tradingview-mcp/ v0.1 ──────────────────────────────────────────────────一个专注且类型安全的 MCP 服务器，让 Claude Code（或任何兼容 MCP 的客户端）能够驱动本地运行的 TradingView 桌面版应用程序 —— 读取图表状态、更改交易品种和时间周期、获取 OHLCV 数据、截取屏幕截图。
[!IMPORTANT] 本项目与 TradingView Inc. 无关，未得到其认可或关联。 这是一个个人使用的桥接工具，通过 Chrome DevTools 协议与您本地运行的 TradingView 桌面版应用程序进行交互 —— 这与 Slack、VS Code、Discord 以及其他所有 Electron 应用内置的调试接口标准相同。
[!IMPORTANT] 需要有效的 TradingView 订阅。 本工具不会绕过、抓取或规避任何 TradingView 的付费墙或访问控制。所有操作均在您的机器上进行，针对的是您已经登录并付费的 TradingView 桌面版实例。
[!NOTE] 所有处理均在本地进行。 本工具不会传输、存储或重新分发任何 TradingView 数据。您的图表、您的数据、您的机器。
[!CAUTION] TradingView 的内部页面 API 未经文档记录。它可能会在桌面版发布版本之间发生变化。如果您需要稳定性，请锁定一个可用的 TradingView 桌面版版本，并在升级前查看 版本兼容性 说明。
将 TradingView 桌面版图表封装在一组定义明确的 MCP 工具中。工具通过 Zod 模式进行端到端类型定义，在边界处进行验证，并在出错时提供有用的错误信息。
┌───────────────┐
│ Claude Code │
│ (or any MCP │
│ client) │
└───────┬───────┘
│ stdio (MCP)
▼
┌───────────────┐
│tradingview-mcp│
└───────┬───────┘
│ Chrome DevTools Protocol
▼
┌───────────────┐
│ TradingView │
│ Desktop │
│ (--remote- │
│ debugging- │
│ port=9222) │
└───────────────┘Related MCP server: TradingView MCP Jackson
现有的 TradingView 自动化项目已经存在。本项目特意缩小了范围：
12 个工具，而不是 78 个。 每个工具都经过文档记录、类型定义和测试。
严格的 TypeScript。 没有 any，没有隐式返回，开启了 noUncheckedIndexedAccess。
每个文件单一职责。 连接、页面、工具和服务器是独立的层级 —— 版本漂移只需修复一个地方。
类型化错误。 ConnectionError、ToolExecutionError、ChartStateError 等，并带有可操作的消息。
tradingview-mcp doctor。 一个诊断命令，可以准确告诉您设置中存在的问题。
如果您想要一个可以在一下午读完的小型、可预测的接口，请使用此工具。如果您想要封装所有 TradingView 功能的“大而全”替代方案，请使用其他工具。
需要 Node.js 20+。
npm install -g tradingview-mcp
# or, in a project:
npm install tradingview-mcp用于开发：
git clone https://github.com/harshil1502/tradingview-mcp.git
cd tradingview-mcp
npm install
npm run build否则无法启用调试端口。
macOS:
open -a "TradingView" --args --remote-debugging-port=9222Windows:
& "C:\Users\<you>\AppData\Local\Programs\TradingView\TradingView.exe" --remote-debugging-port=9222Linux:
tradingview --remote-debugging-port=9222[!NOTE]
--remote-debugging-port标志是一个标准的 Chromium 调试标志。它是可选的，默认禁用。除非您明确传递它，否则不会发生任何事情。
tradingview-mcp doctor如果一切连接正常，您将看到类似以下内容：
tradingview-mcp · doctor
─────────────────────────────────────────────
[ok] CDP endpoint reachable on localhost:9222
[ok] TradingView page found (NASDAQ:AAPL · 1h)
[ok] tvWidget detected — chart state readable
─────────────────────────────────────────────
ready.将其添加到您的 Claude Code MCP 配置中（~/.claude/mcp.json 或项目 .mcp.json）：
{
"mcpServers": {
"tradingview": {
"command": "tradingview-mcp",
"env": {
"TV_MCP_PORT": "9222"
}
}
}
}重启 Claude Code。下面的工具将变为可用状态。
工具 | 描述 |
| 读取当前交易品种、时间周期、可见指标、最新价格 |
| 更改活动交易品种（例如 |
| 更改分辨率（ |
| 从活动图表中获取最多 5,000 条最新的 OHLCV 数据 |
更多工具即将推出 —— 请参阅 docs/roadmap.md。
You: What's the chart showing?
Claude: [calls chart_get_state]
Showing NASDAQ:AAPL on 1h timeframe with EMA20, EMA50.
Last price 187.42.
You: Switch to BTCUSDT 4h and pull the last 200 bars.
Claude: [calls chart_set_symbol, chart_set_timeframe, chart_get_ohlcv]
Done. Range: 187 days. Open at start: 62,440.
Close at end: 67,830. +8.6%.环境变量 | 默认值 | 描述 |
|
| CDP 主机 |
|
| CDP 调试端口 |
| (自动检测) | 显式 CDP 目标 ID —— 仅在打开多个 TradingView 窗口时需要 |
npm install
npm run build # tsc to dist/
npm run dev # tsc --watch
npm test # vitest run
npm run test:coverage # with v8 coverage report
npm run typecheck # tsc --noEmit代码库分为四个层级：
src/
├── index.ts entry — reads env, starts stdio server
├── server.ts MCP server, tool registration, request handlers
├── errors.ts typed error classes
├── types.ts shared types + Zod schemas
├── connection/
│ ├── cdp.ts CDP client wrapper (chrome-remote-interface)
│ └── tradingview.ts TradingView-page interactions (all evaluated JS lives here)
└── tools/
├── index.ts tool registry
└── chart.ts chart_* tools添加工具：
在 src/tools/ 下创建一个新文件（或扩展现有文件）。
导出 <name>Input 和 <name>Output Zod 模式以及处理函数。
将条目添加到 src/tools/index.ts 中的 TOOLS。
在 tests/ 下添加测试。
就是这样 —— 自动注册、自动验证、自动内省。
TradingView 桌面版 | tradingview-mcp | 状态 |
2026.x.x | 0.1.x | 已测试 |
如果 TradingView 更新导致工具开始失效，请首先检查 connection/tradingview.ts —— 这是唯一了解 TradingView 内部 API 的文件。
本软件按“原样”提供，不附带任何形式的保证。运行本软件即表示您承认：
您正在使用自己的付费 TradingView 桌面版实例，针对自己的数据进行操作。
您自行启用了 Chrome DevTools 调试端口。
TradingView 的内部 API 未经文档记录，可能会发生中断。
本软件中的任何内容都不能保证 AI 代理在其之上做出的交易决策的正确性。在让其触及真实资金之前，请先在模拟账户上使用。
MIT © 2026 Harshil Patel
这是一个全新的实现 —— 从零开始构建，目标是小巧、类型良好且易于阅读。如果您曾在此领域从事过类似工具的开发，感谢您铺平道路。
Fetch recent OHLCV bars from the active chart.
| Name | Required | Description | Default |
|---|---|---|---|
| count | No | Number of most-recent bars to return. Capped at 5000. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided; description lacks details about behavior when no chart is active, what 'recent' means, or that count parameter is capped at 5000.
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?
Single sentence, 8 words, no fluff; but could be longer to include essential details without being verbose.
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?
Tool has one parameter and no output schema; description omits explanation of OHLCV, return format, timeframe context, and count's effect.
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?
Schema description coverage is 100%, so baseline is 3; description adds no extra meaning beyond the schema's parameter documentation.
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?
Description clearly states the verb 'Fetch', resource 'OHLCV bars', and context 'from the active chart', distinguishing it from sibling tools like chart_get_state or quote_get.
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?
No guidance on when to use this tool versus alternatives (e.g., quote_get for quotes) or prerequisites like having an active chart.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Read the current chart state: symbol, timeframe, visible studies, and last price.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Description explicitly declares the tool as read-only ('Read'), which aligns with the operation. It discloses the output fields. Since no annotations are provided, the description carries the full burden and does so adequately, though it could mention if auth or rate limits apply.
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?
Single sentence with no unnecessary words. Every part adds value: action, resource, and output details. Highly efficient.
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 no output schema, the description clearly lists all return values (symbol, timeframe, visible studies, last price). The tool is simple, and the description covers its purpose completely.
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?
No parameters exist, and schema coverage is 100%. The description doesn't add parameter information, which is acceptable since there are none. Baseline score of 4 applies.
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?
Description clearly states the action (Read) and the resource (current chart state), and lists specific outputs (symbol, timeframe, visible studies, last price). It distinguishes itself from sibling tools like chart_get_ohlcv (which returns historical data) and chart_set_symbol (which modifies state).
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?
No guidance on when to use this tool versus alternatives. It simply describes the function without providing context on scenarios or exclusions. For example, it doesn't indicate that for historical data one should use chart_get_ohlcv.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Change the active chart symbol (e.g. "NASDAQ:AAPL").
| Name | Required | Description | Default |
|---|---|---|---|
| symbol | Yes | TradingView symbol identifier, e.g. "NASDAQ:AAPL", "BINANCE:BTCUSDT", "NSE:RELIANCE". |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden for behavioral traits. It only states 'change', but does not disclose side effects (e.g., whether it clears chart state, requires certain permissions, or is reversible). Minimal 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 a single sentence with no superfluous words. It is efficiently front-loaded and directly communicates the tool's purpose and provides an example.
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?
For a simple one-parameter setter with no output schema, the description is fairly complete: it defines the action, resource, and provides a valid input example. However, it omits details about what constitutes 'active chart' or confirmation of success, but these are minor gaps given the tool's simplicity.
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?
Schema coverage is 100% with a detailed parameter description. The tool description repeats the example ('NASDAQ:AAPL') which adds little beyond the schema. Baseline 3 is appropriate as the description does not substantially enhance understanding of the parameter.
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 action ('Change the active chart symbol') and the resource, with an example. It effectively distinguishes from sibling tools like chart_set_timeframe (which changes timeframe) and get/read operations.
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?
No guidance is provided on when to use this tool versus alternatives (e.g., if the symbol needs to be set before fetching data or if it has prerequisites). The description lacks explicit context for invocation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Change the active chart timeframe / resolution.
| Name | Required | Description | Default |
|---|---|---|---|
| timeframe | Yes | Resolution: 1m, 3m, 5m, 15m, 30m, 1h, 2h, 4h, 1d, 1w, 1M. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure, but it only states the action without mentioning side effects (e.g., chart reload, impact on other chart state). The tool is a state mutator, yet no consequences are described.
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 a single sentence with no wasted words. It is front-loaded and to the point, though minimal.
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 simplicity of the tool (1 param, no output schema), the description is too brief. It lacks context about when timeframe changes take effect, whether they are reversible, or any related state changes. More context is needed for a mutation tool.
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?
Schema coverage is 100% for the single parameter 'timeframe', including both description and enum. The description adds no extra semantic meaning beyond 'resolution', so baseline 3 is appropriate.
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 action 'change' and the resource 'active chart timeframe / resolution', making the tool's purpose unambiguous. It distinguishes itself from sibling tools like chart_get_ohlcv or chart_set_symbol by focusing on timeframe modification.
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 no guidance on when to use this tool versus alternatives, nor does it mention any prerequisites or context. An agent receives no hints about appropriate usage scenarios.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Trigger a Pine compile and return diagnostics (errors, warnings).
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description should disclose side effects or state dependencies. It does not mention that it compiles the current source or what happens on failure.
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?
Single sentence, no redundancy, and front-loaded with action and result.
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?
Lacks mention of state or prerequisite (e.g., requires source to be set), and no output schema or format details. Incomplete for a compile action.
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?
No parameters exist, so schema coverage is 100%. Description does not explicitly state 'no parameters required' but is acceptable. Baseline 4 for zero params would expect more clarity about inputs.
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 action ('Trigger a Pine compile') and the output ('return diagnostics (errors, warnings)'), distinguishing it from sibling tools like pine_save or pine_get_source.
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?
No guidance on when to use this tool vs alternatives or prerequisites (e.g., setting source via pine_set_source). Purpose is clear but lacks context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Read the current Pine Editor source code. Pine Editor must be open.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided; description indicates read-only operation but does not detail behavior if editor is closed or format of returned source code.
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?
Two sentences, front-loaded, no redundant information. Perfectly concise.
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?
For a simple read tool with no parameters, the description covers purpose and precondition. Could mention output format but not essential.
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?
No parameters, description adds no extra parameter info beyond schema. Baseline 4 for 0 parameters.
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?
Clearly states it reads the current Pine Editor source code, distinguishing it from pine_set_source (write) and pine_compile (compile). The verb 'Read' and resource are specific.
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?
Includes prerequisite 'Pine Editor must be open' but lacks explicit guidance on when to use this tool vs alternatives like pine_compile or saving source code.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Save the current Pine script (commits + reloads the indicator on the chart).
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses that the tool commits and reloads the indicator, which implies it modifies state and may have side effects on the chart. However, without annotations, it does not fully detail what happens to unsaved changes, whether it overwrites previous versions, or if it requires specific permissions. The disclosed behavior is helpful but incomplete.
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 a single, concise sentence that immediately conveys the core action. It is front-loaded with the verb 'save' and includes essential behavioral details parenthetically. No extraneous words or repetition.
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 that there are no parameters, no output schema, and no annotations, the description provides a reasonable overview of the tool's function. However, it lacks details on return values, error conditions, and what 'current Pine script' refers to (e.g., the script in the editor). It is mostly complete for a zero-parameter tool but could elaborate on state implications.
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 input schema has no parameters, so the description does not need to add parameter semantics. The baseline for 0 parameters is 4, and the description appropriately avoids unnecessary detail.
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 saves the current Pine script, with the specific actions of committing and reloading the indicator. The verb 'save' and resource 'Pine script' are precise, and the detail 'commits + reloads' differentiates it from siblings like pine_compile (which only compiles) or pine_set_source (which sets source but may not commit).
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?
No guidance is provided on when to use this tool versus alternatives such as pine_compile or pine_set_source. The description does not mention prerequisites, ordering, or scenarios where saving might be inappropriate (e.g., if the script has errors).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Replace the Pine Editor source code with new content.
| Name | Required | Description | Default |
|---|---|---|---|
| code | Yes | New Pine Script source code. Replaces the current editor contents entirely. Include `//@version=5` at the top. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must convey behavioral traits. It notes that the replacement is 'entirely,' indicating full overwrite. However, it omits important details such as whether the operation triggers compilation, validates syntax, or interacts with unsaved content. The description is minimal but not misleading.
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?
Extremely concise at 8 words. While efficient, it could be slightly expanded to include usage context (e.g., 'before compiling'). The single sentence is front-loaded but borderline under-specified for a set operation.
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?
For a simple setter with one parameter and no output schema, the description is adequate but not comprehensive. It fails to mention typical usage patterns (e.g., paired with pine_get_source and pine_compile) or the need for valid Pine Script. Schema covers parameter details, but contextual workflow is missing.
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?
Schema coverage is 100%, and the schema already provides a detailed description of the 'code' parameter (new source, replaces entirely, include version). The tool description adds no additional semantic value beyond the schema, meeting the baseline for high schema coverage.
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's function: 'Replace the Pine Editor source code with new content.' It uses a specific verb ('Replace') and resource ('Pine Editor source code'). This distinguishes it from sibling tools like pine_get_source (retrieve) and pine_compile (compile), and from unrelated tools like chart_get_ohlcv.
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?
No guidance on when to use this tool versus alternatives (e.g., pine_save). No prerequisites, constraints, or workflow hints (e.g., compiling after setting). The description only states what it does, not when it's appropriate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get a real-time quote snapshot for the active symbol (last price, day OHLC, volume).
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It discloses the tool is a read operation (real-time snapshot), but omits critical behavioral details: the dependency on a pre-set 'active symbol', potential error conditions if no symbol is active, and any side effects or rate limits. The active symbol mechanism is not explained, leaving significant transparency gaps.
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 a single efficient sentence that front-loads the action and key outcomes. Every word contributes value, with no redundancy or filler.
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?
For a zero-parameter tool with no output schema, the description covers the basic purpose and return fields. However, it lacks essential context about the active symbol dependency, how to ensure the symbol is set, and error handling. While low complexity reduces the burden, this missing information could lead to incorrect invocation.
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?
There are zero parameters, and the schema coverage is effectively 100%. According to guidelines, baseline is 4 when no parameters exist. The description adds no parameter-specific info but none is needed.
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 retrieves a real-time quote snapshot for the active symbol, specifying the exact data fields (last price, day OHLC, volume). It distinguishes from sibling tools like chart_get_ohlcv which fetch historical OHLC data, not real-time snapshots.
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 implies usage when a real-time snapshot is needed but does not provide explicit guidance on when not to use it or alternatives. For instance, it does not mention that the active symbol must be set beforehand via chart_set_symbol, nor does it contrast with chart_get_ohlcv for historical data.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Capture the chart pane as a base64-encoded PNG.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It correctly implies a read operation ('capture') but does not mention potential side effects, error conditions (e.g., no chart loaded), or authentication needs. It is adequate but not thorough.
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 a single, concise sentence that conveys all necessary information. It is front-loaded with the core purpose and efficiently structured.
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 no parameters and no output schema, the description is largely complete. It specifies the action and output format. However, additional context about when the tool might fail or prerequisites would improve completeness.
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 input schema has zero parameters, so baseline is 4. The description adds value by specifying the output format (base64-encoded PNG), which is beyond the schema. However, there is no additional semantic enrichment for parameters.
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 action ('capture'), the target ('chart pane'), and the output format ('base64-encoded PNG'). It is specific and distinguishes from the sibling tool 'screenshot_full' which captures the full screen.
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 implies the tool is used when needing a chart pane screenshot, but provides no explicit guidance on when to use it versus alternatives or any prerequisites (e.g., a chart must be open).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Capture the full TradingView viewport as a base64-encoded PNG.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so the description carries the full burden. It discloses the action and output format, but lacks details on side effects, performance, or permission requirements. Adequate for a simple tool.
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?
Single sentence that is front-loaded with the action and resource. No unnecessary words, every part earns its place.
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 zero parameters and no output schema, the description adequately covers what the tool does and the output format. Could mention any constraints (e.g., chart must be loaded), but not required for this simplicity.
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?
Zero parameters, so the baseline is 4 per rubric. The description does not need to add parameter info, and the schema coverage is 100%.
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 action ('Capture'), the specific resource ('full TradingView viewport'), and the output format ('base64-encoded PNG'). It is distinct from siblings like screenshot_chart, which likely captures a chart area.
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?
No explicit guidance on when to use this tool versus alternatives (e.g., screenshot_chart). However, the zero-parameter simplicity implies it's for full viewport capture, which is moderately clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.1.0chart_get_ohlcvchart_get_statechart_set_symbolchart_set_timeframepine_compilepine_get_sourcepine_savepine_set_sourcequote_getscreenshot_chartscreenshot_fullScored across 11 tools
Each tool has a clearly distinct purpose. The chart_* tools handle different aspects of chart interaction, pine_* tools manage Pine script editing and compilation, screenshot_* tools capture images, and quote_get fetches real-time quotes. No overlapping functionality.
Tool names follow a consistent pattern: <domain>_<verb>_<noun> (e.g., chart_get_ohlcv, pine_set_source, screenshot_chart). All use lowercase with underscores, and the verb-noun structure is uniform across domains.
With 11 tools, the server is well-scoped for a TradingView MCP. It covers chart manipulation, Pine scripting, quotes, and screenshots without being bloated or too sparse.
The tool set covers core workflows like symbol/timeframe changes, data retrieval, Pine script management, and screenshots. A minor gap is the lack of tools to add or remove studies (only visible studies are read), but this does not severely hinder typical use cases.
MCP server for OpenMM — exposes market data, account, trading, and strategy tools to AI agents
MCP server for Gainium — manage trading bots, deals, and balances via AI assistants
Remote MCP server for AI.TV creators — delegate account operations to your AI agent over MCP.
MCP server exposing the Backtest360 engine API as tools for AI agents.
