Thin MCP server for GrowthBook — skill loader + authenticated API passthrough
Nothing to run from here
Vilsem for Power BI is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
99/100
trust score
20
tools declared
local
runs on your machine
—
calls last 7d
What it does
Author custom Power BI visuals on your live Desktop model: preview, self-review, commit to PBIP.
Quickstart
Install it the way its author documents:
1. Download vilsem-mcp-0.9.2.mcpb and open it in Claude Desktop or another client that installs MCP bundles (.mcpb)
2. Its sha256 is 42ecdc46274e0bf5d8ac61a61a9f6129686cf6b36b02530077dc59e164089f32
The full guide: https://github.com/bcsnpc/vilsem-mcp/releases/download/v0.9.2/vilsem-mcp-0.9.2.mcpb
Publishernot claimed
BCAll 1 server
bcsnpc1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Vilsem for Power BI as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Install it the way its author documents:
1. Download vilsem-mcp-0.9.2.mcpb and open it in Claude Desktop or another client that installs MCP bundles (.mcpb)
2. Its sha256 is 42ecdc46274e0bf5d8ac61a61a9f6129686cf6b36b02530077dc59e164089f32
The full guide: https://github.com/bcsnpc/vilsem-mcp/releases/download/v0.9.2/vilsem-mcp-0.9.2.mcpb
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
Return the Vilsem playbook the agent must follow before building or editing visuals. Call with no arguments first (compact core + index), then request sections such as 9a or cookbook:sankey when needed. Read-only.
No parameter schema on file.
Get bounded PNG/JPEG image statistics only: palette/background/light-dark/aspect ratio and approximate text/gridline evidence. No ML/OCR or inferred fields/data. image is a local path or PNG/JPEG data URI.
No parameter schema on file.
Render with real model data at the reference aspect ratio and return reference/render side by side, critique and a structural diff. The calling agent may supply reference_structure; semantic reference properties otherwise remain unknown. Writes no report.
No parameter schema on file.
Connect read-only to an existing model. Prefer source.kind="report" with reportDir to follow definition.pbir: byPath matches the open Desktop model or returns offline schema-only TMDL; byConnection/Fabric/SSAS are disabled in this local-only release; VILSEM_ENABLE_ONLINE=1 is an unsupported…
No parameter schema on file.
Read model context without writes. Default detail=summary omits measure DAX and relationship graph; ask for full to understand calculations and join paths. Columns include exact DAX cardinality, BLANK share and numeric/date min/max, plus up to10 distinct samples and hidden/key flags. On large…
No parameter schema on file.
Execute a read-only DAX EVALUATE table query against a connected model. Returns at most maxRows rows, default 200. Use it to inspect data and verify visual bindings; this tool does not expose XMLA commands or persistent model changes.
No parameter schema on file.
List shipped and saved user templates. By default returns a compact list (id, name, description, slots, source). Pass id for one complete template (slots, params, template, exampleSpec), search to filter by text, or full:true for every template in full (very large, about 550 KB).…
No parameter schema on file.
Save a validated complete spec to the OS user template library, or VILSEM_TEMPLATES_DIR. Names are lowercase slugs; existing entries are refused. This does not write a report or model.
No parameter schema on file.
Delete one named user-library template only. Shipped templates, reports and models are never deleted.
No parameter schema on file.
Resolve a Vilsem spec without data. With spec.measures, connectionId is required: validates schema references, cycles and scalar DAX using the connected engine. Run before preview_visual.
No parameter schema on file.
Explain a Vilsem custom visual spec, its field bindings, resolved empty-data ECharts option and exact DAX query before preview or commit. Does not inspect or modify native visuals or model objects.
No parameter schema on file.
motion:auto captures actual animation in an installed fresh network-blocked headless browser when available; motion:states uses discrete timeline states, and motion:browser requires a browser. Optional frames (2..12) also returns a timeline-state contact sheet. Validate a Vilsem spec, query actual…
No parameter schema on file.
Compare1..4 candidate specs using ONE identical bound-data query; returns one labelled2x2 PNG and per-candidate critique. Bindings and visual-scoped measures must be shared, so design differences cannot silently change the numbers. Use this to choose between approaches before committing.
No parameter schema on file.
Read every vilsem Renderer visual across report pages from PBIR, with summary, bindings, version, layout and optional live thumbnail. Native visuals are skipped. Defaults to live thumbnails; pass thumbnails:false for metadata-only discovery. No separate manifest is used.
No parameter schema on file.
Read a saved vilsem visual: migrated full spec, original-version provenance, field bindings, layout, scoped measures, separate format-pane overrides and current live PNG. Uses connectionId or connects through definition.pbir. Never reads native visuals.
No parameter schema on file.
Read-only comparison against one saved vilsem visual: JSON Patch diff and before/after live PNGs with critique. This writes no files. Run before replacing an existing design.
No parameter schema on file.
Apply RFC6902 JSON Patch to the stored vilsem spec. Validates and previews before writing; returns diff and before/after PNGs. Defaults dryRun:true. Preserves manual format-pane objects unless resetFormatting:true; renderer identity/prototype/version paths are refused. Optional etag protects a…
No parameter schema on file.
Read existing PBIR pages and visual names, types and positions so you can choose a page and avoid overlap. This tool does not edit or validate native visuals, slicers, bookmarks, filters or report themes.
No parameter schema on file.
Add one Vilsem Renderer visual to one existing PBIR page using @vilsem/core. Existing visual names are refused; the only additional changes are missing renderer resources and registration. Native visuals, slicers, bookmarks, filters, themes and model objects are not edited. After committing, relay…
No parameter schema on file.
Validate only Vilsem Renderer specs, reader versions and known container structure. Other official2.x declarations must fit the complete bundled2.7 contract and return an explicit compatibility warning; full validation of their declared schema is not claimed. Unknown fields are refused.…
No parameter schema on file.
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Vilsem for Power BI or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 99 / 100
Release 0.9.2 · scanned 14 Nov 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score99
Findings10 threat · 0 capability
Capabilityminimal
Coveragesource
Verificationrepo
Surface digest2dc22d3bf39daa3966da07121ef3ae7218597d0cc75600bd6ac9471b4c82a657
Score vectorthreat 100 → client 99
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | minimal | capability blast radius (minimal) — client exposure if the model is manipulated | −0 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfacenot available
Implementation sourceread
Package metadataread
Live transportnot available
No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. minimal is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| No per-tool rows for this release — see the note below. | ||
No tool surface was enumerated, so there is nothing to attribute a capability to.
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digest2dc22d3bf39daa39
Scanned2026-11-14
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
It installs from its repository rather than from a versioned package, so the command cannot be pinned to a release. The history below is for reading; the current release on file is 0.9.2.
0.9.2
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Vilsem for Power BI can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.