Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@mcp-openmetadata find tables with column 'email' in the 'sales' schema"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP server providing OpenMetadata APIs - A FastMCP integration for OpenMetadata services.
OpenMetadata API integration with FastMCP
Easy-to-use interface for metadata management
Support for table metadata, sample data, and ownership information
Related MCP server: io.github.Optisol-Business/db-metadata-extractor-mcp
Install it to Cursor with (uv):
uv pip install mcp-openmetadata
uv run python -m mcp-openmetadata.hosts.cursor \
-e OPENMETADATA_URI=<YOUR OPENMETADATA URI> \
-e OPENMETADATA_JWT_TOKEN=<YOUR OPENMETADATA JWT TOKEN>Install it to Cursor with (pip):
pip install mcp-openmetadata
python -m mcp-openmetadata.hosts.cursor \
-e OPENMETADATA_URI=<YOUR OPENMETADATA URI> \
-e OPENMETADATA_JWT_TOKEN=<YOUR OPENMETADATA JWT TOKEN>{
"mcpServers": {
"OpenMetadata": {
"command": "uv",
"args": [
"run",
"--with",
"fastmcp",
"--with",
"httpx",
"--with",
"mcp-openmetadata",
"python",
"-m",
"mcp_openmetadata.server"
],
"env": {
"OPENMETADATA_URI": "http://localhost:8585",
"OPENMETADATA_JWT_TOKEN": "awesome_jwt_token"
}
}
}
}mcp-openmetadata provides token auth and basic auth:
Token Auth
OPENMETADATA_URI=http://localhost:8585
OPENMETADATA_JWT_TOKEN=<YOUR OPENMETADATA JWT TOKEN>Basic Auth
OPENMETADATA_URI=http://localhost:8585
OPENMETADATA_USERNAME=<YOUR OPENMETADATA USERNAME>
OPENMETADATA_PASSWORD=<YOUR OPENMETADATA PASSWORD>mcp-openmetadata does not provide all APIs available in OpenMetadata. Please refer to Supported APIs for the list of available APIs.
Since using the original API directly contains too much unnecessary data that is difficult to fit into the model context, we are working on returning somewhat organized results.
search_entities_with_query: Search entities using query text. Supports pagination and sorting. Useful for:
Listing all tables/topics (q=*)
Searching by field names (e.g., q=columnNames:address)
Searching by tags (e.g., q=tags.tagFQN:user.email)
Complex queries with AND/OR operators
Filtering by service type, constraints, owners, etc.
get_list_of_tables: Get a paginated list of tables with basic information
get_table_by_fqn: Get detailed table information by fully qualified name
get_table_columns_by_fqn: Get table columns information by fully qualified name
get_table_owners_by_fqn: Get table ownership information by fully qualified name
get_sample_data: Get sample data from a specified table
Each tool returns optimized responses with relevant fields to ensure compatibility with model context limits while providing essential metadata information.
This project is open source software licensed as MIT.
Get a list of tables, optionally filtered by database it belongs to. Use fields parameter to get only necessary fields. Use cursor-based pagination to limit the number entries in the list using limit and before or after query params.
| Name | Required | Description | Default |
|---|---|---|---|
| after | No | ||
| limit | No | ||
| before | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description must carry the full burden of behavioral disclosure. It does mention pagination behavior and the ability to filter fields, but it omits critical traits such as whether the operation is read-only, default return size, sorting, and error handling. Additionally, the description references a 'fields' parameter not present in the schema, further reducing transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise, consisting of two sentences with clear front-loading of the main purpose. However, the inclusion of a 'fields' parameter that does not exist in the schema is an unnecessary and potentially misleading addition, preventing a perfect score.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of annotations, output schema, and the presence of only three parameters, the description is incomplete. It fails to describe the return format, the database filter mechanism, the meaning of 'fields', or any defaults/behavior when no parameters are supplied. This is a list tool where users likely need to know pagination details and field selection, but the description only scratches the surface.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must compensate. It explains limit and before/after as cursor-based pagination, but does not detail the format or semantics of the cursor values or pagination order. It also introduces 'fields' and 'database' parameters that are not in the schema, confusing the parameter model rather than clarifying it.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool returns a list of tables, optionally filtered by database, which distinguishes it from sibling tools like get_table_by_fqn (single table) or get_table_owners_by_fqn. However, the mention of a database filter is not reflected in the schema, creating some ambiguity about the actual scope.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives explicit instructions for using cursor-based pagination (limit, before/after) and mentions a fields parameter, but does not provide guidance on when to choose this tool over alternatives. No exclusions or references to sibling tools are given, leaving the when-to-use context implied rather than explicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get sample data from a table.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | ||
| limit | No | ||
| offset | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It only states a read operation ('Get') without describing any behavioral traits such as what the returned data looks like, whether it respects permissions, or the meaning of 'sample.'
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, straightforward sentence with no fluff. It is appropriately sized for a simple tool, though it sacrifices detail for brevity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with no annotations, no output schema, and three parameters, the description is insufficient. It omits how 'sample' is determined, what the id refers to, and the effect of limit/offset, making it hard to use correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has three parameters (id, limit, offset) with 0% schema description coverage. The description does not explain any parameter semantics, particularly the 'id' field, which is ambiguous.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb 'Get' and identifies the resource as 'sample data from a table.' It is clearly distinct from sibling tools that query metadata, columns, owners, or lists of tables.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives. It does not mention prerequisites, exclusions, or recommend alternative tools for other use cases.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get a table by fully qualified table name.
| Name | Required | Description | Default |
|---|---|---|---|
| fully_qualified_name | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of behavioral disclosure. It does not mention return format, error handling, or whether the response includes metadata, columns, or other details. It adds no information beyond what the tool name implies.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence with no wasted words. While it is very concise, it remains appropriately sized for a simple getter; the lack of detail is a completeness issue, not a conciseness issue.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the absence of an output schema and the presence of sibling tools for columns, owners, and sample data, the description does not clarify what 'a table' means in terms of response content. It leaves the agent to wonder if the result includes nested fields, relationships, or just basic metadata.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, and the description merely repeats the parameter name 'fully qualified table name' without specifying its format (e.g., 'catalog.schema.table') or providing an example. No additional meaning is added over the schema's property title.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (get) and resource (table) with the lookup method (by fully qualified name). It implicitly distinguishes from sibling tools like get_table_owners_by_fqn and get_table_columns_by_fqn by focusing on the table object itself.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives like search_entities_with_query or get_list_of_tables. The description only states what it does, leaving the agent to infer the appropriate context for invocation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get a table columns by fully qualified table name.
| Name | Required | Description | Default |
|---|---|---|---|
| fully_qualified_name | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It does not disclose side effects, permissions, return format, or any other behavioral traits beyond the basic 'get' operation. The verb 'Get' implies read-only, but this is not explicitly stated.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence, but it contains a grammatical error ('a table columns' instead of 'a table's columns'). It is short and front-loaded, though the wording is slightly awkward.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema and no annotations, the description should specify what is returned (e.g., column names, types, metadata) and any prerequisites. It only provides the core action, leaving the agent to infer the result structure.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, and the description does not explain the fully_qualified_name format (e.g., catalog.schema.table). The phrase 'fully qualified table name' simply restates the parameter name without adding semantic value.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's function: retrieving table columns by fully qualified name. It distinguishes from siblings like get_table_by_fqn (table metadata), get_table_owners_by_fqn (owners), and get_sample_data (sample rows).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives. The description simply states what it does without mentioning related tools or scenarios where it should be preferred.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get a table owners by fully qualified table name.
| Name | Required | Description | Default |
|---|---|---|---|
| fully_qualified_name | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the full burden of disclosing behavior. It implies a read operation but does not specify whether a list of owners is returned, the format, possible errors (e.g., table not found), or permissions required. With no annotation support, this minimal description leaves the agent uncertain about side effects and return shape.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, front-loaded with the action, and contains no redundant information. It is appropriately sized for a simple retrieval tool.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool is simple with one required parameter, but the description omits return value structure, behavioral nuances, and usage context. With no output schema or annotations, the description should provide at least minimal detail about outputs and error conditions. It falls short of being complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema provides only the parameter name with no description (0% coverage). The tool description mentions 'by fully qualified table name,' which partially explains the parameter's role, but does not clarify the expected format (e.g., catalog.schema.table) or whether the name is case-sensitive. The description adds some value but not enough to fully compensate for the missing schema documentation.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses the specific verb 'Get' and identifies the resource as 'table owners' scoped by fully qualified table name. It distinguishes from sibling tools like get_table_columns_by_fqn and get_table_by_fqn by focusing on owners. The minor grammatical issue ('a table owners') does not impair understanding.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus siblings like get_table_by_fqn or search_entities_with_query. There are no exclusions, prerequisites, or alternative tool mentions. This is a significant gap given five sibling tools with overlapping table-related purposes.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search entities using query test. Use query params from and size for pagination. Use sort_field to sort the results in sort_order.
| Name | Required | Description | Default |
|---|---|---|---|
| q | No | * |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure, but it falls short. It mentions pagination (from, size) and sorting (sort_field, sort_order) parameters that are not present in the schema, which is misleading. It also fails to mention that the tool is read-only or describe the return format.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is short, but the second sentence about pagination and sorting wastes space on parameters that are not available. It does not earn its place, making the description less concise than it appears.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given a single-parameter schema, no output schema, and no annotations, the description is incomplete. It fails to explain the query syntax for 'q' or the nature of the search results, and the misleading parameter references further detract from completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema coverage is 0%, yet the description does not explain the sole parameter 'q' at all. Instead, it introduces parameters (from, size, sort_field, sort_order) that do not exist in the input schema, actively confusing the agent about the available options.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states that the tool searches entities, using the verb 'Search' and resource 'entities', which distinguishes it from the table-specific sibling tools. However, the phrase 'using query test' is awkward and likely a typo for 'query text', which slightly obscures the intended functionality.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is given on when to use this tool versus alternatives. The description only mentions pagination and sorting instructions without explaining when this search tool is appropriate compared to table-specific tools like get_table_by_fqn or get_list_of_tables.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.1.0get_list_of_tablesget_sample_dataget_table_by_fqnget_table_columns_by_fqnget_table_owners_by_fqnsearch_entities_with_queryScored across 6 tools
Each tool has a clearly distinct purpose: search across entities, retrieve a table, fetch sample data, fetch owners, fetch columns, and list tables. While get_table_by_fqn may return columns as part of the entity, the specific getters are explicitly focused, so an agent can select based on need without confusion.
All tool names follow a consistent verb_noun pattern (get_* and search_*), use lowercase with underscores, and are uniformly structured. There are no mixed conventions or vague verbs.
With 6 tools, the server is well-scoped for a metadata browsing purpose. Each tool provides a distinct capability without redundancy or excessive granularity, fitting comfortably within the ideal range.
The server covers core table read operations (get, list, columns, owners, sample data) and a general entity search. However, it lacks direct retrieval for other metadata entities like databases, schemas, and tags, and has no create/update/delete operations, which are common in metadata management. This leaves notable gaps for a full OpenMetadata surface.
Cross-tool context for your data stack. Search, lineage, and impact across warehouse and BI tools.
Search, access, and get insights on your Amplitude data
Search, sample and query open reproducible datasets published as immutable Parquet with schemas.
Software component catalog: search your org's services, docs, APIs, dependencies, and ownership.
