io.github.henriquepe/lousa
NPM · LOUSA
A whiteboard where AI agents draw their explanations as hand-drawn animated diagrams
Available components
Last scanned (16 hours ago)
Scores higher than 61% of npm servers
Category Design and Media
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security94
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- No install/post-install scripts declared.Pass
- 5 of 5 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (AGPL-3.0-only).Pass
- Actively maintained (last published 95 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability71
- AI-judged instruction clarity (good).Pass
- Tool/resource definitions use about 665 tokens (~110/item across 6 items; 6 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage86
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 57% of tool parameters carry a description.Partial
Tool Safety75
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "delete_board" implies "delete" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
- An AI judge read all 6 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Checks we ran (16)
- Malware scan
- Known CVEs
- Install scripts
- Dependency health
- Source repository
- Provenance
- License
- Maintenance
- Security disclosure
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Does not apply to this package (2)
- Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
- Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
The score does not measure everything. What the score does not measure →
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 29 Oct 26 0
- Stability: 0.97 → pass security
- 28 Oct 26 0
- Stability: pass → 0.97 functional
- 16 Oct 26 0
- Stability: 0.97 → pass security
- 15 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.
- 12 Oct 26 +16
- Malware scan: unverified → pass ▲ security
- Security disclosure: unverified → fail ▼ functional
- 11 Oct 26 −15
- Malware scan: pass → unverified ▼ security
- Security disclosure: fail → unverified ▼ functional
- 3 Oct 26 −2
- Stability: pass → 0.80 functional
- 2 Oct 26 79
- Stability: 0.97 → pass security
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 6 Nov 2026 · Analysed npm/lousa@0.1.1
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | npm |
Background: How many MCP packages publish verified provenance →
Dependencies 5 packages
| Packages resolved | 5 |
|---|---|
| Stale | 5 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
create_board ~317
Creates a board (a hand-drawn visual explanation) on Lousa and returns {id, url}. Open/share the url with the user — the drawing animates in as if sketched live. You author the drawing: think like a senior engineer sketching on a whiteboard. Coordinates: x grows right, y grows down; design within ~1600x1000 (exceed if needed). Guidelines: flow left-to-right or top-to-bottom; generous spacing (>=60 between shapes); few colors with meaning (blue components, green happy path, red errors/bottlenecks, gray context, purple storage); short labels; title via type=text size=32; caveats as type=note; prefer arrows with from/to (ids). cylinder = database/storage, diamond = decision. Label language = the conversation's language. The viewer renders with a hand-drawn stroke and animates elements in sequence.
| Name | Type | Req | Description |
|---|---|---|---|
| narration | string | – | 1-2 sentences about what the drawing shows (shown as a card in the viewer). |
| requests | array | – | The user request(s) that originated the board. |
| scene | array | yes | The complete scene, in drawing order (titles and shapes before the arrows that connect them). |
| title | string | yes | Short board title. |
| ttlHours | number | – | Hours until the board expires and is deleted (default 12; 0 = permanent; max 720). Expiry slides on every update. Use 0 only if the user asks to keep the board. |
No output schema declared.
No examples provided.
delete_board ~20
Deletes a board permanently.
| Name | Type | Req | Description |
|---|---|---|---|
| id | string | yes | – |
No output schema declared.
No examples provided.
get_board ~30
Reads a full board (title, narration, scene, requests, selection).
| Name | Type | Req | Description |
|---|---|---|---|
| id | string | yes | – |
No output schema declared.
No examples provided.
get_selection ~86
Returns what the user selected in the viewer (click toggles; Esc clears): {selection: ids, selectionAt, elements}. Use when the user references "what I selected" / "this part" — those elements are the target of the request. An old selectionAt may be residue from a previous request; when in doubt, confirm the target.
| Name | Type | Req | Description |
|---|---|---|---|
| id | string | yes | – |
No output schema declared.
No examples provided.
list_boards ~24
Lists existing boards (id, title, narration, element count, dates).
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
update_board ~188
Updates an existing board. The scene you send REPLACES the current one entirely: keep unchanged elements byte-identical (same id and fields) — the viewer animates only what changed, live in the user's open tab; to remove an element, omit it. If the user's request references something they pointed at ("what I selected", "this part"), call get_selection first to learn the target.
| Name | Type | Req | Description |
|---|---|---|---|
| appendRequest | string | – | The user's follow-up request, for the board history. |
| id | string | yes | – |
| narration | string | – | – |
| scene | array | – | The complete scene, in drawing order (titles and shapes before the arrows that connect them). |
| title | string | – | – |
| ttlHours | number | – | Changes expiry (default 12h since last update; 0 = permanent). Use 0 when the user asks to keep/pin the board. |
No output schema declared.
No examples provided.
How do I install the io.github.henriquepe/lousa MCP server?
io.github.henriquepe/lousa runs locally as an npm package, launched with npx -y lousa mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · lousa
claude mcp add henriquepe-lousa -- npx -y lousa mcp
What is the io.github.henriquepe/lousa MCP server?
io.github.henriquepe/lousa is an MCP server listed in the public MCP registry as io.github.henriquepe/lousa. A whiteboard where AI agents draw their explanations as hand-drawn animated diagrams. This page covers its npm package (lousa).
Is the io.github.henriquepe/lousa MCP server safe to use?
io.github.henriquepe/lousa scores 79 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 6 November 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the io.github.henriquepe/lousa MCP server expose?
io.github.henriquepe/lousa exposes 6 tools: create_board, update_board, get_board, list_boards, get_selection, delete_board. Their descriptions and schemas cost roughly 665 tokens of context every time the server is loaded.
Is the io.github.henriquepe/lousa MCP server still maintained?
io.github.henriquepe/lousa is still listed as active in the MCP registry. We last reached this channel on 6 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the io.github.henriquepe/lousa MCP server under?
io.github.henriquepe/lousa declares the AGPL-3.0-only licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.
What did VerifyMCP test on the io.github.henriquepe/lousa MCP server?
VerifyMCP ran 16 checks on io.github.henriquepe/lousa, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.