Mcp Datahub

io.github.txn2由 GitHub 账号 txn2 发布v1.15.1更新于 Oct 24, 2026

MCP server for DataHub data catalogs. Discover datasets, explore lineage, and access metadata.

概览

AI 生成的概览

将 AI 助手连接到 DataHub 元数据目录,可搜索数据集、查看 schema、追溯血缘并管理目录实体。

可以做什么
  • 搜索目录中的数据集、仪表板与管道,并浏览标签、域和数据产品
  • 按 URN 读取实体元数据、数据集 schema、术语表词条、数据产品详情及关联 SQL 查询
  • 追溯上下游血缘,支持列级血缘
  • 创建、更新和删除标签、域、术语表词条、数据产品、文档、事件、数据契约等目录实体(写入工具默认关闭)
  • 列出已配置的 DataHub 连接,并在多服务器场景中指定目标连接
适用场景
适合需要助手回答组织数据资产相关问题的场景,例如找到正确的表、了解其 schema 与负责人,或查看哪些下游依赖它。也适合希望助手不仅读取、还能维护目录元数据的团队。
运行要求
以本地进程运行,可通过 macOS/Windows 安装包、Homebrew 或 Go 安装。需要可访问的 DataHub GraphQL 端点与 API 令牌,通过 DATAHUB_URL 和 DATAHUB_TOKEN(或 YAML/JSON 配置文件)提供。需 DataHub 1.3.x 及以上,文档功能需 1.4.x。多实例可用 DATAHUB_ADDITIONAL_SERVERS。
安装前请注意
令牌可访问整个目录,通过环境变量或配置文件传入,请勿放入共享配置。写入工具默认关闭,除非设置 DATAHUB_WRITE_ENABLED;启用后助手可创建、更新和删除目录实体,删除操作具破坏性。目录元数据会发送到所配置的 DataHub 服务器。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Mcp Datahub,将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Desktop only,通过 STDIO。 STDIO 服务会启动本地进程,因此需要 SourceWeft 桌面宿主。

其他 MCP 客户端

参照 仓库 中的启动说明。

README

[txn2/mcp-datahub]

[GitHub license] [Go Reference] [Go Report Card] [codecov] [OpenSSF Scorecard] [SLSA 3]

An MCP server and composable Go library that connects AI assistants to DataHub metadata catalogs. Search datasets, explore schemas, trace lineage, and access glossary terms and domains.

mcp-datahub.txn2.com | Installation | Library Docs

MCP Data Platform Ecosystem

mcp-datahub is part of a broader suite of open-source MCP servers designed to work together as a composable data platform. Each component can run standalone or be combined to give AI assistants unified access to storage, query engines, and metadata catalogs.

Two Ways to Use

1. Standalone MCP Server

Install and connect to Claude Desktop, Cursor, or any MCP client:

Claude Desktop (Easiest) - Download the .mcpb bundle from releases and double-click to install:

  • macOS Apple Silicon: mcp-datahub_X.X.X_darwin_arm64.mcpb
  • macOS Intel: mcp-datahub_X.X.X_darwin_amd64.mcpb
  • Windows: mcp-datahub_X.X.X_windows_amd64.mcpb

Other Installation Methods:

bash
# Homebrew (macOS)brew install txn2/tap/mcp-datahub
# Go installgo install github.com/txn2/mcp-datahub/cmd/mcp-datahub@latest

Manual Claude Desktop Configuration (if not using MCPB):

json
{  "mcpServers": {    "datahub": {      "command": "/opt/homebrew/bin/mcp-datahub",      "env": {        "DATAHUB_URL": "https://datahub.example.com",        "DATAHUB_TOKEN": "your_token"      }    }  }}
Multi-Server Configuration

Connect to multiple DataHub instances simultaneously:

bash
# Primary serverexport DATAHUB_URL=https://prod.datahub.example.com/api/graphqlexport DATAHUB_TOKEN=prod-tokenexport DATAHUB_CONNECTION_NAME=prod
# Additional servers (JSON)export DATAHUB_ADDITIONAL_SERVERS='{"staging":{"url":"https://staging.datahub.example.com/api/graphql","token":"staging-token"}}'

Use datahub_list_connections to discover available connections, then pass the connection parameter to any tool.

2. Composable Go Library

Import into your own MCP server for custom authentication, tenant isolation, and audit logging:

go
import (    "github.com/txn2/mcp-datahub/pkg/client"    "github.com/txn2/mcp-datahub/pkg/tools")
// Create client and register tools with your MCP serverdatahubClient, _ := client.NewFromEnv()defer datahubClient.Close()
toolkit := tools.NewToolkit(datahubClient, tools.Config{})toolkit.RegisterAll(yourMCPServer)
Customizing Tool Descriptions

Override tool descriptions to match your deployment:

go
toolkit := tools.NewToolkit(datahubClient, tools.Config{},    tools.WithDescriptions(map[tools.ToolName]string{        tools.ToolSearch: "Search our internal data catalog for datasets and dashboards",    }),)
Customizing Tool Annotations

Override MCP tool annotations (behavior hints for AI clients):

go
toolkit := tools.NewToolkit(datahubClient, tools.Config{},    tools.WithAnnotations(map[tools.ToolName]*mcp.ToolAnnotations{        tools.ToolSearch: {ReadOnlyHint: true, OpenWorldHint: boolPtr(true)},    }),)

All 12 tools ship with default annotations: read tools are marked ReadOnlyHint: true; datahub_create is non-destructive and non-idempotent; datahub_update is non-destructive and idempotent; datahub_delete is destructive and idempotent.

Extensions (Logging, Metrics, Error Hints)

Enable optional middleware via the extensions package:

go
import "github.com/txn2/mcp-datahub/pkg/extensions"
// Load from environment variables (MCP_DATAHUB_EXT_*)cfg := extensions.FromEnv()opts := extensions.BuildToolkitOptions(cfg)toolkit := tools.NewToolkit(datahubClient, toolsCfg, opts...)
// Or load from a YAML/JSON config fileserverCfg, _ := extensions.LoadConfig("config.yaml")

See the library documentation for middleware, selective tool registration, and enterprise patterns.

Combining with mcp-trino

Build a unified data platform MCP server by combining DataHub metadata with Trino query execution:

go
import (    datahubClient "github.com/txn2/mcp-datahub/pkg/client"    datahubTools "github.com/txn2/mcp-datahub/pkg/tools"    trinoClient "github.com/txn2/mcp-trino/pkg/client"    trinoTools "github.com/txn2/mcp-trino/pkg/tools")
// Add DataHub tools (search, lineage, schema, glossary)dh, _ := datahubClient.NewFromEnv()datahubTools.NewToolkit(dh, datahubTools.Config{}).RegisterAll(server)
// Add Trino tools (query execution, catalog browsing)tr, _ := trinoClient.NewFromEnv()trinoTools.NewToolkit(tr, trinoTools.Config{}).RegisterAll(server)
// AI assistants can now:// - Search DataHub for tables -> Get schema -> Query via Trino// - Explore lineage -> Understand data flow -> Run validation queries

See txn2/mcp-trino for the companion library.

Bidirectional Integration with QueryProvider

The library supports bidirectional context injection. While mcp-trino can pull semantic context from DataHub, mcp-datahub can receive query execution context back from a query engine:

go
import (    datahubTools "github.com/txn2/mcp-datahub/pkg/tools"    "github.com/txn2/mcp-datahub/pkg/integration")
// QueryProvider enables query engines to inject context into DataHub toolstype myQueryProvider struct {    trinoClient *trino.Client}
func (p *myQueryProvider) Name() string { return "trino" }
func (p *myQueryProvider) ResolveTable(ctx context.Context, urn string) (*integration.TableIdentifier, error) {    // Map DataHub URN to Trino table (catalog.schema.table)    return &integration.TableIdentifier{        Catalog: "hive", Schema: "production", Table: "users",    }, nil}
func (p *myQueryProvider) GetTableAvailability(ctx context.Context, urn string) (*integration.TableAvailability, error) {    // Check if table is queryable    return &integration.TableAvailability{Available: true}, nil}
func (p *myQueryProvider) GetQueryExamples(ctx context.Context, urn string) ([]integration.QueryExample, error) {    // Return sample queries for this entity    return []integration.QueryExample{        {Name: "sample", SQL: "SELECT * FROM hive.production.users LIMIT 10"},    }, nil}
// Wire it uptoolkit := datahubTools.NewToolkit(datahubClient, config,    datahubTools.WithQueryProvider(&myQueryProvider{trinoClient: trino}),)

When a QueryProvider is configured, tool responses are enriched:

  • Search results: Include query_context with table availability
  • Entity details: Include query_table, query_examples, query_availability
  • Schema: Include query_table for immediate SQL usage
  • Lineage: Include execution_context mapping URNs to tables

Integration Middleware

Enterprise features like access control and audit logging are enabled through middleware adapters:

go
import (    datahubTools "github.com/txn2/mcp-datahub/pkg/tools"    "github.com/txn2/mcp-datahub/pkg/integration")
// Access control - filter entities by user permissionstype myAccessFilter struct{}func (f *myAccessFilter) CanAccess(ctx context.Context, urn string) (bool, error) { /* ... */ }func (f *myAccessFilter) FilterURNs(ctx context.Context, urns []string) ([]string, error) { /* ... */ }
// Audit logging - track all tool invocationstype myAuditLogger struct{}func (l *myAuditLogger) LogToolCall(ctx context.Context, tool string, params map[string]any, userID string) error { /* ... */ }
// Wire up with multiple integration optionstoolkit := datahubTools.NewToolkit(datahubClient, config,    datahubTools.WithAccessFilter(&myAccessFilter{}),    datahubTools.WithAuditLogger(&myAuditLogger{}, func(ctx context.Context) string {        return ctx.Value("user_id").(string)    }),    datahubTools.WithURNResolver(&myURNResolver{}),      // Map external IDs to URNs    datahubTools.WithMetadataEnricher(&myEnricher{}),    // Add custom metadata)

See the library documentation for complete integration patterns.

Available Tools

Read Tools (always available)

ToolDescription
datahub_searchSearch for datasets, dashboards, pipelines by query and entity type
datahub_get_entityGet entity metadata by URN (description, owners, tags, domain)
datahub_get_schemaGet dataset schema with field types and descriptions
datahub_get_lineageGet upstream/downstream lineage (supports level=column for column-level)
datahub_get_queriesGet SQL queries associated with a dataset
datahub_browseBrowse catalog: list tags, domains, or data products
datahub_get_glossary_termGet glossary term definition and properties
datahub_get_data_productGet data product details (owners, domain, properties)
datahub_list_connectionsList configured DataHub server connections (multi-server mode)

Write Tools (require DATAHUB_WRITE_ENABLED=true)

3 CRUD tools using the what discriminator pattern — 37 operations total:

ToolOperationsDescription
datahub_create10Create tags, domains, glossary terms, data products, documents, applications, queries, incidents, structured properties, data contracts
datahub_update19Update descriptions (including tag/glossaryTerm descriptions), tags, glossary terms, links, owners, domains, structured properties, custom properties, incidents, queries, documents, data contracts
datahub_delete8Delete queries, tags, domains, glossary entities, data products, applications, documents, structured properties

Write tools are disabled by default for safety.

DataHub Version Compatibility

Minimum: DataHub 1.3.x. Full feature set: DataHub 1.4.x.

DataHub VersionFeatures
1.3.x+ (minimum)All read tools, all write operations except documents (tags, domains, glossary, data products, queries, owners, links, descriptions, incidents, applications, structured properties incl. delete, data contracts)
1.4.x+ (full)+ Documents (create/update/delete)

The client gracefully handles version differences — read queries return empty results (not errors) when a feature is unavailable on older versions.

See the tools reference for detailed documentation.

Configuration

VariableDescriptionDefault
DATAHUB_URLDataHub GraphQL API URL(required)
DATAHUB_TOKENAPI token(required)
DATAHUB_TIMEOUTRequest timeout (seconds)30
DATAHUB_DEFAULT_LIMITDefault search limit10
DATAHUB_MAX_LIMITMaximum limit100
DATAHUB_CONNECTION_NAMEDisplay name for primary connectiondatahub
DATAHUB_ADDITIONAL_SERVERSJSON map of additional servers(optional)
DATAHUB_WRITE_ENABLEDEnable write operations (true or 1)false
DATAHUB_DEBUGEnable debug logging (1 or true)false

Extensions

VariableDescriptionDefault
MCP_DATAHUB_EXT_LOGGINGEnable structured logging of tool callsfalse
MCP_DATAHUB_EXT_METRICSEnable metrics collectionfalse
MCP_DATAHUB_EXT_METADATAEnable metadata enrichment on resultsfalse
MCP_DATAHUB_EXT_ERRORSEnable error hint enrichmenttrue

Config File

As an alternative to environment variables, configure via YAML or JSON:

yaml
datahub:  url: https://datahub.example.com  token: "${DATAHUB_TOKEN}"  timeout: "30s"  write_enabled: true
toolkit:  default_limit: 20  descriptions:    datahub_search: "Custom search description for your deployment"
extensions:  logging: true  errors: true

Load with extensions.LoadConfig("config.yaml"). Environment variables override file values for sensitive fields. Token values support $VAR / ${VAR} expansion.

See configuration reference for all options.

Development

bash
make build     # Build binarymake test      # Run tests with race detectionmake lint      # Run golangci-lintmake security  # Run gosec and govulncheckmake coverage  # Generate coverage reportmake verify    # Run tidy, lint, and testmake help      # Show all targets

Related Projects

Contributing

See CONTRIBUTING.md for guidelines.

License

Apache License 2.0


Open source by Craig Johnston, sponsored by Deasil Works, Inc.

来源:README.md,提交 8b66462

工具

0
SourceWeft 尚未在沙箱中启动过该软件包,因此其工具未知。

版本历史

1
  1. v1.15.1最新Sep 16, 2026

评分

已满足适用检查项的 50%

该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。

  • 近 30 天内可连通25 分

    请保持端点能够响应 MCP 握手;SourceWeft 每 30 天探测一次。

  • 已声明认证方式10 分

    请在注册中心条目中声明凭据请求头,或保持端点能够响应探测,以便判定其认证方式。

  • 已列出工具15 分

    请让服务器在无凭据时响应 tools/list,或发布可在沙箱中无凭据启动的软件包。

  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分