Tableau Graphql MCP vs Kibana
A side-by-side look at the Tableau Graphql MCP and Kibana MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Tableau Graphql MCP for data visualization work as a local process; choose Kibana for data visualization as a local process. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose Tableau Graphql MCP when
- You need dedicated capabilities in the Data Visualization domain.
- You prefer a local stdio subprocess transport.
- You have the keys it needs:
TABLEAU_SERVER, TABLEAU_SITE_CONTENT_URL, TABLEAU_PAT_NAME, TABLEAU_PAT_SECRET, TABLEAU_AUTH_TOKEN, TABLEAU_COOKIE, TABLEAU_TIMEOUT, TABLEAU_API_VERSION. - You want tools like
graphql_query, introspect_schema, lineage_examples.
Choose Kibana when
- You need dedicated capabilities in the Data Visualization domain.
- You prefer a local stdio subprocess transport.
- Its auth model fits you: API key required.
- You have the keys it needs:
KIBANA_URL, KIBANA_API_KEY, KIBANA_USERNAME, KIBANA_PASSWORD, KIBANA_COOKIES. - You want tools like
get_status, execute_kb_api, search_kibana_api_paths.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Data Visualization | Data Visualization |
| Quality signal | 57/100 · Good | 69/100 · Great |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | Not declared | API key required |
| Pricing | Not declared | Free |
| Required env vars | TABLEAU_SERVERTABLEAU_SITE_CONTENT_URLTABLEAU_PAT_NAMETABLEAU_PAT_SECRETTABLEAU_AUTH_TOKENTABLEAU_COOKIETABLEAU_TIMEOUTTABLEAU_API_VERSION | KIBANA_URLKIBANA_API_KEYKIBANA_USERNAMEKIBANA_PASSWORDKIBANA_COOKIES |
| Verified owner | Community listing | Community listing |
| GitHub stars | 1 | 84 |
| Directory activity | 2 views 0 installs 0 upvotes | 4 views 0 installs 0 upvotes |
| Tools | 7 | 16 |
| Full listing | View Tableau Graphql MCP | View Kibana |
Tools & capabilities
Tableau Graphql MCP tools 7
graphql_queryRun ANY read-only GraphQL query against the Tableau Metadata API. This is the general-purpose tool; use it for any lineage question. Returns {"data": ..., "errors": ...}. The Metadata API is a GraphQL graph of Tableau content (workbooks, sheets, dashboards, datasources, fields) and, with the Data Management add-on, physical assets (databases, tables, columns) and their upstream/downstream lineage. How to write a correct query: - Filters are EXACT and case-sensitive: `filter: {name: "X"}` or `filter: {nameWithin: ["X","Y"]}` (nameWithin is the only multi/OR match; there is NO substring or regex). - Every list field has a `<name>Connection` variant with `first`/`offset`/`after` + `pageInfo` (page size max 1000). Keep one query under ~20,000 nodes; narrow filters and page. - Fields is an interface; branch with `__typename` and inline fragments (`... on ColumnField { columns { name } }`, `... on CalculatedField { formula }`). - Reach a field's owning workbook via `datasource { ... on EmbeddedDatasource { workbook { name } } }`. - `downstream*` fields (downstreamWorkbooks/Owners, external tables/columns) need Data Management (Tableau Catalog) and are often empty otherwise; then resolve via core lineage (referencedByFields -> sheets -> workbook), or just call the `where_used` tool. Entry points include: workbooks, sheets, dashboards, publishedDatasources, embeddedDatasources, fields, columnFields, calculatedFields, columns, databaseTables, customSQLTables, databases, flows, tableauUsers, dataQualityWarnings. Call `lineage_examples` for ready-made query templates and a schema cheat-sheet, or `introspect_schema` to inspect any type's exact fields. Read-only: mutation and subscription operations are rejected. If a query exceeds the ~20,000-node limit, the response is flagged with `partial_results: true` and a `warning` (it does NOT auto-page an arbitrary query) so you never mistake a truncated result for a complete one.introspect_schemaIntrospect the live Metadata API GraphQL schema (introspection is enabled). With no argument: returns every Query entry point (with its args) and the full list of type names. With `type_name` (e.g. "Column", "Workbook", "DatabaseTable", "CalculatedField"): returns that type's fields, their result types, and args, so you can write a correct query against exactly what this server exposes.lineage_examplesReturn a schema cheat-sheet and a library of curated lineage questions with their correct GraphQL queries (+ example variables). Read this before composing a `graphql_query`. Categories: impact, provenance, calc, datasource, search, inventory, governance, ownership. Pass one to filter; omit to get them all. Each example has: question, graphql, variables, notes.where_usedFind which workbooks (and published datasources) USE the given names, the common 'where is this used / impact analysis' question, resolved robustly. `names` are EXACT, case-sensitive names of any of: a Snowflake/DB column, a Tableau field or alias, or a database table. Pass several to check them in one call. Results group by workbook, showing how each matched (column / field / whole table, with schema and source table) and which worksheets use it. This uses CORE lineage (referencedByFields -> field.sheets -> workbook, and field.datasource -> workbook), so it works even without the Data Management add-on where `downstreamWorkbooks` is empty. For other shapes of question, use `graphql_query`.impact_analysisFull transitive (MULTI-HOP) downstream impact of a column, field, or table. Returns every field that directly OR indirectly depends on it, and all affected sheets, dashboards, workbooks, plus the de-duplicated set of OWNERS to notify before a change. This is the "what breaks if I change/drop this?" tool. Unlike `where_used` (one core-lineage hop), it follows the whole dependency chain — a calc built on a calc built on the column is included. `name` is exact and case-sensitive. Workbooks are derived from downstream sheets/dashboards (the flat downstreamWorkbooks edge is unreliable). If it returns nothing on a site without Data Management, the transitive lineage may not be indexed there — use `where_used` for the direct references.search_contentFind content whose NAME contains `term` (case-insensitive SUBSTRING). Use this when you only know part of a name, since every other tool and the Metadata API filter are exact-match. Searches workbooks, published datasources, and database tables by default. Pass `types` to choose from: "workbook", "datasource", "table", "field", "column". Returns matches grouped by type. It pages through content client-side, so on a very large site it scans the first ~1200 of each type and says so in `note`; once you know the exact name, prefer `graphql_query` or `where_used`.server_infoReport the connected Tableau environment: server URL, site, product & REST API version, which Metadata API endpoint is in use, the auth method, and whether external-asset (Data Management / Catalog) lineage appears available. Good first call to confirm the connection and understand what lineage depth to expect.
Kibana tools 16
get_statusGet Kibana server status with multi-space supportexecute_kb_apiExecute a custom API request for Kibana with multi-space support. RETRY SAFETY: this tool can reach any write endpoint. A POST retried after a timeout or dropped response can create a duplicate — prefer a caller-chosen stable id (or the vl_* tool for that object type, which documents the safe pattern) over letting the server auto-generate one.search_kibana_api_pathsSearch Kibana API endpoints by keywordlist_all_kibana_api_pathsList all Kibana API endpoints as a resource listget_kibana_api_detailGet details for a specific Kibana API endpointget_available_spacesGet all available Kibana spaces with current contextvl_search_saved_objectsSearch for Kibana saved objects using Elasticsearch query syntax. This is a universal tool that can search across all saved object types (dashboard, visualization, index-pattern, search, config, lens, map, tag, canvas-workpad, canvas-element, etc.). IMPORTANT: You must specify the 'types' parameter - it is required by the Kibana API. PERFORMANCE TIPS: Always use 'fields' parameter to specify only needed fields (e.g., ['title', 'description']) for faster responses. Use 'perPage' 5-20 for optimal speed. PAGINATION: To get all results, make multiple requests with incrementing 'page' numbers (page=1, page=2, etc.) until you receive fewer results than 'perPage'. Don't stop at the first page - iterate through all pages for complete data. Returns formatted saved object information including type, title, description, and timestamps.vl_get_saved_objectGet a single Kibana saved object by type and ID. This is a universal tool that can retrieve any type of saved object (dashboard, visualization, index-pattern, search, config, lens, map, tag, canvas-workpad, canvas-element, etc.) by its exact type and ID. Use this when you know the specific object you want to retrieve. PERFORMANCE: This is much faster than searching when you have the exact type and ID.vl_bulk_delete_saved_objectsBulk delete multiple Kibana saved objects by type and ID. This is a destructive operation that permanently removes saved objects (dashboard, visualization, index-pattern, search, config, lens, map, tag, canvas-workpad, canvas-element, etc.). WARNING: Deleted objects cannot be recovered. Use with caution. IMPORTANT: Objects that exist in multiple namespaces require the 'force' parameter to be deleted.vl_create_saved_objectCreate a new Kibana saved object (dashboard, visualization, index-pattern, search, config, lens, map, tag, canvas-workpad, canvas-element, etc.). This is a universal tool that can create any type of saved object by specifying the type and attributes. Each object type has specific attribute requirements. IMPORTANT: The 'title' field is required for most object types. Complex fields like panelsJSON, visState should be JSON strings.vl_update_saved_objectUpdate a single Kibana saved object by type and ID. This performs a partial update - only the specified attributes will be changed, other attributes remain unchanged. Supports all saved object types (dashboard, visualization, index-pattern, search, config, lens, map, tag, canvas-workpad, canvas-element, etc.). IMPORTANT: Use version parameter for optimistic concurrency control to prevent conflicts.vl_bulk_update_saved_objectsUpdate multiple Kibana saved objects in a single operation. Each object can be of different types and will be partially updated (only specified attributes changed). Supports all saved object types (dashboard, visualization, index-pattern, search, config, lens, map, tag, canvas-workpad, canvas-element, etc.). PERFORMANCE: More efficient than multiple single updates. Each object can have individual version control.- +4 more on the listing page
Ready-to-paste client configs
Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
Tableau Graphql MCP
{
"mcpServers": {
"tableau-graphql-mcp": {
"command": "uvx",
"args": [
"tableau-graphql-mcp"
],
"env": {
"TABLEAU_SERVER": "YOUR_TABLEAU_SERVER_HERE",
"TABLEAU_SITE_CONTENT_URL": "YOUR_TABLEAU_SITE_CONTENT_URL_HERE",
"TABLEAU_PAT_NAME": "YOUR_TABLEAU_PAT_NAME_HERE",
"TABLEAU_PAT_SECRET": "YOUR_TABLEAU_PAT_SECRET_HERE",
"TABLEAU_AUTH_TOKEN": "YOUR_TABLEAU_AUTH_TOKEN_HERE",
"TABLEAU_COOKIE": "YOUR_TABLEAU_COOKIE_HERE",
"TABLEAU_TIMEOUT": "YOUR_TABLEAU_TIMEOUT_HERE",
"TABLEAU_API_VERSION": "YOUR_TABLEAU_API_VERSION_HERE"
}
}
}
}
Kibana
{
"mcpServers": {
"kibana": {
"command": "npx",
"args": [
"-y",
"@tocharianou/mcp-server-kibana"
],
"env": {
"KIBANA_URL": "YOUR_KIBANA_URL_HERE",
"KIBANA_API_KEY": "YOUR_KIBANA_API_KEY_HERE",
"KIBANA_USERNAME": "YOUR_KIBANA_USERNAME_HERE",
"KIBANA_PASSWORD": "YOUR_KIBANA_PASSWORD_HERE",
"KIBANA_COOKIES": "YOUR_KIBANA_COOKIES_HERE"
}
}
}
}
Frequently asked questions
Tableau Graphql MCP is categorized under Data Visualization and uses a local stdio subprocess. Kibana belongs to Data Visualization and uses a local stdio subprocess. Pick Tableau Graphql MCP for data visualization work and Kibana for data visualization.
Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.
Tableau Graphql MCP has no declared pricing — check the project's own site. Kibana is listed as free. Auth: api key required. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.
Yes. MCP clients support multiple servers: add tableau-graphql-mcp and kibana as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Tableau Graphql MCP has a quality signal of 57/100 (Good) with 2 views, 0 installs and 1 GitHub stars. Kibana has 69/100 (Great) with 4 views, 0 installs and 84 GitHub stars.