apache-atlas-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ATLAS_TIMEOUT | No | HTTP request timeout (seconds) | 30 |
| ATLAS_BASE_URL | Yes | Atlas server URL (e.g., http://localhost:21000) | |
| ATLAS_PASSWORD | Yes | Authentication password | |
| ATLAS_USERNAME | Yes | Authentication username | |
| ATLAS_VERIFY_SSL | No | Verify SSL certificates | true |
| ATLAS_ALLOW_WRITE | No | Enable write operations (create, delete, classify) | false |
Capabilities
Features and capabilities supported by this server
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| extensions | {
"io.modelcontextprotocol/ui": {}
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_entities | Search for entities in Apache Atlas using basic search. Finds data assets (tables, columns, processes, etc.) by keyword, type, or classification. Returns matching entity headers with key attributes. Args: query: Free-text search query (e.g., "customer_orders"). type_name: Filter by entity type (e.g., "hive_table", "rdbms_table"). classification: Filter by classification tag (e.g., "PII", "Confidential"). limit: Maximum number of results (default: 25, max: 100). offset: Pagination offset. |
| dsl_search | Execute an Atlas DSL (Domain Specific Language) search query. Atlas DSL supports structured queries with type filters, attribute conditions, and aggregations. Useful for complex, precise queries. Example DSL queries:
Args: query: Atlas DSL query string. limit: Maximum number of results (default: 25). offset: Pagination offset. |
| quick_search | Perform a quick search across all entity types. Faster than basic search, optimized for autocomplete-style lookups. Good for finding entities when you have a partial name. Args: query: Search text (supports partial matching). type_name: Optional type filter (e.g., "hive_table"). limit: Maximum number of results (default: 25). |
| get_entity | Get full details of an entity by its GUID. Returns the complete entity with all attributes, classifications, relationship attributes, and optionally referred entities. Args: guid: The unique identifier (GUID) of the entity. min_ext_info: If true, returns minimal info for referred entities. ignore_relationships: If true, omits relationship attributes. |
| get_entity_by_attribute | Get an entity by its unique attribute value. Useful when you know the qualified name or another unique attribute instead of the GUID. Common pattern: look up by qualifiedName. Args: type_name: The entity type (e.g., "hive_table", "rdbms_table"). attribute_name: Unique attribute name (typically "qualifiedName"). attribute_value: The attribute value to match. |
| get_entities_bulk | Get multiple entities by their GUIDs in a single request. Efficient way to fetch details for several entities at once, e.g., after collecting GUIDs from a search or lineage query. Args: guids: List of entity GUIDs to retrieve (max 25). |
| get_lineage | Get the data lineage graph for an entity. Traces upstream (INPUT) and/or downstream (OUTPUT) data flow relationships. This is the most valuable tool for understanding how data moves through your system. The response includes:
Args: guid: The GUID of the entity to trace lineage for. direction: "INPUT" (upstream), "OUTPUT" (downstream), or "BOTH". depth: How many hops to traverse (default: 3, max: 10). |
| get_lineage_by_attribute | Get lineage for an entity identified by a unique attribute. Same as get_lineage but uses a unique attribute (like qualifiedName) instead of a GUID. Convenient when you know the entity's name but not its GUID. Args: type_name: Entity type (e.g., "hive_table"). attribute_name: Unique attribute name (typically "qualifiedName"). attribute_value: The attribute value to match. direction: "INPUT" (upstream), "OUTPUT" (downstream), or "BOTH". depth: How many hops to traverse (default: 3, max: 10). |
| get_classifications | Get all classifications (tags) applied to an entity. Classifications are used for data governance — e.g., PII, Confidential, HIPAA, GDPR tags that indicate sensitivity or compliance requirements. Args: guid: The GUID of the entity. |
| list_glossaries | List all business glossaries. Glossaries organize business terms and definitions, providing a shared vocabulary for data assets across the organization. Args: limit: Maximum number of glossaries to return. offset: Pagination offset. |
| get_glossary | Get a glossary by its GUID, including its terms and categories. Args: glossary_guid: The GUID of the glossary. |
| get_glossary_terms | List terms in a specific glossary. Returns business terms with their definitions, linked entities, and category assignments. Args: glossary_guid: The GUID of the glossary. limit: Maximum number of terms to return. offset: Pagination offset. |
| get_glossary_term | Get a glossary term by its GUID. Returns the full term including definition, linked entities, related terms (seeAlso), and category assignments. Args: term_guid: The GUID of the glossary term. |
| get_all_type_definitions | Get all type definitions from Atlas. Returns the complete type system including entity types, classification types, relationship types, enum types, and struct types. This is useful for understanding the metadata schema structure. Warning: This can return a large response. Consider using get_type_definition for specific types instead. |
| get_type_definition | Get a specific type definition by name. Returns the full type definition including attributes, super types, and constraints. Useful for understanding what attributes an entity type has. Args: name: The type name (e.g., "hive_table", "rdbms_column", "PII"). |
| get_entity_type_definition | Get an entity type definition by name. Returns the entity type definition with all attribute definitions, super types, sub types, and relationship attribute definitions. Args: name: The entity type name (e.g., "hive_table", "hive_db", "rdbms_table"). |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/DanMeon/apache-atlas-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server