Markmap MCP Server vs Tableau Workbook Auditor
A side-by-side look at the Markmap MCP Server and Tableau Workbook Auditor MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Markmap MCP Server for data visualization work as a local process; choose Tableau Workbook Auditor 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 Markmap MCP Server when
- You need dedicated capabilities in the Data Visualization domain.
- You prefer a local stdio subprocess transport.
- Its auth model fits you: No auth required.
- You want tools like
markdown_to_mindmap, list_mindmaps, get_mindmap.
Choose Tableau Workbook Auditor when
- You need dedicated capabilities in the Data Visualization domain.
- You prefer a local stdio subprocess transport.
- You want tools like
analyze_workbook, list_calculated_fields, get_field.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Data Visualization | Data Visualization |
| Quality signal | 68/100 · Great | 60/100 · Good |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | No auth required | Not declared |
| Pricing | Free | Not declared |
| Required env vars | None listed | None listed |
| Verified owner | Community listing | Community listing |
| GitHub stars | 289 | 7 |
| Directory activity | 5 views 0 installs 0 upvotes | 2 views 0 installs 0 upvotes |
| Tools | 4 | 11 |
| Full listing | View Markmap MCP Server | View Tableau Workbook Auditor |
Tools & capabilities
Markmap MCP Server tools 4
markdown_to_mindmapConvert structured Markdown (headings # and nested lists -) into an interactive mind map HTML file, with optional server-side PNG/JPG/SVG export. Use when the user wants a visual mind map/outline of structured content (architecture, plans, notes, hierarchies), or asks to visualize / mindmap / diagram. Do not use for flat unstructured text (restructure first), or to list/read existing outputs (use list_mindmaps / get_mindmap). Behavior: - WRITES files under the configured output dir. HTML is always written; image formats write an extra file. Reusing filename overwrites. - html is fast (<1s). png/svg/jpg launch headless Chromium via Playwright (5–15s; requires: npm install playwright && npx playwright install chromium). - Local only — no external APIs or third-party keys. Open mode=never: The server never opens the browser. - Offline=false (server config). Response: - JSON {"htmlFilePath":"<path>","filePath":"<path>"} — htmlFilePath is always the HTML source; filePath is the primary artifact (HTML or image). - Return mode=path: Paths JSON only — no inline content. - Errors: isError:true with {"error","message"}.list_mindmapsList markmap* files (html/png/jpg/jpeg/svg) in the output directory, newest first. Read-only — no side effects. Missing/empty dirs return {"files":[]}. Returns: {"outputDir","files":[{"name","filePath","size","mtimeMs","mtime"}]} (mtime is ISO 8601). Use before get_mindmap to discover paths, or before cleanup_mindmaps to preview targets. Not for generating new mind maps (use markdown_to_mindmap).get_mindmapRetrieve a generated mind map file by absolute path. Read-only — no side effects. Only paths inside the configured output directory are allowed (path traversal denied). Returns JSON {"filePath","mimeType","size"}. For text/html or image/svg+xml under 200KB, also appends a text content block. PNG/JPG return metadata only (no image block) — re-export via markdown_to_mindmap with format=png|jpg if the agent needs pixels. On error: isError:true with {"error":"Failed to retrieve mind map","message"}. Use list_mindmaps first to obtain a valid filePath. Prefer this over regenerating when the file already exists.cleanup_mindmapsPermanently delete markmap* files from the output directory. DESTRUCTIVE and irreversible when dryRun is false. dryRun defaults to false — omitting it WILL delete. Always call once with dryRun=true to preview, then again with dryRun=false to commit. Prefer list_mindmaps beforehand. Returns {"deleted":["<path>",...],"kept":<n>}; dryRun responses also include dryRun:true and do not delete. Use instead of manual file deletion when pruning old generated mind maps.
Tableau Workbook Auditor tools 11
analyze_workbookParse a local Tableau workbook (.twbx or .twb) and return an overview: field counts, datasources, calculated-field names by type, parameter names, and raw fields. Parsing happens locally; the file is never uploaded. Start here, then use the other tools for details.list_calculated_fieldsList every calculated field in the workbook with its formula, type (calculated / LOD / table calc), datasource, and what it directly depends on. Optionally filter by a case-insensitive substring of the field name or formula.get_fieldFull detail for a single field by name (brackets optional, case-insensitive): formula, type, direct dependencies, and every field that directly uses it.trace_dependenciesTrace what a field is built from (upstream, recursive tree down to raw columns and parameters) and everything that would be affected if it changed (downstream, transitive). The impact-analysis tool: use before editing a calculation.list_parametersList every parameter in the workbook: current value, datatype, allowed values, and which calculated fields use each one.get_lineage_graphThe complete dependency graph as JSON: one node per field/parameter (with type) and one directed edge per dependency (source feeds target). Suitable for rendering or graph analysis.list_sql_queriesExtract every SQL statement the workbook contains: Custom SQL relations (with the full query text), Initial SQL run when a connection opens, stored-procedure references with their parameters, and RAWSQL_* calculated fields. Each entry names the datasource and the database connection (class, server, dbname) it targets. Note: queries Tableau auto-generates at runtime for live connections are not stored in the file, so they cannot be extracted.list_filtersEvery filter in the workbook, deduplicated across worksheets: the field it acts on (caption-resolved), filter kind (categorical / quantitative / relative-date), whether it is a context filter, which worksheets use it, selected member values when stored, and quantitative ranges. Includes a by_worksheet grouping and the distinct list of fields driving any filter. Data-source filters are marked "(data source filter)".list_worksheetsEvery worksheet in the workbook with the fields it uses (caption-resolved, from its datasource dependencies) and the filters it applies (field, kind, context status). The per-sheet view of the workbook: use it to answer "what does this sheet depend on?" or "where is this field actually displayed?".diff_workbooksSemantic diff between two Tableau workbooks: calculations added, removed, renamed or edited (with the downstream fields each edit affects), plus changed parameters, filters, worksheets, dashboards, data sources and stored SQL. Formula reformatting is ignored, and a field that disappears while an identical formula appears under a new name is reported as a rename. Use this for release notes, code review of a workbook change, or answering "what changed and what does it break?".audit_workbookFind what is wrong with a workbook: fields and parameters nothing uses (each with a confidence level and the reason), duplicate calculations (identical formulas under different names, and the more dangerous same-name-different-formula case), and performance findings (heavy LODs, nested calculations, deep calculation chains, non-fixed dashboard sizing, live connections, and more). Use it before a cleanup, a migration, or a workbook review. Unused fields are reported with confidence rather than as certainties, because a field can be referenced in ways a file cannot show.
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.
Markmap MCP Server
{
"mcpServers": {
"jinzcdev-markmap-mcp-server": {
"command": "npx",
"args": [
"-y",
"@jinzcdev/markmap-mcp-server"
]
}
}
}
Tableau Workbook Auditor
{
"mcpServers": {
"tableau-workbook-auditor": {
"command": "npx",
"args": [
"-y",
"tableau-lineage-mcp"
]
}
}
}
Frequently asked questions
Markmap MCP Server is categorized under Data Visualization and uses a local stdio subprocess. Tableau Workbook Auditor belongs to Data Visualization and uses a local stdio subprocess. Pick Markmap MCP Server for data visualization work and Tableau Workbook Auditor 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.
Markmap MCP Server is listed as free. Auth: no auth required. Tableau Workbook Auditor has no declared pricing — check the project's own site. 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 jinzcdev-markmap-mcp-server and tableau-workbook-auditor as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Markmap MCP Server has a quality signal of 68/100 (Great) with 5 views, 0 installs and 289 GitHub stars. Tableau Workbook Auditor has 60/100 (Good) with 2 views, 0 installs and 7 GitHub stars.