Skip to main content
Glama
openmetadata-mcp-server

openmetadata-mcp-server

by us-all

OpenMetadata MCP Server

The OpenMetadata MCP that ships full CRUD across every entity type — including OM 1.12+ Data Contracts, Metrics, Search Index, API Collections, and API Endpoints that the embedded MCP doesn't cover yet.

172 tools, 4 workflow Prompts (lineage impact / DQ investigation / glossary bootstrap / owner reassign), 7 MCP Resources, and aggregations like lineage-impact (downstream blast-radius w/ owner notification list), quality-rollup (DQ status across a scope), and official Data Contract validation.

npm downloads tools @us-all standard Glama MCP server

What it does that others don't

  • OM 1.12+ entity coverage — Data Contracts, Metrics, Search Index, API Collections, API Endpoints, plus native contract validation/result retrieval. Not in the embedded MCP yet.

  • Aggregation tools — lineage-impact answers "what breaks if I change/drop X?" by walking lineage + counting consumers + breaking down by entity type + resolving the owner union for change-mgmt notifications, in one call. get-domain-summary returns domain + 6 child entity types via /search/query with track_total_hits in one call instead of 7 sequential. get-table-summary folds table + lineage + sample-data + DQ similarly.

  • Semantic search — semantic-search over OM 1.12+ vector index (POST /search/vector/query). Useful when keyword search misses synonyms.

  • MCP Prompts (4) — lineage-impact-analysis, data-quality-investigation, glossary-term-bootstrap, owner-change-propagation. Workflow templates the model invokes directly.

  • MCP Resources (7) — om://table/{fqn}, om://glossary-term/{fqn}, om://lineage/{type}/{fqn}, om://search/{query}, om://dashboard/{fqn}, om://pipeline/{fqn}, om://schema/{fqn}.

  • Token-efficient by design — extractFields projection on 28 read tools (drops changeDescription/version/updatedBy/href noise — ~80% size reduction), OM_TOOLS/OM_DISABLE category toggles, search-tools meta-tool.

  • Apps SDK card — lineage-impact renders as a blast-radius card on ChatGPT clients (downstream/upstream counts + type breakdown + top consumers + owners-to-notify) via _meta["openai/outputTemplate"]. Claude clients receive the same JSON content.

  • stdio + Streamable HTTP — defaults to stdio. Set MCP_TRANSPORT=http for ChatGPT Apps SDK or remote clients (Bearer auth via MCP_HTTP_TOKEN).

Related MCP server: Datris MCP Server

Try this — 5 prompts

Connect the server to Claude Desktop or Claude Code, then paste any of these:

  1. Lineage impact — "The payments.transactions table is being deprecated. List every dashboard, pipeline, and ML model that depends on it (upstream + downstream, depth 3)."

  2. Data quality investigation — "Show all failing test cases from the last 7 days. Group by table, then by test type, with pass/fail counts."

  3. Glossary bootstrap — "Create a payments glossary with these 8 terms: chargeback, refund, settlement, KYC, AML, transaction, customer-id, payment-method. Link related terms."

  4. Owner reassign — "User taehee is leaving. List every entity (table/dashboard/pipeline/ML model) where they are owner. Then reassign all of them to team data-platform."

  5. Domain summary — "Summarize the analytics domain: total tables/dashboards/pipelines/ML models, top 5 by recent updates, and the data products it owns."

When to use this vs OpenMetadata's embedded MCP

OpenMetadata 1.12+ ships an embedded MCP. They are complementary:

OM 1.12 embedded MCP

@us-all/openmetadata-mcp (this)

Tool count

~10 (search, glossary basics, lineage, DQ, RCA, semantic search)

172 (full CRUD across all entity types)

OM 1.12+ entity types (Data Contracts/Metrics/Search Index/API)

partial

✅ 12 tools

Aggregation tools

❌

✅ lineage-impact, get-domain-summary, get-table-summary

MCP Prompts

❌

✅ 4

MCP Resources

❌

✅ 7

Auth

OAuth2 / PAT, OM Authorization Engine (RBAC)

JWT bot token + write gate

Deployment

Embedded in OM server (marketplace install)

Standalone npm / Docker / npx

OM version

1.12+ only

1.x compatible

Best for

RBAC-aware AI agents, SSO orgs

Bulk CRUD, automation, sample-data, older OM clusters

Use the embedded MCP for RBAC-aware governance with SSO. Use this server for bulk metadata operations, full entity CRUD parity, automation, and OM clusters older than 1.12.

Install

Claude Desktop

{
  "mcpServers": {
    "openmetadata": {
      "command": "npx",
      "args": ["-y", "@us-all/openmetadata-mcp"],
      "env": {
        "OPENMETADATA_HOST": "http://your-host:8585",
        "OPENMETADATA_TOKEN": "<jwt-bot-token>"
      }
    }
  }
}

Claude Code

claude mcp add openmetadata -s user \
  -e OPENMETADATA_HOST=http://your-host:8585 \
  -e OPENMETADATA_TOKEN=<jwt-bot-token> \
  -- npx -y @us-all/openmetadata-mcp

Docker

docker run --rm -i \
  -e OPENMETADATA_HOST=http://your-host:8585 \
  -e OPENMETADATA_TOKEN=<jwt-bot-token> \
  ghcr.io/us-all/openmetadata-mcp-server

Build from source

git clone https://github.com/us-all/openmetadata-mcp-server.git
cd openmetadata-mcp-server && pnpm install && pnpm build
node dist/index.js

Get a token

  1. Open OpenMetadata UI → Settings → Bots

  2. Create a new bot or use an existing one (ingestion-bot works)

  3. Copy the JWT token

Configuration

Variable

Required

Default

Description

OPENMETADATA_HOST

✅

—

OpenMetadata server URL (e.g. http://localhost:8585)

OPENMETADATA_TOKEN

✅

—

JWT or Bot token

OPENMETADATA_ALLOW_WRITE

❌

false

Set true to enable mutations (create/update/delete)

OM_TOOLS

❌

—

Comma-sep allowlist of categories. Biggest token saver.

OM_DISABLE

❌

—

Comma-sep denylist. Ignored when OM_TOOLS is set.

MCP_TRANSPORT

❌

stdio

http to enable Streamable HTTP transport

MCP_HTTP_TOKEN

conditional

—

Bearer token. Required when MCP_TRANSPORT=http

MCP_HTTP_PORT

❌

3000

HTTP listen port

MCP_HTTP_HOST

❌

127.0.0.1

HTTP bind host (DNS rebinding protection auto-enabled for localhost)

MCP_HTTP_SKIP_AUTH

❌

false

Skip Bearer auth — e.g. behind a reverse proxy that handles it

Categories (10): search, core, discovery, governance, quality, services, admin, events, entities, meta (always-on).

When MCP_TRANSPORT=http: POST /mcp (Bearer-auth JSON-RPC) + GET /health (public liveness).

Token efficiency

Scenario

Tools

Schema tokens

vs default

default (all categories)

172

24,000

—

typical (OM_TOOLS=search,core,governance,quality,discovery)

120

19,500

−19%

narrow (OM_TOOLS=search,core)

26

4,600

−81%

extractFields adds another ~80–90% reduction on individual responses (e.g. get-table 8KB → 200B with extractFields: "name,columns.*.name,columns.*.dataType"). Auto-applied across 28 read tools.

// without
get-table { "id": "..." }

// with
get-table { "id": "...", "extractFields": "name,description,columns.*.name,columns.*.dataType" }

MCP Prompts (4)

Workflow templates available via MCP prompts/list:

  • lineage-impact-analysis — given an entity, walk upstream + downstream lineage and rank by impact.

  • data-quality-investigation — diff DQ test results across two windows; cluster failure modes.

  • glossary-term-bootstrap — bulk-create a glossary with N related terms, link automatically.

  • owner-change-propagation — find all entities owned by user X, propose batch reassignment.

MCP Resources

URI-based read-only access:

om://table/{fqn} (table + columns + owners + tags + joins), om://glossary-term/{fqn}, om://lineage/{type}/{fqn} (depth 3), om://search/{query} (top 10 keyword hits), om://dashboard/{fqn}, om://pipeline/{fqn} (with tasks), om://schema/{fqn}.

Tools (172)

10 categories. Use search-tools to discover at runtime; full list collapsed below.

Category

Tools

Tables / Databases / Schemas / Lineage

22

Services (database/dashboard/messaging/pipeline/ml/storage)

16

Glossaries / Terms

12

Domains / Data Products

12

Classifications / Tags

10

Discovery (dashboards / pipelines / charts / topics / containers / ml-models)

36

Governance (roles / policies / users / teams / bots)

13

Quality (test suites / cases / sample data)

13

Stored Procedures / Queries

11

OM 1.12+ entities (Data Contract / Metric / Search Index / API Collection / API Endpoint)

12

Search (search-metadata, suggest-metadata, semantic-search)

3

Aggregations (lineage-impact, quality-rollup, get-domain-summary, get-table-summary)

4

Quality (run-test-suite write-gated)

1

Meta (search-tools)

1

Search (3)

search-metadata, suggest-metadata, semantic-search

Tables (6)

list-tables, get-table, get-table-by-name, create-table, update-table, delete-table

Databases (6)

list-databases, get-database, get-database-by-name, create-database, update-database, delete-database

Database Schemas (6)

list-schemas, get-schema, get-schema-by-name, create-schema, update-schema, delete-schema

Lineage (4)

get-lineage, get-lineage-by-name, add-lineage, delete-lineage

Services (16)

6 database-service tools + 2 each for dashboard/messaging/pipeline/ml-model/storage services.

Glossaries (12)

6 glossary CRUD + 6 glossary-term CRUD.

Dashboards / Pipelines / Topics / Charts / Containers / ML Models (36)

6 CRUD each, follows list / get / get-by-name / create / update / delete.

Classifications & Tags (10)

4 classification + 6 tag CRUD.

Domains & Data Products (12)

6 domain + 6 data-product CRUD.

Users & Teams (9)

3 user reads + 6 team CRUD.

Access Control (4)

list-roles, get-role, list-policies, get-policy

Data Quality (7)

list-test-suites, get-test-suite, get-test-suite-by-name, list-test-cases, get-test-case, get-test-case-by-name, list-test-case-results

Stored Procedures (6)

6 CRUD.

Queries (5)

list-queries, get-query, create-query, update-query, delete-query

Events (3)

list-events, get-event-subscription, get-event-subscription-by-name

Bots (3)

list-bots, get-bot, get-bot-by-name

Sample Data (6, read-only)

get-table-sample-data, get-table-sample-data-by-name, get-topic-sample-data, get-topic-sample-data-by-name, get-container-sample-data, get-container-sample-data-by-name

OM 1.12+ entities (12)

list-data-contracts, get-data-contract-by-name, run-data-contract-validation, get-data-contract-latest-result, list-metrics, get-metric-by-name, list-search-indexes, get-search-index-by-name, list-api-collections, get-api-collection-by-name, list-api-endpoints, get-api-endpoint-by-name

Aggregations

lineage-impact, quality-rollup, get-domain-summary, get-table-summary

Quality (write-gated)

run-test-suite — triggers the test-suite's associated ingestion pipeline. Async; results land via the normal pipeline flow.

Meta

search-tools — query other tools by keyword; always enabled.

Architecture

Claude → MCP stdio → src/index.ts → src/tools/*.ts → OpenMetadataClient (fetch) → OpenMetadata REST

Built on @us-all/mcp-toolkit:

  • extractFields — token-efficient response projections

  • aggregate(fetchers, caveats) — fan-out helper used by lineage-impact / get-domain-summary / get-table-summary

  • createWrapToolHandler — OPENMETADATA_TOKEN redaction + OpenMetadataError extraction

  • search-tools meta-tool

Targets OM 1.x. Validated against real OM backend with the OM 1.12+ entities.

Tech stack

Node.js 22+ • TypeScript strict ESM • pnpm • @modelcontextprotocol/sdk • zod • dotenv • vitest.

JSON-Patch updates handled automatically (PATCH application/json-patch+json content-type).

License

MIT

Available Tools

173 tools
add-lineageB

Add or update lineage edge between two entities

Inputs: edge (required).

create-chartC

Create a new chart

Inputs: name (required), service (required), description, displayName, +4 more.

create-classificationC

Create a new tag classification

Inputs: name (required), description (required), mutuallyExclusive.

create-containerC

Create a new storage container

Inputs: name (required), service (required), description, displayName, +3 more.

create-dashboardC

Create a new dashboard

Inputs: name (required), service (required), description, displayName, +3 more.

create-databaseC

Create a new database in OpenMetadata

Inputs: name (required), service (required), description, owners, +1 more.

create-database-serviceC

Create a new database service connector

Inputs: name (required), serviceType (required), connection (required), description.

create-data-productC

Create a new data product

Inputs: name (required), domains (required), description, displayName, +3 more.

create-domainC

Create a new domain

Inputs: name (required), description (required), domainType (required), displayName, +2 more.

create-glossaryC

Create a new glossary for business terms

Inputs: name (required), description (required), displayName, mutuallyExclusive, +3 more.

create-glossary-termC

Create a new glossary term

Inputs: glossary (required), name (required), description (required), displayName, +5 more.

create-ml-modelC

Create a new ML model

Inputs: name (required), service (required), algorithm (required), description, +5 more.

create-pipelineC

Create a new pipeline

Inputs: name (required), service (required), description, displayName, +4 more.

create-queryC

Save a new SQL query

Inputs: query (required), service (required), description, name, +3 more.

create-schemaC

Create a new database schema

Inputs: name (required), database (required), description, owners, +1 more.

create-stored-procedureC

Create a new stored procedure

Inputs: name (required), databaseSchema (required), description, storedProcedureCode, +2 more.

create-tableC

Create a new table in OpenMetadata

Inputs: name (required), databaseSchema (required), columns (required), tableType, +3 more.

create-tagB

Create a new tag under a classification

Inputs: classification (required), name (required), description (required), displayName, +1 more.

create-teamC

Create a new team

Inputs: name (required), teamType (required), description, displayName, +4 more.

create-topicC

Create a new topic

Inputs: name (required), service (required), description, partitions, +4 more.

delete-chartC

Delete a chart by UUID

Inputs: id (required), hardDelete, recursive.

delete-classificationB

Delete a tag classification

Inputs: id (required), hardDelete, recursive.

delete-containerC

Delete a container by UUID

Inputs: id (required), hardDelete, recursive.

delete-dashboardB

Delete a dashboard by UUID

Inputs: id (required), hardDelete, recursive.

delete-databaseC

Delete a database by UUID

Inputs: id (required), hardDelete, recursive.

delete-database-serviceC

Delete a database service

Inputs: id (required), hardDelete, recursive.

delete-data-productB

Delete a data product by UUID

Inputs: id (required), hardDelete, recursive.

delete-domainC

Delete a domain by UUID

Inputs: id (required), hardDelete, recursive.

delete-glossaryC

Delete a glossary by UUID

Inputs: id (required), hardDelete, recursive.

delete-glossary-termC

Delete a glossary term by UUID

Inputs: id (required), hardDelete, recursive.

delete-lineageB

Delete a lineage edge between two entities

Inputs: fromEntity (required), fromId (required), toEntity (required), toId (required).

delete-ml-modelB

Delete an ML model by UUID

Inputs: id (required), hardDelete, recursive.

delete-pipelineB

Delete a pipeline by UUID

Inputs: id (required), hardDelete, recursive.

delete-queryB

Delete a saved query by UUID

Inputs: id (required), hardDelete.

delete-schemaC

Delete a database schema by UUID

Inputs: id (required), hardDelete, recursive.

delete-stored-procedureB

Delete a stored procedure by UUID

Inputs: id (required), hardDelete, recursive.

delete-tableC

Delete a table by UUID

Inputs: id (required), hardDelete, recursive.

delete-tagB

Delete a tag by UUID

Inputs: id (required), hardDelete, recursive.

delete-teamC

Delete a team by UUID

Inputs: id (required), hardDelete, recursive.

delete-topicB

Delete a topic by UUID

Inputs: id (required), hardDelete, recursive.

get-api-collection-by-nameB

Get an API Collection by fully qualified name (OM 1.12+)

Inputs: fqn (required), fields, include, extractFields.

get-api-endpoint-by-nameC

Get an API Endpoint by fully qualified name (OM 1.12+)

Inputs: fqn (required), fields, include, extractFields.

get-botB

Get bot details by UUID

Inputs: id (required), fields, include.

get-bot-by-nameB

Get bot by name

Inputs: name (required), fields, include.

get-chartC

Get chart details by UUID

Inputs: id (required), fields, include, extractFields.

get-chart-by-nameC

Get chart by fully qualified name

Inputs: fqn (required), fields, include, extractFields.

get-classificationC

Get classification details by name

Inputs: name (required), fields, include.

get-containerB

Get container details by UUID

Inputs: id (required), fields, include, extractFields.

get-container-by-nameB

Get container by fully qualified name

Inputs: fqn (required), fields, include, extractFields.

get-container-sample-dataB

Get sample data for a storage container by UUID

Inputs: id (required).

get-container-sample-data-by-nameC

Get sample data for a storage container by fully qualified name

Inputs: fqn (required).

get-dashboardB

Get dashboard details by UUID

Inputs: id (required), fields, include, extractFields.

get-dashboard-by-nameC

Get dashboard by fully qualified name

Inputs: fqn (required), fields, include, extractFields.

get-dashboard-serviceC

Get dashboard service by name

Inputs: fqn (required), fields, include.

get-databaseC

Get database details by UUID

Inputs: id (required), fields, include.

get-database-by-nameC

Get database details by fully qualified name

Inputs: fqn (required), fields, include.

get-database-serviceC

Get database service details by UUID

Inputs: id (required), fields, include.

get-database-service-by-nameC

Get database service by name

Inputs: fqn (required), fields, include.

get-data-contract-by-nameA

Get a Data Contract by fully qualified name (OM 1.12+)

Inputs: fqn (required), fields, include, extractFields.

get-data-contract-latest-resultB

Get the latest official OpenMetadata Data Contract validation result by contract FQN

Inputs: fqn (required), extractFields.

get-data-productB

Get data product details by UUID

Inputs: id (required), fields, include.

get-data-product-by-nameC

Get data product by fully qualified name

Inputs: fqn (required), fields, include.

get-domainB

Get domain details by UUID

Inputs: id (required), fields, include.

get-domain-by-nameC

Get domain by name

Inputs: name (required), fields, include.

get-domain-summaryA

Aggregated Domain scope: domain config (experts/owners/description) + per-entity-type counts and samples (data products, tables, dashboards, pipelines, topics, ml models) in a single call. Replaces 5-7 sequential round-trips. Failures per entity-type are collected in caveats.

Inputs: domainFqn (required), entityLimit, extractFields.

get-event-subscriptionB

Get event subscription details by UUID

Inputs: id (required), fields, include.

get-event-subscription-by-nameD

Get event subscription by name

Inputs: name (required), fields, include.

get-glossaryC

Get glossary details by UUID

Inputs: id (required), fields, extractFields.

get-glossary-by-nameC

Get glossary details by name

Inputs: fqn (required), fields, extractFields.

get-glossary-termB

Get glossary term details by UUID

Inputs: id (required), fields, extractFields.

get-glossary-term-by-nameB

Get glossary term by fully qualified name

Inputs: fqn (required), fields, extractFields.

get-lineageC

Get upstream and downstream lineage for an entity by UUID

Inputs: entity (required), id (required), upstreamDepth, downstreamDepth.

get-lineage-by-nameC

Get upstream and downstream lineage for an entity by FQN

Inputs: entity (required), fqn (required), upstreamDepth, downstreamDepth.

get-messaging-serviceC

Get messaging service by name

Inputs: fqn (required), fields, include.

get-metric-by-nameC

Get a Metric by fully qualified name (OM 1.12+)

Inputs: fqn (required), fields, include, extractFields.

get-ml-modelB

Get ML model details by UUID

Inputs: id (required), fields, include, extractFields.

get-ml-model-by-nameB

Get ML model by fully qualified name

Inputs: fqn (required), fields, include, extractFields.

get-ml-model-serviceC

Get ML model service by name

Inputs: fqn (required), fields, include.

get-pipelineC

Get pipeline details by UUID

Inputs: id (required), fields, include, extractFields.

get-pipeline-by-nameB

Get pipeline by fully qualified name

Inputs: fqn (required), fields, include, extractFields.

get-pipeline-serviceC

Get pipeline service by name

Inputs: fqn (required), fields, include.

get-policyA

Get policy details by name

Inputs: name (required), fields, include.

get-queryB

Get query details by UUID

Inputs: id (required), fields, include.

get-roleB

Get role details by name

Inputs: name (required), fields, include.

get-schemaC

Get database schema details by UUID

Inputs: id (required), fields, include.

get-schema-by-nameC

Get database schema details by fully qualified name

Inputs: fqn (required), fields, include.

get-search-index-by-nameC

Get a Search Index by fully qualified name

Inputs: fqn (required), fields, include, extractFields.

get-storage-serviceC

Get storage service by name

Inputs: fqn (required), fields, include.

get-stored-procedureB

Get stored procedure details by UUID

Inputs: id (required), fields, include.

get-stored-procedure-by-nameC

Get stored procedure by fully qualified name

Inputs: fqn (required), fields, include.

get-tableC

Get table details by UUID

Inputs: id (required), fields, include, extractFields.

get-table-by-nameC

Get table details by fully qualified name

Inputs: fqn (required), fields, include, extractFields.

get-table-sample-dataA

Get sample data rows for a table by UUID (use this instead of querying BigQuery directly)

Inputs: id (required).

get-table-sample-data-by-nameB

Get sample data rows for a table by fully qualified name

Inputs: fqn (required).

get-table-summaryA

Aggregated table view: entity + lineage + (optional) sample data + (optional) DQ test cases in a single call. Replaces 3-4 round-trips of get-table-by-name + get-lineage + get-sample-data + list-test-cases.

Inputs: fqn (required), includeLineage, includeSample, includeTestCases, +1 more.

get-tagB

Get tag details by UUID

Inputs: id (required), fields, include.

get-tag-by-nameC

Get tag by fully qualified name

Inputs: fqn (required), fields, include.

get-teamB

Get team details by UUID

Inputs: id (required), fields, include.

get-team-by-nameC

Get team by name

Inputs: name (required), fields, include.

get-test-caseC

Get test case details by UUID

Inputs: id (required), fields, include.

get-test-case-by-nameC

Get test case by fully qualified name

Inputs: fqn (required), fields, include.

get-test-suiteC

Get test suite details by UUID

Inputs: id (required), fields, include.

get-test-suite-by-nameC

Get test suite by fully qualified name

Inputs: fqn (required), fields, include.

get-topicB

Get topic details by UUID

Inputs: id (required), fields, include, extractFields.

get-topic-by-nameC

Get topic by fully qualified name

Inputs: fqn (required), fields, include, extractFields.

get-topic-sample-dataA

Get sample data (messages) for a topic by UUID

Inputs: id (required).

get-topic-sample-data-by-nameB

Get sample data (messages) for a topic by fully qualified name

Inputs: fqn (required).

get-userB

Get user details by UUID

Inputs: id (required), fields, include.

get-user-by-nameC

Get user by username

Inputs: name (required), fields, include.

lineage-impactA

Aggregated downstream impact analysis: walks lineage (default 3 levels down, 1 up), counts unique consumers, breaks down by entity type, surfaces highest-fan-out top consumers, and (optionally) resolves the union of owners affected. Answers 'who/what breaks if I change X?' in one call instead of recursive get-lineage walks. Renders an Apps SDK card on ChatGPT clients.

Inputs: entity (required), fqn (required), downstreamDepth, upstreamDepth, +2 more.

list-api-collectionsB

List API Collections (OM 1.12+) with pagination

Inputs: fields, limit, before, after, +3 more.

list-api-endpointsB

List API Endpoints (OM 1.12+) with pagination

Inputs: fields, limit, before, after, +3 more.

list-botsC

List bots with pagination

Inputs: fields, limit, before, after, +1 more.

list-chartsA

List charts with pagination and service filtering

Inputs: fields, limit, before, after, +3 more.

list-classificationsC

List tag classifications

Inputs: fields, limit, before, after, +1 more.

list-containersB

List storage containers with pagination

Inputs: fields, limit, before, after, +3 more.

list-dashboardsB

List dashboards with pagination and service filtering

Inputs: fields, limit, before, after, +3 more.

list-dashboard-servicesC

List dashboard services

Inputs: fields, limit, before, after, +1 more.

list-databasesC

List databases with pagination and service filtering

Inputs: fields, limit, before, after, +2 more.

list-database-servicesC

List database services (connectors)

Inputs: fields, limit, before, after, +1 more.

list-data-contractsC

List Data Contracts (OM 1.12+) with pagination

Inputs: fields, limit, before, after, +2 more.

list-data-productsC

List data products with pagination

Inputs: fields, limit, before, after, +2 more.

list-domainsC

List domains with pagination

Inputs: fields, limit, before, after, +1 more.

list-eventsC

List event subscriptions

Inputs: fields, limit, before, after, +1 more.

list-glossariesC

List glossaries with pagination

Inputs: fields, limit, before, after, +2 more.

list-glossary-termsC

List glossary terms with pagination and glossary filtering

Inputs: fields, limit, before, after, +4 more.

list-messaging-servicesC

List messaging services (Kafka, etc.)

Inputs: fields, limit, before, after, +1 more.

list-metricsB

List business/operational Metrics (OM 1.12+) with pagination

Inputs: fields, limit, before, after, +2 more.

list-ml-modelsB

List ML models with pagination and service filtering

Inputs: fields, limit, before, after, +3 more.

list-ml-model-servicesD

List ML model services

Inputs: fields, limit, before, after, +1 more.

list-pipelinesB

List pipelines with pagination and service filtering

Inputs: fields, limit, before, after, +3 more.

list-pipeline-servicesC

List pipeline services (Airflow, etc.)

Inputs: fields, limit, before, after, +1 more.

list-policiesC

List policies with pagination

Inputs: fields, limit, before, after, +1 more.

list-queriesB

List saved queries with pagination

Inputs: fields, limit, before, after, +2 more.

list-rolesB

List roles with pagination

Inputs: fields, limit, before, after, +1 more.

list-schemasC

List database schemas with pagination

Inputs: fields, limit, before, after, +2 more.

list-search-indexesB

List Search Indexes (e.g. ElasticSearch/OpenSearch) with pagination

Inputs: fields, limit, before, after, +3 more.

list-storage-servicesC

List storage services (S3, GCS, etc.)

Inputs: fields, limit, before, after, +1 more.

list-stored-proceduresB

List stored procedures with pagination

Inputs: fields, limit, before, after, +2 more.

list-tablesA

List tables with pagination and optional field expansion

Inputs: fields, limit, before, after, +4 more.

list-tagsC

List tags with pagination and classification filtering

Inputs: fields, limit, before, after, +2 more.

list-teamsC

List teams with pagination

Inputs: fields, limit, before, after, +2 more.

list-test-case-resultsC

List test case execution results

Inputs: id (required), startTs, endTs.

list-test-casesC

List data quality test cases with filtering

Inputs: fields, limit, before, after, +4 more.

list-test-suitesC

List data quality test suites

Inputs: fields, limit, before, after, +1 more.

list-topicsC

List topics (Kafka, etc.) with pagination

Inputs: fields, limit, before, after, +3 more.

list-usersB

List users with pagination and team filtering

Inputs: fields, limit, before, after, +4 more.

quality-rollupA

Aggregated DQ status across a scope (table / test suite / org-wide). Lists test cases under the scope, buckets them by current status (Success/Failed/Aborted/Queued), surfaces the top failing cases (with fqn/result/timestamp), reports passRatePct + most-recent-run timestamp. Replaces the recursive list-test-cases + list-test-case-results walk LLMs do for 'what's broken in ?'. Provide ONE of entityLink / tableFqn / testSuiteId / testSuiteFqn (or none for org-wide).

Inputs: entityLink, tableFqn, testSuiteId, testSuiteFqn, +2 more.

run-data-contract-validationB

Trigger OpenMetadata's native Data Contract validation and return the official validation result. Write-gated by OPENMETADATA_ALLOW_WRITE because OM records validation results.

Inputs: fqn (required), extractFields.

run-test-suiteA

Trigger execution of a Test Suite via its associated ingestion pipeline. Async — returns the trigger ack, results land via the normal pipeline → testCaseResult flow (poll list-test-case-results or quality-rollup). Provide pipelineFqn or pipelineId directly, OR testSuiteFqn (resolved to its first associated pipeline). Write-gated by OPENMETADATA_ALLOW_WRITE.

Inputs: pipelineFqn, pipelineId, testSuiteFqn.

search-metadataB

Search OpenMetadata entities (tables, topics, dashboards, pipelines, glossary terms, etc.) by keyword

Inputs: q (required), index, from, size, +7 more.

search-toolsA

Discover available tools by natural language query. Returns matching tool names + descriptions across all categories. Use this to navigate the 154-tool surface efficiently — call this first, then call the specific tool you need.

Inputs: query (required), category, limit.

suggest-metadataB

Get autocomplete suggestions for OpenMetadata entity names

Inputs: q (required), index, size, field.

update-chartB

Update a chart using JSON Patch operations

Inputs: id (required), operations (required).

update-containerB

Update a container using JSON Patch operations

Inputs: id (required), operations (required).

update-dashboardB

Update a dashboard using JSON Patch operations

Inputs: id (required), operations (required).

update-databaseA

Update a database using JSON Patch operations

Inputs: id (required), operations (required).

update-database-serviceB

Update a database service using JSON Patch

Inputs: id (required), operations (required).

update-data-productA

Update a data product using JSON Patch operations

Inputs: id (required), operations (required).

update-domainB

Update a domain using JSON Patch operations

Inputs: id (required), operations (required).

update-glossaryC

Update a glossary using JSON Patch operations

Inputs: id (required), operations (required).

update-glossary-termC

Update a glossary term using JSON Patch operations

Inputs: id (required), operations (required).

update-ml-modelB

Update an ML model using JSON Patch operations

Inputs: id (required), operations (required).

update-pipelineB

Update a pipeline using JSON Patch operations

Inputs: id (required), operations (required).

update-queryB

Update a saved query using JSON Patch operations

Inputs: id (required), operations (required).

update-schemaB

Update a database schema using JSON Patch operations

Inputs: id (required), operations (required).

update-stored-procedureC

Update a stored procedure using JSON Patch operations

Inputs: id (required), operations (required).

update-tableB

Update a table using JSON Patch operations

Inputs: id (required), operations (required).

update-tagA

Update a tag using JSON Patch operations

Inputs: id (required), operations (required).

update-teamB

Update a team using JSON Patch operations

Inputs: id (required), operations (required).

update-topicB

Update a topic using JSON Patch operations

Inputs: id (required), operations (required).

validate-data-contractA

Read-only validation of an OM 1.12+ Data Contract against the actual entity state. Reports per-rule schema findings (column existence, type, nullable/constraint match) + latest test case result for each linked qualityExpectation. Companion to the data-contract-bootstrap Prompt — bootstrap infers, this validates.

Inputs: contractFqn (required), includeQualityResults.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    C2.6/5.0

    Scored across 173 tools

    Disambiguation4/5

    The list/get/create/update/delete pattern per entity type makes most tools easy to tell apart, and UUID vs FQN variants are explicitly labeled in each description. A few aggregated and validation tools overlap conceptually (validate-data-contract vs run-data-contract-validation, get-table-summary vs get-table + get-lineage), but those descriptions are differentiated enough to avoid major mis-selection.

    Naming Consistency4/5

    Overwhelmingly consistent: almost every tool uses lowercase snake_case with a verb-noun pattern like list-tables, get-table-by-name, and update-database. The small set of aggregate/utility tools (semantic-search, lineage-impact, quality-rollup, search-tools) deviates slightly from that pattern but still reads clearly.

    Tool Count1/5

    173 tools is far beyond the extreme-mismatch threshold and will overwhelm agents, even with search-tools as a navigation aid. The per-entity CRUD expansion could be parameterized into a much smaller set without losing capability.

    Completeness4/5

    The set gives deep lifecycle coverage for most core data assets—tables, databases, schemas, dashboards, pipelines, topics, glossaries, teams, and domains—plus lineage, sample data, quality rollups, and data-contract validation. The main gaps are read-only admin surfaces (users, roles, policies, metrics, API collections, search indexes) and missing create/update for some service types, which are workable but noticeable.

    Maintenance

    ActivityNo data
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      F
      maintenance
      Open-source agentic schema layer. Define metrics once in YAML, query governed data from any warehouse (Snowflake, BigQuery, Databricks, PostgreSQL, DuckDB) via MCP.
      28
      Apache 2.0
    • A
      license
      A
      quality
      B
      maintenance
      MCP server with 32 tools for ETL ingestion, AI-generated data quality rules, AI transformations, vector search, and natural-language SQL. Works across Postgres, MongoDB, Kafka, S3/MinIO, HashiCorp Vault, and five vector stores (Qdrant, Weaviate, Milvus, Chroma, pgvector).
      90
      14
      Apache 2.0
    • A
      license
      Not graded
      quality
      C
      maintenance
      Data Workers is the Autonomous Agentic Data Platform: reduce your data ops to zero, with agents that run the whole data platform (pipelines, quality, incidents, schema change, catalog, governance) through MCP in Claude Code, Codex, Cursor and any MCP client. Learn more at dataworkers.io.
      14
      Apache 2.0