuration files, and system documents.
Neo4j Graph is the intelligent brain
Graph integrating those facts to form a digital twin, which can
answer multi hop complex questions
Gen AI links interdependencies in real time
Gen AI enables interacting with the Digital Twin using natural
language querying
70.
Sunil Thakur
AVP (AI& Data Infosys IT)
Infosys
Thank You
Sunil_Thakur@infosys.com
Radhika_Jampani@infosys.com
For developers, dataanalysts, and data scientists
Premium, trusted cloud-native graph intelligence platform
Cross cloud, easy to use, and enable AI accuracy
Provides foundational services
likememory to power all
AI platforms.
Agentic Brain
Graph Intelligence Platform
Browser (Query) Bloom (Explore) NeoDash(Dashboards) Data & Document Import GraphQL
Aura Agents
Build multi hop agents
in seconds.
Graph Engine
Graph
AI
AI
Powered
Graph
Tools
Database
& Graph
Algorithms
97.
Fully Managed
Seconds toSign Up
Minutes to Wow
Days to Value Integrated Ecosystem
Strategic Investments
Trusted Fundamentals Scalability with Enterprise Security, Governance, and Compliance
c
98.
Fully Managed
Seconds toSign Up
Minutes to Wow
Days to Value Integrated Ecosystem
Trusted Fundamentals Scalability with Enterprise Security, Governance, and Compliance
Strategic Investments
c
99.
Autonomous
Clustering
High availability withmulti-DB support.
Servers and databases are decoupled:
servers provide computation and storage
power for databases to use. Each
database relies on its own autonomous
cluster, organized in primaries and
secondaries.
Scalability, allocation / reallocation,
service elasticity, load balancing,
automatic routing are automatically
provided (or they can be finely controlled).
3 primary
3 primary +
2 secondary
Composite
Database
APP APP APP
Applications
Databases
Servers
CORE DATABASE ENHANCEMENTS
100.
Graph that fitson single
machine in a single clustered
environment replicated for
read scalability.
Replicated Graph Federated Graph
(Fabric)
C
Different graphs (supply chain
& parts graph) in an
organization being queried to
aggregate information.
Could be Replicated
or Sharded.
101.
INTRODUCING
➔ 100TB+ scalewith full ACID compliance
➔ One system for transactions and analytics
➔ Distributed by design, full graph integrity
➔ AI-ready -billions of vectors directly in the graph
102.
Create Large ScaleSharded Graphs
INFINITE SCALABILITY
C
Sharded Graph
(InfiniGraph)
Single Graph sharded across
many machines across
clustered environments.
Growing need to support
large graph sizes.
Graph that fits on single
machine in a single clustered
environment replicated for
read scalability.
Replicated Graph Federated Graph
(Fabric)
C
Different graphs (supply chain
& parts graph) in an organiz-
ation being queried to
aggregate information.
Could be Replicated
or Sharded.
103.
Large Graph
Support
● Highdata volumes-up to 100TB (and
potentially more) of graph data
● Fast data loading-initial bulk import and
staging/live incremental updates
● Semantic indexes-sharded full-text and
vector indexes are natively integrated
● ACID-fully transactional and ACID compliant
● Simplicity-Transparent to user, standard
Cypher
● Analytics-supports Neo4j tools (Query,
Explore, Graph Analytics)
● Transparent to all API calls
NEW CAPABILITIES
EAP Available
GA-Planned Q4 2025
Demo
</>
X
Streaming
Operational
Analytical
READS
Reporting
T
Autonomous Clustering
Property Shards
TXN logs
Graph Shard
101
01
101
01
101
01
101
01
101
01
WRITES
Bulk WRITES
Bulk WRITES
104.
Centralized Management
Monitor &manage all Neo4j databases across the
enterprise
Proactive Monitoring
Insights and health monitoring to optimize
performance and reliability
Identify security risks
Streamlined Operations
Seamless workload operations across databases
to reduce risk and downtime of your enterprise
data
Easily migrate self managed databases
to Aura with few clicks
Fleet
Management
HYBRID ADMIN EXPERIENCE
Aura (Unified Fleet Management)
Aura Self Managed
ENTERPRISE DESKTOP COMMUNITY
Now Available
105.
Block Format issuperior graph native
format to group graph data into blocks
that reduces amount of data read with
greater performance in
memory-constrained scenarios
Parallel Runtime speeds up analytical
queries up to 100x by concurrent
execution on all cores
CDC enables graph changes published as
events in real-time (full or diff mode)
Autonomous clustering with multi-db for
multi-tenant SaaS solutions
Performance &
Scalability
Block Format Parallel Runtime
Change Data Capture Autonomous Clustering (with Multi DB)
CORE DATABASE ENHANCEMENTS
Now Available
106.
GQL as ISOStandard for Graph Queries
Conditional Queries to provide more
flexibility and expressive power to handle
complex querying scenarios
Quantified graph patterns & Quantified
path patterns for simplified execution
Cypher version can be selected at DBMS,
database and single-query level: server
upgrades do not require query migration.
Query Language is decoupled from the
server releases
Language
Enhancements
MATCH (n:Person)
CALL (n) {
WHEN n.age > 60 THEN {
SET n.ageGroup = 'Veteran'
}
WHEN n.age >= 35 AND n.age <= 59 THEN {
SET n.ageGroup = 'Senior'
}
ELSE {
SET n.ageGroup = 'Junior'
}
}
RETURN n.name AS name, n.ageGroup
Conditional Queries Graph Pattern Matching
Quantified Path Patterns Cypher Versioning
CORE DATABASE ENHANCEMENTS
Now Available
107.
Security &
Operations
Graph SchemaProperty Based Access Control (PBAC)
CORE DATABASE ENHANCEMENTS
Offline Incremental Importer Differential Backup & Point in Time Recovery
Now Available
Schema: Unique relationship property,
relationship key, property data types
Property Based Access Control (PBAC)
for RBAC, data-driven rules to control
READ and TRAVERSE privileges on
nodes
Ultra-high speed incremental importer
addition to offline importer
Incremental backup and recovery
108.
● Replication ofdata from one
database instance to another.
● Replication across instances
running in any configuration
(across DCs, Clouds platform,
Self managed vs Aura).
● Neo4j to be Tier 1 platform in
enterprises with potential to
deliver RPO (0) /RTO (15min)
Cross-Cluster
Replication
CORE DATABASE Roadmap
Roadmap -2026
High Availability across DCs/Regions
Migrate Self Managed Databases to Cloud
109.
Strategic Investments
Fully Managed
GraphRAG
TrustedFundamentals Scalability with Enterprise Security, Governance, and Compliance
AI Accuracy
Ease of Use
5Seconds to Sign Up
Minutes to Wow
Days to Value Integrated Ecosystem
110.
Focus on YourApp,
Not Infrastructure!
Available on Google Cloud, AWS, and Azure
99.95% uptime SLA with self-healing
cluster architecture
Scale up for large memory-intensive graphs
Automated backups and restore
Automated upgrades, zero maintenance
CLOUD FIRST CAPABILITIES
More than
30k
Managed
Databases
Available on all major
cloud providers
111.
Aura Launches
2024/2025
Feature: CustomerManaged Keys
(AWS)
GA Date: 18 April
Feature: GDS Sessions (w/console
UX) EAP Date: 6 Jun
Feature: Customer Metrics
Integrations
GA Date: 8 June
Feature: Security Log Forwarding
GA Date: 2 July
Feature: User Management Pro PLG-
GA Date: 3 July
Feature: 512GB RAM (AWS)
GA Date: 8 July
Feature: Customer Managed Keys
(Azure)
GA Date: 12 July
Feature: Query Log Analyzer
EAP Date: 22 July
Feature: Customer Managed Keys
(GCP)
GA Date: 31 July
Feature: Business Critical Tier v1
Date: 1st August
Feature: 512GB RAM GCP
GA Date: 13th August
Feature: SSO Config (Admin UI)
GA Date: 20 August
Feature: Query Log Analyzer
Date: 27 August
Feature: Pro Trial
Date: 2 September
Feature: UPX-Preview
Date: 2 September
Feature: Change Data Capture
Date: 4 September
Feature: VDC Name Change
Date: 4 September
Feature: Query API
GA Date: 6 September
Feature: Migration
Readiness Reports
EAP Date: 6 September
Feature: Console Consumption Reports
GA Date: 16 September
Feature: Mark DB as Production
Date: 14 October
Feature: Secondaries
GA Date: 21 October
Feature: Migration Readiness Report
GA Date: 7 November
Feature: 512Gi GCP Business Critical
Date: 15 November
Feature: Business Critical All Aura Regions
Date: 19 November
Feature: UPX GA Self Serve
Date: 11 December
Feature: 512GB Azure BC & VDC
GA Date: 12 December
Feature: Security Log Analyzer
GA Date: 12 December
Feature: Adaptive Email MFA
GA Date: 15 December
Feature: AuraDB Vector Optimised
GA Date: 19 December
Feature: India Region Pro & BC ‘all
clouds’
Date: 7 Jan
Feature: AuraDB Pro <128GB
(pre-paid)
Date: 13 Jan
Feature: Aura CLI
Date: 14 Jan
Feature: GraphQL for AuraDB
(BETA) Date: 14 Jan
Feature: AuraDB Pro Trial 14 day
length + all CSP Regions
Date: 23 Jan
Feature: AuraDB Latest version
(CalVer)
Date: 29 Jan
Feature: AuraDB: Graph Analytics
(Professional)
Date: 13 Feb
Q2 ‘24 Q1 ‘25
Q3 ‘24 Q4 ‘24
112.
Comprehensive Cloud Offerings
forYour Workloads
Zonal (single AZ) with
functionality aimed at
smaller teams &
departmental solutions
Regional (Multi-AZ) with
enterprise-grade SLA &
functionality
Highest tier, regional
(Multi-AZ) with dedicated
account provisioned per
customer
Perpetually free
database for customers
to learn and experiment
with apps
Now Available
113.
3 paid SKUs:Fit your workloads across Aura
Professional, Business Critical, and Virtual
Dedicated Cloud
Free Trial: Try Aura Professional before you buy
Scale Out: Secondaries provide ability to scale
out for read heavy workloads
Security: SSO using IDPs such as AAD and Okta,
encryption in-transit and at-rest; CMEK, private
VPC and private links, standard industry
compliance
New
Capabilities
Aura Pro (Free Trials)
Secondaries For Scale Out
AURA ENHANCEMENTS
Now available
114.
Security &
Compliance
Trust Center
SSOusing IDPs such as AAD and Okta
Fine-grained access control
Encryption in-transit and at-rest;
Customer Managed Keys (AWS)
Private VPC and Private Links
Standard Industry Compliance
AURADB NEW CAPABILITIES
Now available
114
115.
IP Filtering
Control networkaccess with IP allow-lists
on VDC and BC tiers
Works with public, private, or hybrid
network setups
No endpoints or DNS required, simple UI
or API setup
Enforce consistent network access rules
across instances and projects
AURADB NEW CAPABILITIES
Now available
115
116.
Pay-as-you-go, Serverless offeringproviding
65+ built-in graph algorithms for use with any enterprise
data on any cloud platform
New
Graph Analytics
Use Graph Analytics in any data in any system without
full replication.
Deliver most advanced graph algorithms in industry across
CPU & GPU
Deliver serverless experience so customers only pay
for what they use
Enable real-time execution with high throughput scenarios
Enable interactive experiences with multiple analysts and
data scientists running parallel algorithms
GRAPH ANALYTICS AS KEY DIFFERENTIATOR
Serverless
Analytics
Higher Scalability & Concurrency
All Databases
Projection
Write Back
Now available
117.
Fully Managed
GraphRAG
Trusted FundamentalsScalability with Enterprise Security, Governance, and Compliance
Cloud First AI Accuracy
Seconds to Sign up
Minutes to Wow
Days to Value
Zero Ops
Integrated Ecosystem
Strategic Investments
Improved workflows witha single hub for
all data management tasks
Consistent user experience through a
single unified console across Neo4j tools
Easier collaboration as teams can share
resources and collaborate on projects
Improved productivity with GenAI copilot
by helping developers write and improve
Cypher queries
Secure data access with expanded roles
and new access controls
Unified
Experience
Data Import (growing sources) One Click Graph Data Modeling
AURA ENHANCEMENTS
Co-pilot for Cypher Adoption AI Powered Dashboards
Now available
120.
VS Code enablessyntax highlighting, auto
completions, connection mgmt, and more
JDBC Driver enables tool integrations,
supports SQL translation, and schema
mapping
Neo4j GraphQL library and service to
deploy low code API with GraphQL
Query API (Cypher over HTTPS) allows for
single Cypher requests with the response
returned as JSON
Model Context Protocol (MCP) Server
Developer
Surfaces
VS Code Extension Drivers & Connectors
DEVELOPER EXPERIENCE
GraphQL Support Query API
Now available
121.
Unified local consolewith Neo4j
Enterprise Edition installation
Convenience of offline working
Enable remote connections, including
to Aura Databases
Unified login with Aura
Migrate local databases to Aura
Desktop V2
HYBRID DEVELOPER EXPERIENCE
Coming Soon
Coming Soon
Now available
122.
Strategic Investments
Fully Managed
TrustedFundamentals Scalability with Enterprise Security, Governance, and Compliance
Cloud First Ease of Use
5Seconds to Sign Up
Minutes to Wow
Days to Value
Zero Ops
Integrated Ecosystem
Vector
Support
RELEASED CAPABILITIES
Vector Indexbuilt into the database
Store any property, node, and relationship
as vector in the database
Ability to create embeddings by directly calling
various embedding services like OpenAI, Azure
OpenAI, VertexAI, and Bedrock
Vector Type, Distance Function, Pre-Filtering,
Scaling, external vector stores
Coming Soon
131.
Construct knowledge graphsfrom unstructured
data/documents using schema
Implement different GraphRAG retrievers
Build GenAI RAG pipelines with vector and hybrid
search and GraphRAG retrieval
External vector search integration
GraphRAG
Python Package
RELEASED CAPABILITIES
132.
Integrated with GenAIecosystem
Orchestration & Agent Libraries
Support for major frameworks like
Langchain, LlamaIndex, Spring AI,
Langchain4j, Haystack, Semantic Kernel,
etc.
Integrated with all LLM platforms like AWS,
GCP, Azure, and OpenAI
Model Context Protocol (MCP), CrewAI,
Pydantic.AI, other Agent SDKs
GenAI
Ecosystem
RELEASED CAPABILITIES
● Graph Connector
● CypherQAChain
● KG Construction
● Vector Index
Integration
● Multiple LangChain
Templates
● LangChain.js
● LangChain4j
● Cypher Data
Loader
● Vector Search
Integration
● KG Construction
● Create Vector
Index
● KG Construction
● Query Vector
Index
● Embedding
Retriever
● Dynamic
Document
Retrieve (Cypher)
Coming Soon
133.
MCP is theAI native tool integration
protocol for agents.
Expose Neo4j data to any agentic AI
system, enabling intelligent reasoning
that can break down tasks for
explainable, multi-hop retrieval on
knowledge graphs with an
officially-supported MCP server
Announcing official MCP Server in Beta;
supports self managed and Aura Data
MCP Roadmap
● Neo4j Database & GDS (GA-Q4)
● MCP for Aura Agents (GA-Q4)
● Aura hosted MCP Server (2026)
● MCP for Aura Management (2026)
MCP Servers
133
Beta-Available Now
NEW CAPABILITIES
github.com/neo4j/mcp
134.
An agentic, API-drivenservice enabling
developers to build GenAI applications
in minutes
● Developer-Centric Agent API
provisioned at Database Level
● Low code Agent and Tool creation
with Cypher
● Simple UI to test chat experience
and potentially embed in apps
● Seamlessly integrate explainable,
multi-hop retrieval & reasoning into
your AI workflows
Aura Agent
Beta-Available Now
NEW CAPABILITIES