MCP Tools

OpenMetadata exposes an MCP server at /mcp that turns your metadata into a set of tools any LLM can use. Unlike generic MCP connectors that only read raw database schemas, OpenMetadata’s MCP tools give your AI access to the full context of your data platform — descriptions, owners, lineage, glossary terms, tags, and data quality results.

Available Tools

Tool	Description
`search_metadata`	Search across your OpenMetadata instance
`semantic_search`	AI-powered semantic search that understands meaning and context beyond keyword matching
`get_entity_details`	Get detailed information about an entity
`get_entity_lineage`	Get lineage information for an entity
`create_glossary`	Create a new glossary
`create_glossary_term`	Create a new glossary term
`create_lineage`	Create lineage between entities
`patch_entity`	Update an entity’s metadata
`get_test_definitions`	List available data quality test definitions
`create_test_case`	Create a data quality test case for an entity
`root_cause_analysis`	Analyze root causes of data quality failures

Tool Call Parameters

tool_name

string

required

Name of the MCP tool to invoke. Must be one of the available tools listed above.

arguments

object

required

Tool-specific arguments. Each tool accepts different parameters.

Show search_metadata arguments

query

string

required

Search query string (e.g., "customers", "revenue pipeline").

entity_type

string

Filter by entity type: table, dashboard, pipeline, topic, mlmodel, container, glossaryTerm.

limit

integer

default:"10"

Maximum number of results to return.

Show get_entity_details arguments

entity_id

string

required

UUID or fully qualified name of the entity.

entity_type

string

required

Type of entity: table, dashboard, pipeline, topic, mlmodel, container.

fields

string

Comma-separated list of additional fields to include (e.g., "columns,tags,owners,lineage").

Show get_entity_lineage arguments

entity_id

string

required

UUID or fully qualified name of the entity.

entity_type

string

required

Type of entity to get lineage for.

depth

integer

default:"1"

How many levels of upstream/downstream lineage to retrieve.

Show create_glossary arguments

name

string

required

Name of the glossary.

description

string

required

Description of the glossary in Markdown format.

owners

array

Array of owner references.

Show create_glossary_term arguments

glossary

string

required

Fully qualified name of the parent glossary.

name

string

required

Name of the glossary term.

description

string

required

Description of the term in Markdown format.

synonyms

array

List of synonyms for the term.

Show create_lineage arguments

from_entity

string

required

Fully qualified name of the source entity.

to_entity

string

required

Fully qualified name of the target entity.

from_type

string

required

Type of the source entity.

to_type

string

required

Type of the target entity.

Show patch_entity arguments

entity_id

string

required

UUID of the entity to update.

entity_type

string

required

Type of entity to patch.

patch

array

required

JSON Patch operations (RFC 6902) to apply.

Show semantic_search arguments

query

string

required

Natural language query. The search understands meaning and context beyond exact keyword matching.

entity_type

string

Filter by entity type: table, dashboard, pipeline, topic, mlmodel, container, searchIndex.

limit

integer

default:"10"

Maximum number of results to return.

Show get_test_definitions arguments

entity_type

string

Filter test definitions by entity type (e.g., table, column).

limit

integer

default:"10"

Maximum number of definitions to return.

Show create_test_case arguments

entity_fqn

string

required

Fully qualified name of the entity to test.

test_definition

string

required

Name of the test definition to use (from get_test_definitions).

name

string

required

Name for the test case.

parameters

object

Test-specific parameters (depends on the test definition).

Show root_cause_analysis arguments

test_case_id

string

required

UUID of the failed test case to analyze.

Calling Tools Directly

POST /mcp (call tool)

from ai_sdk import AISdk, AISdkConfig

config = AISdkConfig.from_env()
client = AISdk.from_config(config)

# List available tools
tools = client.mcp.list_tools()
for tool in tools:
    print(f"{tool.name}: {tool.description}")

# Search for tables
result = client.mcp.call_tool("search_metadata", {
    "query": "customers",
    "entity_type": "table",
    "limit": 5
})

# Get entity details
result = client.mcp.call_tool("get_entity_details", {
    "entity_id": "sample_data.ecommerce_db.shopify.customers",
    "entity_type": "table",
    "fields": "columns,tags,owners"
})

# Get lineage
result = client.mcp.call_tool("get_entity_lineage", {
    "entity_id": "sample_data.ecommerce_db.shopify.customers",
    "entity_type": "table",
    "depth": 2
})

{
  "content": [
    {
      "type": "text",
      "text": "[{\"name\": \"customers\", \"fullyQualifiedName\": \"sample_data.ecommerce_db.shopify.customers\", \"entityType\": \"table\", \"description\": \"Customer master data including contact info and account details.\", \"owners\": [\"data-team\"], \"tags\": [\"PII.Sensitive\"]}]"
    }
  ]
}

LangChain Integration

Convert MCP tools to LangChain format with a single method call:

pip install data-ai-sdk[langchain]

from ai_sdk import AISdk, AISdkConfig
from langchain_openai import ChatOpenAI
from langchain.agents import AgentExecutor, create_tool_calling_agent
from langchain_core.prompts import ChatPromptTemplate

config = AISdkConfig.from_env()
client = AISdk.from_config(config)

# Convert MCP tools to LangChain format
tools = client.mcp.as_langchain_tools()

llm = ChatOpenAI(model="gpt-4")
prompt = ChatPromptTemplate.from_messages([
    ("system", "You are an OpenMetadata assistant."),
    ("human", "{input}"),
    ("placeholder", "{agent_scratchpad}"),
])

agent = create_tool_calling_agent(llm, tools, prompt)
executor = AgentExecutor(agent=agent, tools=tools, verbose=True)

result = executor.invoke({
    "input": "Find tables related to customers and show their lineage"
})
print(result["output"])

OpenAI Integration

Convert MCP tools to OpenAI function calling format:

import json
from openai import OpenAI
from ai_sdk import AISdk, AISdkConfig

config = AISdkConfig.from_env()
om_client = AISdk.from_config(config)
openai_client = OpenAI()

tools = om_client.mcp.as_openai_tools()
executor = om_client.mcp.create_tool_executor()

response = openai_client.chat.completions.create(
    model="gpt-4",
    messages=[{"role": "user", "content": "Find customer tables"}],
    tools=tools,
)

message = response.choices[0].message
if message.tool_calls:
    for tool_call in message.tool_calls:
        result = executor(
            tool_call.function.name,
            json.loads(tool_call.function.arguments)
        )
        print(f"Tool: {tool_call.function.name}")
        print(f"Result: {result}")

Tool Filtering

You can filter which tools are exposed to your LLM to restrict its capabilities:

from ai_sdk.mcp.models import MCPTool

# Only include read-only tools
tools = client.mcp.as_langchain_tools(
    include=[
        MCPTool.SEARCH_METADATA,
        MCPTool.SEMANTIC_SEARCH,
        MCPTool.GET_ENTITY_DETAILS,
        MCPTool.GET_ENTITY_LINEAGE,
        MCPTool.GET_TEST_DEFINITIONS,
    ]
)

# Or exclude mutation tools
tools = client.mcp.as_langchain_tools(
    exclude=[MCPTool.PATCH_ENTITY, MCPTool.CREATE_GLOSSARY, MCPTool.CREATE_GLOSSARY_TERM]
)

The same include and exclude parameters work with as_openai_tools():

tools = client.mcp.as_openai_tools(
    include=[MCPTool.SEARCH_METADATA, MCPTool.GET_ENTITY_DETAILS]
)

Error Handling

Code	Error Type	Description
`400`	`BAD_REQUEST`	Invalid tool name or missing required arguments
`401`	`UNAUTHORIZED`	Invalid or missing authentication token
`403`	`FORBIDDEN`	User lacks permission to call the requested tool
`404`	`TOOL_NOT_FOUND`	The requested tool does not exist
`422`	`INVALID_ARGUMENTS`	Tool arguments failed validation
`500`	`TOOL_EXECUTION_ERROR`	Tool encountered an internal error during execution

API Reference

Data Assets

SDK

Discovery

Lineage

Data Contracts

Teams And Users

Data Governance

Data Quality

Main Concepts

MCP Tools

MCP Tools

Available Tools

Tool Call Parameters

Calling Tools Directly

LangChain Integration

OpenAI Integration

Tool Filtering

Error Handling

API Reference

Data Assets

SDK

Discovery

Lineage

Data Contracts

Teams And Users

Data Governance

Data Quality

Main Concepts

​MCP Tools

​Available Tools

​Tool Call Parameters

​Calling Tools Directly

​LangChain Integration

​OpenAI Integration

​Tool Filtering

​Error Handling

MCP Tools

Available Tools

Tool Call Parameters

Calling Tools Directly

LangChain Integration

OpenAI Integration

Tool Filtering

Error Handling