candlestick-chart-mcp
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@candlestick-chart-mcpcandlestick chart with SMA 20, 50 for the provided OHLCV series"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
candlestick-chart-mcp
An MCP server that renders OHLCV data as a candlestick chart PNG and returns it as inline image content, so the model can actually look at the chart it asked for.
It is a pure renderer: no network access, no API keys, no market-data provider. You pass the bars in; it draws them.
Install
npm install
npm run buildVerify it end to end (spawns the server over stdio and calls the tool for real):
npm run checkRender sample charts to out/ to eyeball the output:
npm run smokeRelated MCP server: Chart-Output MCP Server
Register with a client
Claude Code:
claude mcp add candlestick-chart -- node /absolute/path/to/candlestick-chart-mcp/dist/index.jsOr in a config file (.mcp.json, claude_desktop_config.json, …):
{
"mcpServers": {
"candlestick-chart": {
"command": "node",
"args": ["/absolute/path/to/candlestick-chart-mcp/dist/index.js"]
}
}
}The tool
render_candlestick_chart
Returns two content blocks: a short text summary (bar count, date range, OHLC, percent change, plus any notes about inputs that were adjusted) and the PNG.
Bars. candles accepts either form per bar, and mixing them is fine:
{ "time": "2026-01-05", "open": 100, "high": 103.2, "low": 99.4, "close": 102.8, "volume": 1200000 }[1767571200, 100, 103.2, 99.4, 102.8, 1200000]The tuple form is [time, open, high, low, close, volume?] and costs far fewer
tokens — prefer it for anything longer than a handful of bars. time takes epoch
seconds, epoch milliseconds, or any string Date.parse understands. Bars are
sorted by time; a high/low that contradicts the body is clamped rather than
rejected.
Everything else is optional:
Option | Default | Notes |
| — | Subtitle defaults to date range · bar count · change |
|
| or |
|
|
|
|
| or |
|
| or |
| per scheme |
|
|
| Needs a volume column; drawn in its own panel |
|
| |
|
|
|
|
| Any IANA zone; applies to every label |
|
| Arrays of periods, e.g. |
| — |
|
|
| Session-anchored; needs volume on every bar |
|
|
|
|
|
|
Example call:
{
"candles": [[1767571200, 100, 103.2, 99.4, 102.8, 1200000], "…"],
"title": "BTCUSD · 1D",
"sma": [20, 50],
"bollinger": { "period": 20, "stdDev": 2 },
"priceLines": [{ "price": 61941.5, "label": "resistance" }],
"markers": [{ "time": "2026-02-14", "side": "buy", "label": "entry" }],
"yScale": "log",
"timeZone": "Europe/Riga"
}Inputs that cannot be honoured do not fail the call — an SMA period longer than the series, a missing volume column, a log scale with non-positive prices, an unknown time zone are each dropped or downgraded and reported in the text block.
Colour
Up/down is a polarity encoding, so the default diverging scheme uses the
blue ↔ red diverging pair. That pair clears the all-pairs colourblind gate in
both themes (CVD ΔE 21.6 light / 19.2 dark against a ≥ 8 target). The traditional
green/red pair fails it at ΔE 4.1 for deuteranopia, so classic ships with
hollow up-bodies: shape carries the direction and hue only reinforces it.
mono drops hue entirely — ink, hollow versus filled — for print and
forced-colours contexts.
With the up/down pair already on screen there is no room left for a palette of overlay hues: every candidate measured below the normal-vision floor against one of the poles. So all overlays share one validated accent per scheme, and their identity comes from dash pattern + legend + a direct label at the end of each line. Four overlays are distinguishable; a fifth reuses a dash pattern and the response says so.
Volume bars inherit the bar's direction at half strength so the panel stays recessive, and it is a separate panel — never a second y-axis on the price plot.
Layout notes
Bars sit on an ordinal x-axis (one slot per bar), so weekends and market holidays leave no gaps. Time labels appear where the label actually changes; intraday charts substitute the date wherever the day rolls over.
Below ~3.5 px per bar, bodies are dropped and each bar becomes a single high-low hairline — a 1200-bar chart stays readable.
Bodies cap at 26 px wide so a seven-bar chart still looks like candles.
The PNG is capped near 4.5 MB; a request that would exceed it is re-rendered at
scale: 1and, failing that, returns an error asking for smaller dimensions.
Layout of the source
File | Role |
| MCP server, tool registration, marker/time-zone resolution |
| Zod input schema — the tool's contract |
| All drawing: layout, axes, candles, overlays, annotations |
| Palettes and the validation results behind them |
| SMA, EMA, Bollinger, VWAP, Heikin-Ashi |
| Input normalisation |
| Tick stepping, number and date formatting |
Adding an indicator panel (RSI, MACD) means adding a panel band to the layout
block in renderChart and a series function in indicators.ts.
License
MIT
Available Tools
1 toolrender_candlestick_chartRender candlestick chartARead-onlyIdempotent
Draw a candlestick (or Heikin-Ashi / OHLC-bar) chart from OHLCV data and return it as a PNG image. Supports a volume panel, moving-average and Bollinger overlays, VWAP, log price scale, horizontal reference lines, buy/sell markers, and light/dark themes. Colours default to a colourblind-safe blue-up / red-down pair; pass colorScheme:"classic" for traditional green/red. No network calls are made.
| Name | Required | Description | Default |
|---|---|---|---|
| ema | No | Exponential moving average periods. | |
| sma | No | Simple moving average periods. | |
| vwap | No | Session-anchored VWAP (needs volume on every bar). | |
| scale | No | Device-pixel ratio. Raise for print; 1 keeps the returned image small. | |
| theme | No | dark | |
| title | No | Headline, e.g. "BTCUSD · 1h". Omit for a bare plot. | |
| width | No | Logical width in px. | |
| height | No | Logical height in px. | |
| yScale | No | Use log for multi-year or high-growth ranges. | linear |
| candles | Yes | OHLCV bars, oldest first (any order is accepted and sorted). Two accepted forms per bar: {"time":…,"open":…,"high":…,"low":…,"close":…,"volume":…} or the compact tuple [time, open, high, low, close, volume?]. Prefer the tuple form for long series — it costs far fewer tokens. | |
| markers | No | Triangular annotations: buy below the bar, sell above it. | |
| showGrid | No | ||
| subtitle | No | Second header line. Defaults to the date range, bar count and last close. | |
| timeZone | No | IANA time zone used for every axis and header label. | UTC |
| bodyStyle | No | Override body fill. Defaults to filled for diverging, hollow-up for classic and mono. | |
| bollinger | No | Bollinger band overlay. | |
| chartType | No | candlestick = classic bodies; heikin-ashi = smoothed bodies; ohlc-bars = Western bar chart. | candlestick |
| priceLines | No | Horizontal reference lines — support, resistance, entry, stop. | |
| showLegend | No | ||
| showVolume | No | Volume panel below the price panel (needs a volume column). | |
| colorScheme | No | diverging = blue up / red down (validated colourblind-safe, the default). classic = green up / red down (traditional but not CVD-safe, so up bodies are drawn hollow). mono = ink only, direction by hollow vs filled. | diverging |
| showLastPrice | No | Dashed line plus axis chip at the final close. |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses important behavioral traits: it returns a PNG image and makes no network calls. This goes beyond the existing readOnly and idempotent annotations, and does not contradict them. The color scheme default and override hint also add transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is three concise sentences, front-loaded with the core purpose. Every sentence adds value—drawing, features, and network behavior—without unnecessary fluff or repetition of schema details.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (22 parameters, nested objects) and absence of an output schema, the description covers the essential context: return type (PNG) and network behavior. However, it does not specify whether the PNG is returned as base64, a URL, or raw bytes, which is a minor gap for a tool with no output schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema already covers 86% of parameters in detail, so a baseline of 3 applies. The description adds a high-level feature overview (volume panel, moving averages, Bollinger, VWAP, etc.) that maps to parameters, and specifically advises on the 'classic' color scheme, which provides useful guidance beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool draws candlestick charts (with Heikin-Ashi and OHLC-bar variants) from OHLCV data and returns a PNG. It enumerates supported features, leaving no ambiguity about the tool's purpose.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear context on what the tool does and that it makes no network calls, but it does not explicitly state when to use it over alternatives. Since no sibling tools are listed, this is acceptable, yet explicit usage guidance is missing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
1 tool update
v0.1.0- First observed
render_candlestick_chart
TDQS
With only one tool, there is no possibility of confusion or overlapping purposes. The tool's purpose is clearly defined and distinct.
The single tool name follows a clear verb_noun pattern (render_candlestick_chart), which is consistent and descriptive. There are no other tools to create inconsistencies.
A single tool feels thin and borderline for a typical MCP server, even though the tool itself is comprehensive and covers the charting domain well. It sits at the lower boundary of the acceptable range.
The tool appears to fully cover the domain of candlestick chart rendering, supporting multiple chart types, overlays, markers, and themes. No obvious gaps in the server's stated purpose.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
Renders interactive Chart.js charts and dashboards inline in AI conversations.
Renders interactive Chart.js charts and dashboards inline in AI conversations. Supports bar, line, area, pie, doughnut, scatter, and radar charts with multi-chart dashboard grids.
Create, inspect, manage, and render charts and data visualizations as SVG/PNG or interactive embeds.
- mcpOAuthcom.slickfast
Render 47 chart types and tiled dashboards as PNG/SVG. Deterministic, no headless browser.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceTransforms CSV data into beautiful visualizations including line charts, bar graphs, pie charts, and world maps. Returns base64-encoded PNG images optimized for AI chat interfaces and assistants.10Apache 2.0
- AlicenseAqualityDmaintenanceEnables AI agents to generate and render charts as PNG, SVG, or WebP images directly in chat interfaces. Supports Chart.js specifications and natural language descriptions for creating visualizations from data.3341MIT
- AlicenseAqualityBmaintenanceEnables AI agents to create data visualizations like bar charts, line charts, pie charts, scatter plots, and histograms, returning inline SVG or PNG files.5MIT
- FlicenseAqualityDmaintenanceEnables AI agents to capture TradingView chart snapshots via the CHART-IMG API, supporting multiple chart types and resolutions with automatic dimension clamping and authentication.9-
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/dzintars2/candlestick-chart-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server