openmetadata-mcp-server

# 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](https://img.shields.io/npm/v/@us-all/openmetadata-mcp)](https://www.npmjs.com/package/@us-all/openmetadata-mcp)
[![downloads](https://img.shields.io/npm/dm/@us-all/openmetadata-mcp)](https://www.npmjs.com/package/@us-all/openmetadata-mcp)
[![tools](https://img.shields.io/badge/tools-172-blue)](#tools)
[![@us-all standard](https://img.shields.io/badge/built%20to-%40us--all%20MCP%20standard-blue)](https://github.com/us-all/mcp-toolkit/blob/main/STANDARD.md)
[![Glama MCP server](https://glama.ai/mcp/servers/us-all/openmetadata-mcp-server/badges/score.svg)](https://glama.ai/mcp/servers/us-all/openmetadata-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`).

## 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

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

### Claude Code

```bash
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

```bash
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

```bash
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.

```jsonc
// 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 |

<details>
<summary>Full tool list</summary>

### 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