Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Semiotic

NPM · SEMIOTIC · 2 COMPONENTS

Verified React chart generation: select, validate, repair, render, and inspect charts through MCP.

+19 this week 88 Trust /100

Last scanned (12 hours ago)

Scores higher than 92% of npm servers

Category Design and Media

Trust breakdown (7 categories)

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 Security99
  • 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
  • 9 of 97 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency100
  • Source repository is publicly reachable at the declared URL. View diagnostics → Pass
  • Cryptographically verified build provenance (signed, bound to nteract/semiotic). View diagnostics → Pass
  • Clear OSI-approved license (Apache-2.0).Pass
  • Actively maintained (last published 7 days ago).Pass
  • Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability78
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 5092 tokens (~145/item across 35 items; 24 tools + 11 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management47
  • Stability observed for 14 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage95
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 84% of tool parameters carry a description.Partial
  • Structured output schemas are declared (33% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 24 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 25 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
  • Supports UI / widget rendering.Pass
What we tested

Checks we ran (17)

  • 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
  • Capabilities

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 →

Changelog

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.

  • 6 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

  • 5 Nov 26 0
    • Dependency health: 0.80 → 0.96 ▲ functional
  • 4 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.

  • 2 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

  • 31 Oct 26 +16
    • Malware scan: unverified → pass ▲ security
  • 30 Oct 26 −15
    • Malware scan: pass → unverified ▼ security
    • Package version: 3.13.1 → 3.13.3 functional
  • 29 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

  • 27 Oct 26 +16
    • Malware scan: unverified → pass ▲ security
Diagnostics

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/semiotic@3.13.3

Provenance Verified

A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.

Result Verified
Ecosystem npm
Reason Verified
Discovered via Registry attestation endpoint
Source repo nteract/semiotic
Certificate issuer https://token.actions.githubusercontent.com
Certificate SAN https://github.com/nteract/semiotic/.github/workflows/release.yml@refs/tags/v3.13.3
Rekor log index 3573267023
Predicate type SLSA build provenance https://slsa.dev/provenance/v1
Subject digest sha512:8ee761bbf0fc8819110581647a5d6d82b8e4b09adc27fa39fb30025fa5a4eb999fe50379bd437d187cad7c22eb880fd5f823bb2af936b7b342f01305c

Background: How many MCP packages publish verified provenance →

Dependencies 97 packages
Packages resolved 97
Stale 9
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 24 exposed · ~4,827 tokens

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 →

Tool Tokens
applyTheme ~121

Get usage instructions for a named Semiotic theme preset. Returns ThemeProvider examples, CSS custom properties, and design token export patterns. Available themes: light, dark, high-contrast, pastels, pastels-dark, bi-tool, bi-tool-dark, italian, italian-dark, tufte, tufte-dark, journalist, journalist-dark, playful, playful-dark, carbon, carbon-dark.

NameTypeReqDescription
namestring–Theme preset name, e.g. 'tufte', 'pastels-dark', 'bi-tool'. Omit to list all available themes.

No output schema declared.

No examples provided.

auditAccessibility ~345

Audit a Semiotic chart configuration against the Chartability (POUR-CAF) accessibility framework — Perceivable, Operable, Understandable, Robust, Compromising, Assistive, Flexible. Statically grades the config (no DOM/AT): credits the built-ins every HOC ships (keyboard nav, focus ring, skip link, screen-reader data table, reduced-motion + forced-colors, shareable state), flags author-actionable gaps (missing title/description/summary, low contrast, small text, color-only encoding, undescribed trends, data density), and routes everything that needs real assistive-technology testing to a 'manual' item. Returns a per-principle report with the 14 critical heuristics marked. Pass inChartContainer=true to credit data-download/share affordances. Pair with manual NVDA/JAWS/VoiceOver testing — Chartability is not a pass/fail certification.

NameTypeReqDescription
componentstringyesChart component name, e.g. 'LineChart'
describeboolean–True if ChartContainer's describe option (auto-generated L1–L3 description via describeChart) is enabled — passes the 'features described' heuristic.
inChartContainerboolean–True if the chart is (or will be) wrapped in a ChartContainer exposing data-download/copy-config actions.
navigableboolean–True if ChartContainer's navigable option (structured navigation tree via buildNavigationTree) is enabled — passes the 'navigable structure' heuristic.
propsobject–Chart props object, e.g. { data: [...], xAccessor: 'x', title: '...' }.

No output schema declared.

No examples provided.

auditArtifact ~183

Evaluate a chart and its explicit artifact contract under a named policy. The tool audits only supplied claims, evidence, source identity, review state, and time state; missing facts remain missing or unknown. Results are capped and report truncation explicitly.

NameTypeReqDescription
componentstringyesSemiotic component name.
contractobjectyesComplete explicit artifact contract. Validate against semiotic://artifact-contract-schema; omitted source, review, and time facts stay omitted or explicitly unknown.
dataarray–Optional explicit row data overriding props.data.
exceptionsarray––
nowstring–Explicit reference clock for review, freshness, and expiry checks. Use an ISO 8601 timestamp.
policyIdstringyesExplicit built-in policy identifier used for this operation.
propsobject–Chart props/config. Data may be supplied here or separately.
NameTypeReqDescription
alternativesarray––
claimSummaryobject––
contractValidationobjectyes–
manualChecksarray––
obligationSummaryobject––
obligationsarray––
policyobjectyes–
repairsarray––
selectedRepresentationobject––
statusstringyes–
surfaceVersionstringyes–
temporalSummaryobject––
truncatedobject––

No examples provided.

auditMobileVisualization ~183

Audit a Semiotic chart configuration for mobile visualization risks. Use before generating phone-sized charts or when adapting a desktop chart to mobile. Flags fixed desktop widths, rough mark-density overload, hover-only detail, small touch targets, complex gestures without controls, legend dependence, annotation overload, and missing mobile transformation hints. Static analysis only: still verify rendered charts at phone widths.

NameTypeReqDescription
componentstringyesChart component name, e.g. 'LineChart', 'Scatterplot', or 'BarChart'.
inChartContainerboolean–Whether the chart is wrapped in ChartContainer or an equivalent summary/control surface.
propsobject–Chart props/config to audit.
targetSizeinteger–Desired comfortable touch target size in CSS pixels. Defaults to 44.
viewportWidthinteger–Mobile viewport width in CSS pixels. Defaults to 390.

No output schema declared.

No examples provided.

diagnoseConfig ~186

Diagnose a Semiotic chart configuration for common problems (empty data, bad dimensions, missing accessors, wrong data shape, color contrast issues, etc). Pass usageMode='push' for ref-based React HOCs that intentionally omit data; omit usageMode or pass 'static' for renderChart/MCP/server configs where data is required. Checks WCAG color contrast ratios and suggests COLOR_BLIND_SAFE_CATEGORICAL for accessibility. Returns a human-readable diagnostic report with actionable fixes.

NameTypeReqDescription
componentstringyesChart component name, e.g. 'LineChart'
propsobject–Chart props object, e.g. { data: [...], xAccessor: 'x' }.
usageModestring–Validation mode. Use 'push' for ref-based React HOCs that omit data; use 'static' or omit for renderChart/MCP/static data configs.

No output schema declared.

No examples provided.

evaluateChart ~211

Evaluate a Semiotic chart through one deterministic quality pass: numeric data contracts, configuration and representation/deception checks, and static Chartability accessibility heuristics. Returns the independent audit reports plus a severity-ranked findings list and notification feed. Pass data separately when it should override props.data; use inChartContainer, describe, or navigable to describe the intended accessibility wrapper. This is static analysis and does not replace manual assistive-technology testing or render evidence.

NameTypeReqDescription
componentstringyesChart component name, e.g. 'LineChart'.
dataarray–Optional explicit dataset. When supplied, this is used as the effective props.data for evaluation.
describeboolean–Whether ChartContainer's generated description is enabled.
inChartContainerboolean–Whether the chart will be wrapped in ChartContainer or an equivalent control surface.
navigableboolean–Whether ChartContainer's structured navigation tree is enabled.
propsobject–Chart props/config, including accessors and optional data.

No output schema declared.

No examples provided.

explainRefusal ~153

Evaluate an explicit artifact contract under a named policy and explain why publication or action is refused. Missing evidence, source, review, and time facts stay explicit rather than being guessed.

NameTypeReqDescription
componentstringyesSemiotic component name.
contractobjectyesComplete explicit artifact contract. Validate against semiotic://artifact-contract-schema; omitted source, review, and time facts stay omitted or explicitly unknown.
dataarray––
exceptionsarray––
nowstring–Explicit reference clock for review, freshness, and expiry checks. Use an ISO 8601 timestamp.
policyIdstringyesExplicit built-in policy identifier used for this operation.
propsobject––
NameTypeReqDescription
contractValidationobjectyes–
evaluationStatusstring––
explanationstring––
failuresarray––
policyobjectyes–
repairsarray––
statusstringyes–
surfaceVersionstringyes–
truncatedobject––

No examples provided.

getSchema ~80

Return the prop schema for a Semiotic chart component. Pass { component: '<name>' } to get its props, or omit component to list all available components. Components marked [renderable] can be passed to renderChart for static SVG output.

NameTypeReqDescription
componentstring–Component name, e.g. 'LineChart'. Omit to list all.

No output schema declared.

No examples provided.

groundChart ~103

Build the agent-reader grounding payload for a Semiotic chart: the layered L1–L3 natural-language description, the L4 communicative-act sentence (what the chart is asking the reader to do), and a structured navigation tree (chart → axes/series → datum). Use this to interpret a chart faithfully without pixels.

NameTypeReqDescription
componentstringyesChart component name, e.g. 'LineChart'
propsobjectyesThe full chart props including data
NameTypeReqDescription
componentstringyes–
descriptionobjectyes–
intentobject––
physicsobject––
structureobject––
textstringyes–

No examples provided.

interrogateChart ~99

Conversational interrogation of a Semiotic chart. Extract a statistical summary and answer natural language questions about the data, trends, and outliers. Returns a summary and guidance for an AI to generate a textual answer and visual annotations.

NameTypeReqDescription
componentstringyesChart component name, e.g. 'LineChart'
propsobjectyesThe full chart props including data
querystring–A natural language question about the chart data

No output schema declared.

No examples provided.

proposeChartVariants ~271

Propose and score chart variants for a selected Semiotic component. Uses the capability registry plus heuristic variant discovery: registered variants, conservative transforms, and same-intent cross-family alternatives. Returns ranked proposals with fit/novelty/risk scores, rationale, and ready-to-use props. Use after suggestCharts when an agent wants to actively explore variants rather than stop at the first chart recommendation.

NameTypeReqDescription
audienceobject–Audience profile — familiarity, adoption targets, exposure level, and reception modality.
componentstringyesBase chart component to vary, e.g. 'LineChart', 'BarChart', or 'BoxPlot'.
dataarray–Row data to profile. Overrides props.data when present.
fieldRolesobject–Per-field semantic or exact encoding-role hints used before chart ranking.
identifiersarray–Fields that identify records and must not be used as visual encodings or measures.
intent––Ranking intent(s), e.g. trend, distribution, rank, compare-categories, composition-over-time.
maxResultsinteger–Cap on proposals returned (default 8).
propsobject–Existing chart props. If props.data is present it is profiled; network/hierarchy/geo object data can be passed here as raw input.

No output schema declared.

No examples provided.

recommendRepresentation ~192

Recommend chart and non-chart outcomes from explicit data and an explicit artifact contract. Evidence, source, review, and time facts are never synthesized. The named policy can recommend waiting, collecting data, or making no claim instead of forcing a chart.

NameTypeReqDescription
contractobjectyesComplete explicit artifact contract. Validate against semiotic://artifact-contract-schema; omitted source, review, and time facts stay omitted or explicitly unknown.
dataarray–Explicit row data; omit only when contract evidence is sufficient.
exceptionsarray––
identifiersarray––
intent–––
maxChartCandidatesinteger––
nowstring–Explicit reference clock for review, freshness, and expiry checks. Use an ISO 8601 timestamp.
policyIdstringyesExplicit built-in policy identifier used for this operation.
preferredComponentstring–Optional Semiotic component preference.
NameTypeReqDescription
alternativesarray––
contractValidationobjectyes–
policyobjectyes–
reasonsarray––
rejectedarray––
selectedobject––
statusstringyes–
surfaceVersionstringyes–
truncatedobject––

No examples provided.

renderChart ~553

Render a Semiotic chart to static SVG or PNG. This is a static snapshot path: props must include data immediately, and ref/push-mode charts cannot be rendered through this tool. Returns SVG text by default or an image/png artifact when format='png', plus a "Render evidence" JSON block (mark counts by type, resolved axis domains, empty flag, annotation count, accessible name) — read the evidence instead of parsing the SVG to verify the chart actually rendered data marks. An optional explicit contract is preserved in render evidence together with its transfer status; missing contract facts are not inferred. Optionally pass theme CSS custom properties (--semiotic-bg, --semiotic-text, etc.) to style the output. PNG requires the 'sharp' package to be installed. Available components: AreaChart, BarChart, BigNumber, BoxPlot, BubbleChart, BumpChart, CalendarHeatmapRecipe, CandlestickChart, ChainReactionChart, ChordDiagram, ChoroplethMap, CirclePack, CollisionSwarmChart, ConnectedScatterplot, CrucibleChart, DependencyForestChart, DifferenceChart, DistanceCartogram, DonutChart, DotPlot, EventDropChart, FlowCircuitChart, FlowMap, ForceDirectedGraph, FunnelChart, GaltonBoardChart, GaugeChart, GauntletChart, GroupedBarChart, Heatmap, Histogram, LikertChart, LineChart, MinimapChart, MotifBraidChart, MultiAxisLineChart, OrbitDiagram, PacketFlowChart, ParallelCoordinatesRecipe, PieChart, ProcessFlowChart, ProcessSankey, ProportionalSymbolMap, QuadrantChart, RadarChart, RidgelinePlot, SankeyDiagram, Scatterplot, ScatterplotMatrix, StackedAreaChart, StackedBarChart, SwarmPlot, SwimlaneChart, TemporalHistogram, TreeDiagram, Treemap, UnitPileChart, ViolinPlot, WaterfallChart.

NameTypeReqDescription
componentstringyesChart component name, e.g. 'LineChart', 'BarChart'
contractobject–Optional explicit artifact contract. The render evidence reports whether it was preserved, invalid, or an unsupported version.
formatstring–Output format: 'svg' (default) returns SVG markup, 'png' returns image/png artifact data. PNG requires the 'sharp' package.
propsobject–Chart props object, e.g. { data: [...], xAccessor: 'x' }.
themeobject–CSS custom properties for theming, e.g. { '--semiotic-bg': '#1a1a2e', '--semiotic-text': '#ededed' }. Only --semiotic-* variables are applied.

No output schema declared.

No examples provided.

renderInteractiveChart ~388

Render a static-data Semiotic chart as a ChatGPT Apps widget. Use this after suggestCharts/getSchema/diagnoseConfig when the user wants to see an interactive chart inside ChatGPT. The server renders Semiotic to SVG and the widget adds fit, zoom, data, hover, and render-evidence controls. Available components: AreaChart, BarChart, BigNumber, BoxPlot, BubbleChart, BumpChart, CalendarHeatmapRecipe, CandlestickChart, ChainReactionChart, ChordDiagram, ChoroplethMap, CirclePack, CollisionSwarmChart, ConnectedScatterplot, CrucibleChart, DependencyForestChart, DifferenceChart, DistanceCartogram, DonutChart, DotPlot, EventDropChart, FlowCircuitChart, FlowMap, ForceDirectedGraph, FunnelChart, GaltonBoardChart, GaugeChart, GauntletChart, GroupedBarChart, Heatmap, Histogram, LikertChart, LineChart, MinimapChart, MotifBraidChart, MultiAxisLineChart, OrbitDiagram, PacketFlowChart, ParallelCoordinatesRecipe, PieChart, ProcessFlowChart, ProcessSankey, ProportionalSymbolMap, QuadrantChart, RadarChart, RidgelinePlot, SankeyDiagram, Scatterplot, ScatterplotMatrix, StackedAreaChart, StackedBarChart, SwarmPlot, SwimlaneChart, TemporalHistogram, TreeDiagram, Treemap, UnitPileChart, ViolinPlot, WaterfallChart.

NameTypeReqDescription
componentstringyesRenderable chart component name, e.g. 'LineChart', 'BarChart', 'GaugeChart'.
propsobject–Static Semiotic chart props, including data/accessors where required.
themeobject–CSS custom properties such as { '--semiotic-bg': '#fff', '--semiotic-text': '#111' }. Only --semiotic-* variables are applied.
NameTypeReqDescription
componentstringyes–
datumCountnumber|nullyes–
evidence–yes–
summarystringyes–
titlestringyes–

No examples provided.

repairArtifact ~239

Propose repairs for a chart and explicit artifact contract. By default this is proposal-only. If enabled, safe application fills missing component and configuration/data identity fields only; existing bindings are never overwritten. Mismatches require an explicit revision and claim reassessment. Source, evidence, review, approval, and time facts are never invented. Returned contracts omit evidence samples, report transfer losses, and are withheld above a 64 KiB UTF-8 cap.

NameTypeReqDescription
applySafeIdentityRepairsboolean–Fill missing identity fields only; existing mismatches require an explicit revision and claim reassessment. Defaults to false.
componentstringyesSemiotic component name.
contractobjectyesComplete explicit artifact contract. Validate against semiotic://artifact-contract-schema; omitted source, review, and time facts stay omitted or explicitly unknown.
dataarray––
exceptionsarray––
nowstring–Explicit reference clock for review, freshness, and expiry checks. Use an ISO 8601 timestamp.
policyIdstringyesExplicit built-in policy identifier used for this operation.
propsobject––
NameTypeReqDescription
afterStatusstring––
beforeStatusstring––
contractobject–Complete explicit artifact contract. Validate against semiotic://artifact-contract-schema; omitted source, review, and time facts stay omitted or explicitly unknown.
contractTransferobject––
contractValidationobjectyes–
ledgerarray––
policyobjectyes–
statusstringyes–
surfaceVersionstringyes–
truncatedobject––

No examples provided.

repairChartConfig ~152

Validate that a chart component is a sensible choice for a dataset, and if not, propose ranked alternatives that fit. Returns a structured status of ok, alternative, or unknown.

NameTypeReqDescription
componentstringyesChart component name to validate, e.g. 'PieChart'
dataarrayyesRow data — array of objects.
fieldRolesobject–Per-field semantic or exact encoding-role hints used before chart ranking.
identifiersarray–Fields that identify records and must not be used as visual encodings or measures.
intent––User intent — informs ranking of alternatives when the chart doesn't fit.
maxAlternativesinteger–Cap on alternatives returned (default 3).
NameTypeReqDescription
alternativesarray––
componentstringyes–
profileobjectyes–
reasonstring––
repairsarray––
statusstringyes–

No examples provided.

reportIssue ~111

Generate a GitHub issue URL for Semiotic bug reports or feature requests. Returns a URL the user can open to submit. For rendering bugs, include the component name, props summary, and any diagnoseConfig output in the body.

NameTypeReqDescription
bodystring–Issue body with details, reproduction steps, diagnoseConfig output
labels––GitHub labels, e.g. ['bug'] or 'bug'
titlestringyesIssue title, e.g. 'Bug: BarChart tooltip shows undefined'

No output schema declared.

No examples provided.

suggestChart ~192

Lightweight heuristic chart recommender for a small data sample (1-5 rows) with capability filtering (push API, linked hover, SSR, selection, legend). Returns ranked recommendations with example props. For richer capability-descriptor ranking (scores, reasons, caveats) and the full 13-intent taxonomy, prefer `suggestCharts` (plural).

NameTypeReqDescription
capabilitiesobject–Capability constraints — set a key to true to require, false to forbid. Unset keys are ignored.
dataarrayyes1-5 sample data objects
intentstring–Visualization intent. Accepts this engine's intents (comparison, trend, distribution, relationship, composition, geographic, network, hierarchy) AND the richer suggestCharts taxonomy (compare-categor…

No output schema declared.

No examples provided.

suggestCharts ~216

Recommend Semiotic charts for a dataset using heuristic capability descriptors. Returns ranked, structured suggestions with scores, reasons, caveats, and ready-to-use props; no LLM call is made.

NameTypeReqDescription
allowarray–Restrict to these component names.
audienceobject–Audience profile — familiarity, adoption targets, exposure level, and reception modality.
dataarrayyesRow data — array of objects.
denyarray–Exclude these component names.
fieldRolesobject–Per-field semantic or exact encoding-role hints used before chart ranking.
identifiersarray–Fields that identify records and must not be used as visual encodings or measures.
intent––Ranking intent. One of: trend, compare-series, compare-categories, rank, part-to-whole, distribution, correlation, flow, hierarchy, geo, outlier-detection, composition-over-time, change-detection. Cu…
maxResultsinteger–Cap on suggestions returned (default 8).
NameTypeReqDescription
suggestionsarrayyes–

No examples provided.

suggestDashboard ~215

Generate a dashboard of complementary chart panels for a dataset — each panel answers a distinct analytical intent (trend, rank, distribution, correlation, etc.) and the engine diversifies by chart family by default. Heuristic only; no LLM call. Use when the user asks 'show me this data' or 'build me a dashboard' rather than picking one chart.

NameTypeReqDescription
audienceobject–Audience profile — familiarity, adoption targets, exposure level, and reception modality.
dataarrayyesRow data — array of objects.
diversifyByFamilyboolean–Prefer not to repeat chart families across panels (default true).
fieldRolesobject–Per-field semantic or exact encoding-role hints used before chart ranking.
identifiersarray–Fields that identify records and must not be used as visual encodings or measures.
intentsarray–Intents to cover. Omit to let the engine pick based on the data shape.
maxPanelsinteger–Maximum panels (default 6).

No output schema declared.

No examples provided.

suggestStreamCharts ~167

Recommend streaming Semiotic charts for a schema (not row data). Pass fields (with optional cardinality and additive hints) plus optional throughput (band or rows/sec), retention, shape ('append'|'keyed'|'aggregate'), and keyFields. Ranks realtime XY charts plus push-capable ordinal/value/xy charts (BarChart, PieChart, Scatterplot, BigNumber, GaugeChart, …). Returns suggestions, excluded fits-reasons, the ranking intents (inferred when none is given), schema warnings, and optional stretch picks when audience is set.

NameTypeReqDescription
audienceobject––
intent––Ranking intent.
maxResultsinteger––
schemaobjectyesStream schema — fields plus throughput/retention/shape hints. No row data.

No output schema declared.

No examples provided.

suggestStreamDashboard ~61

Compose a multi-panel dashboard from one or more stream schemas. Honors AudienceProfile.dashboard layout policy (cellBudget, leadFamilies, windowPreference).

NameTypeReqDescription
audienceobject––
budgetinteger––
intent–––
schemas–yes–

No output schema declared.

No examples provided.

suggestStretchCharts ~168

Recommend literacy-growth chart picks for a dataset given an AudienceProfile. Returns charts the data supports but the audience is unfamiliar with (familiarity ≤ 3, or ≤ 4 at exposureLevel 2), each paired with the familiar chart it could substitute for and a rationale. Use when the consumer wants to gently expose users to less familiar but more analytically appropriate visualizations.

NameTypeReqDescription
audienceobjectyesAudience profile — familiarity, targets, exposure level, reception modality.
dataarrayyesRow data.
fieldRolesobject–Per-field semantic or exact encoding-role hints used before chart ranking.
identifiersarray–Fields that identify records and must not be used as visual encodings or measures.
intent–––
maxResultsinteger––

No output schema declared.

No examples provided.

suggestTokenEncoding ~238

Recommend a semantic token / ISOTYPE encoding for a reader task. Use before drawing repeated dots, icons, glyphs, natural-frequency grids, quantile dotplots, or hybrid bar-token views. Returns the recommended tokenEncoding, warnings, alternatives, and matching suggestCharts capability intents. Accepts canonical token intents (precise-comparison, probability-estimation, risk-communication, memory, support-decision, etc.) and friendly aliases (measure, estimate probability, understand risk, remember, decide).

NameTypeReqDescription
audiencestring–Audience for the recommendation.
availableSpacestring–Space budget for visible tokens.
concreteEntitystring–Concrete icon/glyph concept, e.g. person, bus, server. Becomes tokenEncoding.icon when useful.
dataTypestring–Data shape or meaning behind the tokenized view.
precisionNeedstring–How much exact magnitude reading matters.
taskIntentstringyesReader task intent, e.g. 'estimate probability', 'understand risk', 'remember', 'measure', 'decide', or canonical token intents like 'probability-estimation'.

No output schema declared.

No examples provided.

Install

How do I install the Semiotic MCP server?

Semiotic runs locally as an npm package, launched with npx -y semiotic. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · semiotic

# add to Claude Code
claude mcp add nteract-semiotic -- npx -y semiotic
Common questions

What is the Semiotic MCP server?

Semiotic is an MCP server listed in the public MCP registry as io.github.nteract/semiotic. Verified React chart generation: select, validate, repair, render, and inspect charts through MCP. This page covers its npm package (semiotic).

Is the Semiotic MCP server safe to use?

Semiotic scores 88 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. Its build provenance is signed and verified. 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 Semiotic MCP server expose?

Semiotic exposes 24 tools: auditArtifact, recommendRepresentation, repairArtifact, explainRefusal, getSchema, and 19 more. Their descriptions and schemas cost roughly 4,827 tokens of context every time the server is loaded.

Is the Semiotic MCP server still maintained?

Semiotic 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 Semiotic MCP server under?

Semiotic declares the Apache-2.0 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 Semiotic MCP server?

VerifyMCP ran 17 checks on Semiotic, covering Malware scan, Known CVEs, Install scripts, Dependency health and 13 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.