pinescript-plugin
v0.5.0by jpantsjoha · author: Jaroslav Pantsjoha
This plugin, by Jaroslav Pantsjoha, helps a coding agent write TradingView Pine Script v6 and check it. Its MCP server validates Pine code and returns the real signatures from the official 475-function reference, including the overloads models often get wrong. A hook checks every .pine file the agent edits. Four skills cover indicators, strategies, the v6 language and validation. MIT.
TradingView Pine Script v6 for coding agents, backed by a real validator rather than prose. A language skill plus an MCP server that validates Pine and returns real signatures from the official 475-function reference, including the overloads models routinely get wrong, and a hook that checks every.pine file the agent edits.
What pinescript-plugin does, in the publisher's words
> Your agent writes Pine Script it cannot check. This gives it a checker.
> Eight of these checks catch code that compiles perfectly and still loses money.
Every AI Pine Script tool on the market ships advice. None of them can verify a single line they produce. That gap is the whole reason this exists.
- Parameter names are not guessable. label.new takes textalign. box.new takes text_halign. Nothing about either implies the other.
- Several functions have two valid call forms. line.new, label.new and box.new each accept a chart.point or independent coordinates. A model that has seen one will insist the other is wrong.
- The language moves quarterly, in both directions. TradingView added request.footprint() and multiline strings, then removed the wrapped-line indentation rules in December 2025. Training data goes stale coming and going.
From the project README, punctuation lightly normalized · Open the README on GitHub
- Skills
- 4
- MCP servers
- 1
- Stars
- 3
- License
- MIT
- Repo created
- 2026-08-07
- Last pushed
- 2026-10-02
- Publisher type
- User
- Version
- 0.5.0
Links
Skills · 4
- pinescript-indicator
- Generate working TradingView Pine Script v6 indicators, plotting, drawing objects, tables, alerts, inputs and the plot/object limits that break scripts at scale. Provides validated scaffolds to start from rather than composing from memory. Use when asked to write, create or build an indicator, stu…
- pinescript-strategy
- Write TradingView Pine Script v6 strategies that behave the same live as in backtest, entries, exits, position sizing, commission and slippage, and the repainting and lookahead traps that make a backtest lie. Includes validated scaffolds and webhook alert payloads for broker automation. Use when a…
- pinescript-v6
- Write and debug TradingView Pine Script v6 correctly. Covers the execution model, the v6 type system, overloaded drawing constructors, anti-repainting with request.security, and the API TradingView shipped through 2026. Validate every script before claiming it works. Use when the user mentions: pin…
- pinescript-validation
- Diagnose and fix Pine Script v6 errors deterministically, read each validator diagnostic, apply the known fix, re-validate. Covers every diagnostic class the validator emits, what it cannot see, and how to work through an existing codebase of broken.pine files. Use when a Pine script fails to com…
Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.
MCP servers · 1
- pinescriptstdio
- node ./mcp/server.js
Read from the plugin's own mcp.json. We list environment variable names, never values.
Category
Code Review & Quality. Assigned by this directory. Agent Plugins 1.0.0 has no category field, so no manifest declares one.
Keywords
pinescript · pine-script · pine-v6 · tradingview · trading · indicators · strategies · backtesting · validation · linter · mcp · claude-code · agent-plugin
Related by publisher and keywords
A full Google Cloud delivery team for your coding agent: vendor-objective solution designer, GCP architect, agentic-systems architect (ADK / Agent Runtime / MCP / A2A / AP2), plus security, SRE, and QA, wired into a design-first, security-first delivery gate. Eleven service skills (Cloud Run, GKE, IAM, BigQuery, Cloud Storage, Vertex AI, networking, observability), MCP server setup, and a self-validating research pipeline that keeps every reference current.
Shared delivery practices for human: AI teams: planning, tickets, model selection, testing, independent review and release readiness. Install for a project or user; adopt project-owned authority and checks.
Governed local-first coding through the verified Simplicio Runtime MCP and portable agent skills.
Build, run and manage trading automation on Sigrex: code and AI strategies, trading bots, webhooks and signals across crypto exchanges, DEXs and prediction markets. Connects the official Sigrex MCP server (OAuth) and bundles Sigrex workflow skills for strategies, bots, webhooks, the API and safe testing.
Query edgeful's futures and stock trading reports and discovery scans, build and save custom reports, and manage your edgeful settings, watchlists and templates from your AI agent.
Expert skills for building n8n workflows with the n8n-mcp MCP server
[](https://agentpluginsdirectory.com/plugins/pinescript-plugin)✓ Verified . We fetched the manifest from GitHub and checked it against the official Agent Plugins 1.0.0 schema at agent-plugins.org.