What can Druid MCP Server do?

druid cluster introspection and metadata discovery, sql query execution against druid datasources, datasource ingestion and data loading orchestration, segment lifecycle management and retention policies, cluster health monitoring and diagnostic reporting, dynamic configuration and runtime parameter management, query performance analysis and optimization recommendations, multi-datasource schema discovery and data lineage tracking, contextual prompt templates for druid operations

Druid MCP Server

MCP ServerFree

** - STDIO/SEE MCP Server for Apache Druid by [iunera](https://www.iunera.com) that provides extensive tools, resources, and prompts for managing and analyzing Druid clusters.

Open Source

/ 100

9 capabilities

Capabilities9 decomposed

druid cluster introspection and metadata discovery

Medium confidence

Exposes Druid cluster metadata through MCP resources and tools, enabling programmatic discovery of datasources, segments, tasks, and cluster topology. Implements resource-based access patterns that map Druid's REST API endpoints to queryable MCP resources, allowing clients to inspect cluster state without direct API knowledge.

Solves for

Understand what datasources and segments exist in my Druid clusterDiscover cluster topology, broker/coordinator/historical nodes, and their statusRetrieve task execution history and current task queue stateInspect segment metadata, replication factors, and data distribution

Best for

Data engineers managing Druid infrastructure

Analytics teams needing cluster visibility within LLM-powered tools

DevOps teams automating Druid cluster monitoring

Requires

Apache Druid 0.20.0 or later

Network connectivity to Druid coordinator and broker endpoints

MCP client supporting resource discovery protocol

Limitations

Read-only introspection — does not modify cluster state directly

Metadata freshness depends on Druid's internal state update frequency

Large clusters with thousands of segments may experience latency in resource enumeration

What makes it unique

Bridges Druid's native REST API into MCP resource abstraction, allowing LLM agents to discover and reason about cluster state through standard MCP resource patterns rather than requiring direct HTTP client implementation

vs alternatives

Provides native MCP integration for Druid visibility without requiring separate API client libraries or custom HTTP orchestration in agent code

sql query execution against druid datasources

Medium confidence

Executes Druid SQL queries through MCP tools, translating user intent into Druid SQL syntax and returning structured result sets. Implements query validation, result streaming, and error handling that maps Druid's native SQL API responses back to the MCP client with proper type coercion and pagination support.

Solves for

Run analytical queries against Druid datasources from within an LLM agentFetch time-series data for specific metrics and dimensionsPerform aggregations and grouping operations on large datasetsValidate data quality by querying sample rows and computing statistics

Best for

Data analysts using LLM agents for exploratory analysis

Automated reporting systems querying Druid for metric computation

Debugging workflows that need to inspect raw data in Druid

Requires

Apache Druid 0.20.0+ with SQL API enabled

Druid broker endpoint accessible from MCP server

Appropriate database permissions for query execution

Limitations

Query timeout depends on Druid broker configuration — long-running queries may fail

Result set size is bounded by available memory in the MCP server process

No built-in query optimization or cost estimation before execution

What makes it unique

Wraps Druid's native SQL API within MCP tool abstraction, enabling LLM agents to compose and execute queries without managing HTTP clients or parsing raw JSON responses directly

vs alternatives

Tighter integration with Druid's SQL dialect than generic database connectors, with Druid-specific optimizations like native support for time-series aggregations and segment pruning

datasource ingestion and data loading orchestration

Medium confidence

Provides MCP tools for submitting ingestion tasks to Druid, managing ingestion specs, and monitoring task execution. Implements task submission via Druid's indexing service API, with support for batch and streaming ingestion configurations, allowing agents to programmatically load data into Druid clusters.

Solves for

Submit batch ingestion tasks to load data from S3, HDFS, or local filesConfigure and deploy streaming ingestion from Kafka or other message brokersMonitor ingestion task progress and handle failuresManage ingestion specs and reuse configurations across multiple runs

Best for

Data pipeline orchestrators automating Druid data loading

DevOps teams managing ETL workflows with LLM-driven automation

Data engineers prototyping ingestion configurations

Requires

Apache Druid 0.20.0+ with indexing service enabled

Druid overlord endpoint accessible from MCP server

Data source (S3, HDFS, Kafka, etc.) configured and accessible to Druid

Limitations

Ingestion spec validation is minimal — invalid specs fail at task execution time

No built-in retry logic or failure recovery — requires external orchestration

Large ingestion tasks may exceed coordinator memory limits

What makes it unique

Abstracts Druid's task submission API into MCP tools, enabling LLM agents to compose ingestion specs and monitor task execution without managing Druid's indexing service API directly

vs alternatives

Provides Druid-native ingestion orchestration within LLM agent workflows, avoiding the need for separate ETL tools or custom Python/Java clients

segment lifecycle management and retention policies

Medium confidence

Exposes Druid segment management operations through MCP tools, including segment dropping, retention rule configuration, and compaction scheduling. Implements coordination with Druid's coordinator service to apply retention policies, drop segments, and trigger compaction tasks, enabling automated data lifecycle management.

Solves for

Drop old segments to manage storage costsConfigure retention rules based on time or size thresholdsTrigger segment compaction to optimize query performanceMonitor segment replication and balance across historicals

Best for

Data platform teams automating storage optimization

Cost-conscious organizations managing Druid cluster expenses

DevOps engineers implementing data retention compliance policies

Requires

Apache Druid 0.20.0+ with coordinator service

Coordinator endpoint accessible from MCP server

Appropriate permissions to modify retention rules and drop segments

Limitations

Segment dropping is irreversible — no built-in recovery mechanism

Retention rule changes apply asynchronously — may take minutes to take effect

Compaction scheduling depends on available cluster resources

What makes it unique

Provides MCP-based lifecycle management for Druid segments, allowing agents to automate retention and compaction without direct coordinator API calls or manual intervention

vs alternatives

Integrates segment management into LLM-driven workflows, enabling data retention policies to be expressed and enforced programmatically through agent logic

cluster health monitoring and diagnostic reporting

Medium confidence

Aggregates Druid cluster health metrics and diagnostic information through MCP resources and tools, including node status, query performance, ingestion lag, and system resource utilization. Implements health check logic that queries multiple Druid endpoints and synthesizes results into actionable diagnostic reports for LLM analysis.

Solves for

Get real-time cluster health status and identify unhealthy nodesDiagnose query performance issues and slow query detectionMonitor ingestion lag and identify data freshness problemsRetrieve system metrics (CPU, memory, disk) for capacity planning

Best for

SRE teams monitoring Druid cluster health

Automated alerting systems powered by LLM analysis

Troubleshooting workflows for cluster issues

Requires

Apache Druid 0.20.0+ with metrics exposure enabled

Druid broker, coordinator, and historical endpoints accessible

Prometheus or similar metrics backend (optional, for enhanced diagnostics)

Limitations

Health metrics are point-in-time snapshots — no historical trending

Diagnostic reports depend on Druid's internal metrics exposure

No built-in alerting — requires external notification system

What makes it unique

Synthesizes multi-endpoint Druid health data into structured diagnostic reports optimized for LLM reasoning, rather than exposing raw metrics that require manual interpretation

vs alternatives

Provides Druid-specific health diagnostics within agent workflows, enabling automated troubleshooting without requiring separate monitoring infrastructure or manual metric interpretation

dynamic configuration and runtime parameter management

Medium confidence

Exposes Druid runtime configuration through MCP tools, enabling agents to query and modify dynamic configuration properties like query timeouts, segment cache sizes, and ingestion concurrency limits. Implements configuration validation and change propagation to affected Druid services without requiring cluster restart.

Solves for

Adjust query timeout settings to handle long-running queriesModify ingestion concurrency to optimize data loading performanceConfigure segment cache sizes based on available memoryEnable/disable features or experimental query optimizations

Best for

Performance tuning workflows for Druid clusters

Automated capacity management systems

Experimentation platforms testing configuration changes

Requires

Apache Druid 0.20.0+ with dynamic configuration support

Coordinator endpoint for configuration management

Appropriate permissions to modify cluster configuration

Limitations

Some configuration changes require service restart — not all are dynamic

Configuration changes apply immediately without rollback capability

No built-in validation of configuration value ranges

What makes it unique

Abstracts Druid's dynamic configuration API into MCP tools, allowing agents to adjust cluster behavior at runtime without requiring direct coordinator API calls or service restarts

vs alternatives

Enables runtime configuration management within LLM agent workflows, supporting dynamic tuning without manual intervention or external configuration management tools

query performance analysis and optimization recommendations

Medium confidence

Analyzes executed queries through MCP tools to extract performance metrics, identify bottlenecks, and generate optimization recommendations. Implements query plan parsing and cost analysis that examines segment pruning, filter pushdown, and aggregation strategies to suggest schema or query rewrites.

Solves for

Understand why a query is slow and what's causing the bottleneckGet recommendations for query rewrites or schema changesIdentify missing indexes or segment optimizationsCompare query performance across different execution strategies

Best for

Data analysts optimizing analytical queries

Database administrators tuning Druid schemas

Performance engineering teams analyzing query workloads

Requires

Apache Druid 0.20.0+ with query logging enabled

Query execution history available in Druid

Access to query plans and execution metrics

Limitations

Recommendations are heuristic-based — not guaranteed to improve performance

Analysis requires query execution — cannot predict performance without running

Complex queries with many joins may be difficult to analyze

What makes it unique

Provides Druid-specific query analysis within MCP, enabling LLM agents to reason about query performance and generate optimization suggestions without requiring external query profiling tools

vs alternatives

Integrates query optimization analysis into agent workflows, enabling automated performance tuning recommendations based on Druid's native execution metrics

multi-datasource schema discovery and data lineage tracking

Medium confidence

Discovers and maps schemas across multiple Druid datasources through MCP resources, including column definitions, data types, and relationships. Implements data lineage tracking that correlates ingestion sources with datasources and enables agents to understand data flow and dependencies across the cluster.

Solves for

Understand the schema and available columns in a datasourceDiscover relationships and dependencies between datasourcesTrack data lineage from source systems through ingestion to DruidIdentify data quality issues by comparing schemas across related datasources

Best for

Data governance teams managing Druid metadata

Analytics engineers building data models

Data quality monitoring systems

Requires

Apache Druid 0.20.0+ with metadata API

Optional external metadata store for lineage information

Access to ingestion specs and source system configurations

Limitations

Lineage tracking requires manual configuration or external metadata store

Schema changes are not automatically detected — requires periodic refresh

No built-in data quality metrics or validation rules

What makes it unique

Provides MCP-based schema discovery and lineage tracking for Druid, enabling agents to understand data relationships without requiring separate data catalog or metadata management tools

vs alternatives

Integrates schema and lineage information into LLM agent context, enabling data-aware reasoning about datasource relationships and dependencies

contextual prompt templates for druid operations

Medium confidence

Provides pre-built MCP prompts that guide LLM agents through common Druid operations like cluster diagnostics, query optimization, and ingestion troubleshooting. Implements prompt templates that inject cluster context, available tools, and operational best practices to improve agent decision-making and reduce hallucination.

Solves for

Get step-by-step guidance for diagnosing cluster issuesFollow best practices when configuring ingestion tasksUnderstand how to optimize queries for specific use casesLearn Druid-specific operational patterns and anti-patterns

Best for

LLM agents performing Druid operations

Teams new to Druid learning operational best practices

Automated systems requiring consistent operational procedures

Requires

MCP client supporting prompt discovery

LLM capable of following multi-step instructions

Limitations

Prompts are static — do not adapt to specific cluster configurations

Best practices may not apply to all use cases or cluster sizes

Prompts require LLM to follow instructions — not guaranteed

What makes it unique

Provides Druid-specific prompt templates within MCP that guide agent behavior through operational workflows, reducing hallucination and improving decision quality

vs alternatives

Embeds Druid operational knowledge directly in prompts, enabling agents to follow best practices without requiring external documentation or manual instruction

Capabilities are decomposed by AI analysis. Each maps to specific user intents and improves with match feedback.

Related Artifactssharing capabilities

Artifacts that share capabilities with Druid MCP Server, ranked by overlap. Discovered automatically through the match graph.

MCP Server44

OpenMetadata

OpenMetadata is a unified metadata platform for data discovery, data observability, and data governance powered by a central metadata repository, in-depth column level lineage, and seamless team collaboration.

multi-source metadata ingestion with connector framework

1 shared capability

MCP Server44

OpenMetadata

multi-source metadata ingestion with 100+ connector framework

1 shared capability

Repository23

WhoDB

SQL/NoSQL/Graph/Cache/Object data explorer with AI-powered chat + other useful features

schema visualization and metadata introspection

1 shared capability

Product29

Latentspace

Intelligent data analyst, offering a user-friendly interface to connect your analytics with AI...

data exploration and schema browsing

1 shared capability

MCP Server46

Grafana MCP Server

Query Grafana dashboards, datasources, and alerts via MCP.

datasource discovery and metadata introspection

1 shared capability

MCP Server22

MotherDuck

** - Query and analyze data with MotherDuck and local DuckDB

database schema introspection and discovery

1 shared capability

Best For

✓Data engineers managing Druid infrastructure
✓Analytics teams needing cluster visibility within LLM-powered tools
✓DevOps teams automating Druid cluster monitoring
✓Data analysts using LLM agents for exploratory analysis
✓Automated reporting systems querying Druid for metric computation
✓Debugging workflows that need to inspect raw data in Druid
✓Data pipeline orchestrators automating Druid data loading
✓DevOps teams managing ETL workflows with LLM-driven automation

Known Limitations

⚠Read-only introspection — does not modify cluster state directly
⚠Metadata freshness depends on Druid's internal state update frequency
⚠Large clusters with thousands of segments may experience latency in resource enumeration
⚠Query timeout depends on Druid broker configuration — long-running queries may fail
⚠Result set size is bounded by available memory in the MCP server process
⚠No built-in query optimization or cost estimation before execution

Requirements

Apache Druid 0.20.0 or laterNetwork connectivity to Druid coordinator and broker endpointsMCP client supporting resource discovery protocolApache Druid 0.20.0+ with SQL API enabledDruid broker endpoint accessible from MCP serverAppropriate database permissions for query executionApache Druid 0.20.0+ with indexing service enabledDruid overlord endpoint accessible from MCP server

Input / Output

Accepts: cluster endpoint URL, optional query filters (datasource name, segment ID), Druid SQL query string, optional query parameters (timeout, max rows), ingestion spec (JSON), datasource name, data source configuration, segment ID or time range, retention rule specification (JSON), optional filter criteria (node type, datasource), configuration property name, new property value, optional scope (global, datasource-specific), query string or query ID, optional performance baseline for comparison, optional filter criteria (column name, data type), operation type (diagnostics, optimization, ingestion), optional context (cluster size, workload type)

Produces: JSON metadata objects, structured cluster topology, segment inventory with replication info, JSON array of result rows, column metadata with types, query execution statistics, task ID, task status, ingestion metrics (rows loaded, errors), operation status, affected segment count, estimated storage savings, cluster health status (JSON), node status list, performance metrics, diagnostic recommendations, configuration change status, affected services, previous value, performance metrics (latency, rows scanned), query plan analysis, optimization recommendations, estimated improvement potential, schema definition (columns, types), lineage information, datasource relationships, ingestion source details, structured prompt template, step-by-step instructions, relevant tools and resources

UnfragileRank

Adoption15%(30% weight)

Quality27%(25% weight)

Ecosystem30%(25% weight)

Match Graph10%(15% weight)

Freshness75%(5% weight)

UnfragileRank is computed from adoption signals, documentation quality, ecosystem connectivity, match graph feedback, and freshness. No artifact can pay for a higher rank.

Type: MCP Server

9 capabilities

Visit Druid MCP Server→

About

** - STDIO/SEE MCP Server for Apache Druid by [iunera](https://www.iunera.com) that provides extensive tools, resources, and prompts for managing and analyzing Druid clusters.

Alternatives to Druid MCP Server

IntelliCode50Extension

AI-assisted development

Compare →

GitHub Copilot Chat53Extension

AI chat features powered by Copilot

Compare →

GitHub Copilot52Extension

Your AI pair programmer

Compare →

Claude Code for VS Code52Extension

Claude Code for VS Code: Harness the power of Claude Code without leaving your IDE

Compare →

Are you the builder of Druid MCP Server?

Claim this artifact to get a verified badge, access match analytics, see which intents users search for, and manage your listing.

Claim this artifact →Verification via email

Get the weekly brief

New tools, rising stars, and what's actually worth your time. No spam.

Data Sources

github awesome

Looking for something else?

Search →

Capabilities9 decomposed

druid cluster introspection and metadata discovery

Medium confidence

Solves for

Best for

Data engineers managing Druid infrastructure

Analytics teams needing cluster visibility within LLM-powered tools

DevOps teams automating Druid cluster monitoring

Requires

Apache Druid 0.20.0 or later

Network connectivity to Druid coordinator and broker endpoints

MCP client supporting resource discovery protocol

Limitations

Read-only introspection — does not modify cluster state directly

Metadata freshness depends on Druid's internal state update frequency

Large clusters with thousands of segments may experience latency in resource enumeration

What makes it unique

vs alternatives

Provides native MCP integration for Druid visibility without requiring separate API client libraries or custom HTTP orchestration in agent code

sql query execution against druid datasources

Medium confidence

Solves for

Best for

Data analysts using LLM agents for exploratory analysis

Automated reporting systems querying Druid for metric computation

Debugging workflows that need to inspect raw data in Druid

Requires

Apache Druid 0.20.0+ with SQL API enabled

Druid broker endpoint accessible from MCP server

Appropriate database permissions for query execution

Limitations

Query timeout depends on Druid broker configuration — long-running queries may fail

Result set size is bounded by available memory in the MCP server process

No built-in query optimization or cost estimation before execution

What makes it unique

Wraps Druid's native SQL API within MCP tool abstraction, enabling LLM agents to compose and execute queries without managing HTTP clients or parsing raw JSON responses directly

vs alternatives

Tighter integration with Druid's SQL dialect than generic database connectors, with Druid-specific optimizations like native support for time-series aggregations and segment pruning

datasource ingestion and data loading orchestration

Medium confidence

Solves for

Best for

Data pipeline orchestrators automating Druid data loading

DevOps teams managing ETL workflows with LLM-driven automation

Data engineers prototyping ingestion configurations

Requires

Apache Druid 0.20.0+ with indexing service enabled

Druid overlord endpoint accessible from MCP server

Data source (S3, HDFS, Kafka, etc.) configured and accessible to Druid

Limitations

Ingestion spec validation is minimal — invalid specs fail at task execution time

No built-in retry logic or failure recovery — requires external orchestration

Large ingestion tasks may exceed coordinator memory limits

What makes it unique

Abstracts Druid's task submission API into MCP tools, enabling LLM agents to compose ingestion specs and monitor task execution without managing Druid's indexing service API directly

vs alternatives

Provides Druid-native ingestion orchestration within LLM agent workflows, avoiding the need for separate ETL tools or custom Python/Java clients

segment lifecycle management and retention policies

Medium confidence

Solves for

Best for

Data platform teams automating storage optimization

Cost-conscious organizations managing Druid cluster expenses

DevOps engineers implementing data retention compliance policies

Requires

Apache Druid 0.20.0+ with coordinator service

Coordinator endpoint accessible from MCP server

Appropriate permissions to modify retention rules and drop segments

Limitations

Segment dropping is irreversible — no built-in recovery mechanism

Retention rule changes apply asynchronously — may take minutes to take effect

Compaction scheduling depends on available cluster resources

What makes it unique

Provides MCP-based lifecycle management for Druid segments, allowing agents to automate retention and compaction without direct coordinator API calls or manual intervention

vs alternatives

Integrates segment management into LLM-driven workflows, enabling data retention policies to be expressed and enforced programmatically through agent logic

cluster health monitoring and diagnostic reporting

Medium confidence

Solves for

Best for

SRE teams monitoring Druid cluster health

Automated alerting systems powered by LLM analysis

Troubleshooting workflows for cluster issues

Requires

Apache Druid 0.20.0+ with metrics exposure enabled

Druid broker, coordinator, and historical endpoints accessible

Prometheus or similar metrics backend (optional, for enhanced diagnostics)

Limitations

Health metrics are point-in-time snapshots — no historical trending

Diagnostic reports depend on Druid's internal metrics exposure

No built-in alerting — requires external notification system

What makes it unique

Synthesizes multi-endpoint Druid health data into structured diagnostic reports optimized for LLM reasoning, rather than exposing raw metrics that require manual interpretation

vs alternatives

Provides Druid-specific health diagnostics within agent workflows, enabling automated troubleshooting without requiring separate monitoring infrastructure or manual metric interpretation

dynamic configuration and runtime parameter management

Medium confidence

Solves for

Best for

Performance tuning workflows for Druid clusters

Automated capacity management systems

Experimentation platforms testing configuration changes

Requires

Apache Druid 0.20.0+ with dynamic configuration support

Coordinator endpoint for configuration management

Appropriate permissions to modify cluster configuration

Limitations

Some configuration changes require service restart — not all are dynamic

Configuration changes apply immediately without rollback capability

No built-in validation of configuration value ranges

What makes it unique

Abstracts Druid's dynamic configuration API into MCP tools, allowing agents to adjust cluster behavior at runtime without requiring direct coordinator API calls or service restarts

vs alternatives

Enables runtime configuration management within LLM agent workflows, supporting dynamic tuning without manual intervention or external configuration management tools

query performance analysis and optimization recommendations

Medium confidence

Solves for

Best for

Data analysts optimizing analytical queries

Database administrators tuning Druid schemas

Performance engineering teams analyzing query workloads

Requires

Apache Druid 0.20.0+ with query logging enabled

Query execution history available in Druid

Access to query plans and execution metrics

Limitations

Recommendations are heuristic-based — not guaranteed to improve performance

Analysis requires query execution — cannot predict performance without running

Complex queries with many joins may be difficult to analyze

What makes it unique

Provides Druid-specific query analysis within MCP, enabling LLM agents to reason about query performance and generate optimization suggestions without requiring external query profiling tools

vs alternatives

Integrates query optimization analysis into agent workflows, enabling automated performance tuning recommendations based on Druid's native execution metrics

multi-datasource schema discovery and data lineage tracking

Medium confidence

Solves for

Best for

Data governance teams managing Druid metadata

Analytics engineers building data models

Data quality monitoring systems

Requires

Apache Druid 0.20.0+ with metadata API

Optional external metadata store for lineage information

Access to ingestion specs and source system configurations

Limitations

Lineage tracking requires manual configuration or external metadata store

Schema changes are not automatically detected — requires periodic refresh

No built-in data quality metrics or validation rules

What makes it unique

Provides MCP-based schema discovery and lineage tracking for Druid, enabling agents to understand data relationships without requiring separate data catalog or metadata management tools

vs alternatives

Integrates schema and lineage information into LLM agent context, enabling data-aware reasoning about datasource relationships and dependencies

contextual prompt templates for druid operations

Medium confidence

Solves for

Best for

LLM agents performing Druid operations

Teams new to Druid learning operational best practices

Automated systems requiring consistent operational procedures

Requires

MCP client supporting prompt discovery

LLM capable of following multi-step instructions

Limitations

Prompts are static — do not adapt to specific cluster configurations

Best practices may not apply to all use cases or cluster sizes

Prompts require LLM to follow instructions — not guaranteed

What makes it unique

Provides Druid-specific prompt templates within MCP that guide agent behavior through operational workflows, reducing hallucination and improving decision quality

vs alternatives

Embeds Druid operational knowledge directly in prompts, enabling agents to follow best practices without requiring external documentation or manual instruction

Capabilities are decomposed by AI analysis. Each maps to specific user intents and improves with match feedback.

Alternatives to Druid MCP Server

IntelliCode50Extension

AI-assisted development

Compare →

GitHub Copilot Chat53Extension

AI chat features powered by Copilot

Compare →

GitHub Copilot52Extension

Your AI pair programmer

Compare →

Claude Code for VS Code52Extension

Claude Code for VS Code: Harness the power of Claude Code without leaving your IDE

Compare →

Druid MCP Server

Capabilities9 decomposed

druid cluster introspection and metadata discovery

sql query execution against druid datasources

datasource ingestion and data loading orchestration

segment lifecycle management and retention policies

cluster health monitoring and diagnostic reporting

dynamic configuration and runtime parameter management

query performance analysis and optimization recommendations

multi-datasource schema discovery and data lineage tracking

contextual prompt templates for druid operations

Related Artifactssharing capabilities

OpenMetadata

OpenMetadata

WhoDB

Latentspace

Grafana MCP Server

MotherDuck

Best For

Known Limitations

Requirements

Input / Output

UnfragileRank

About

Categories

Alternatives to Druid MCP Server

Are you the builder of Druid MCP Server?

Get the weekly brief

Data Sources

Druid MCP Server

Capabilities9 decomposed

druid cluster introspection and metadata discovery

sql query execution against druid datasources

datasource ingestion and data loading orchestration

segment lifecycle management and retention policies

cluster health monitoring and diagnostic reporting

dynamic configuration and runtime parameter management

query performance analysis and optimization recommendations

multi-datasource schema discovery and data lineage tracking

contextual prompt templates for druid operations

Related Artifactssharing capabilities

OpenMetadata

OpenMetadata

WhoDB

Latentspace

Grafana MCP Server

MotherDuck

Best For

Known Limitations

Requirements

Input / Output

UnfragileRank

About

Categories

Alternatives to Druid MCP Server

Are you the builder of Druid MCP Server?

Get the weekly brief

Data Sources