Pine Script v6 Documentation

Measured conclusion: Deep-tested. L2 outcome: tools_ok.

Pine Script v6 documentation lookup, function validation, and linting for AI code generation

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "Pine Script v6 Documentation": {
      "url": "https://pinescript-mcp.fly.dev/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (10)

• list_docs read-only

  USE WHEN discovering what Pine Script v6 documentation is available. Returns a categorised list of doc file paths with one-line descriptions. AFTER calling this tool, call get_doc(path) for small files or list_sections(path) then get_section(path, header) for large files (ta.md, strategy.md, collections.md, drawing.md, general.md). Data sourced from bundled Pine Script v6 documentation.

  Hints: read-only yes · destructive not declared · idempotent yes · open-world no

• list_sections read-only

  USE WHEN navigating a large documentation file before reading a specific section. Returns a newline-separated list of # and ## headers (### excluded) in the file. AFTER calling this tool, call get_section(path, header) with a header from this list. Data sourced from bundled Pine Script v6 documentation.

  Parameters:

  • path (required) — string — Documentation file path (e.g., 'reference/functions/ta.md').

  Hints: read-only yes · destructive not declared · idempotent yes · open-world no

• get_doc read-only

  USE WHEN reading the full content of a Pine Script v6 documentation file. Returns the file content; when limit is set, a header shows the char range and offset to continue reading. AFTER calling this tool, use offset=<end> to continue if the header indicates more content is available. For large files (ta.md, strategy.md, collections.md, drawing.md, general.md), prefer list_sections() + get_section() instead. Data sourced from bundled Pine Script v6 documentation.

  Parameters:

  • path (required) — string — Relative path to the documentation file (e.g., 'reference/functions/ta.md').
  • limit — integer — Maximum characters to return. Use 30000 for large files. 0 = no limit.
  • offset — integer — Character offset to start reading from.

  Hints: read-only yes · destructive not declared · idempotent yes · open-world no

• get_section read-only

  USE WHEN reading a specific named section from a Pine Script v6 documentation file. Returns the section content from the matched header to the next same-level header, with file path and line range. AFTER calling this tool, call list_sections(path) if the header was not found, or get_section() again with a child header for a narrower subsection. Data sourced from bundled Pine Script v6 documentation.

  Parameters:

  • path (required) — string — Documentation file path (e.g., 'reference/functions/strategy.md').
  • header (required) — string — Header text to find (e.g., 'strategy.exit()' or '## strategy.exit()').
  • include_children — boolean — Include nested subsections under the matched header.

  Hints: read-only yes · destructive not declared · idempotent yes · open-world no

• search_docs read-only

  USE WHEN finding documentation sections that match specific terms across all Pine Script v6 docs. Returns up to max_results sections ranked by match count, each with a preview and a get_section() call hint. AFTER calling this tool, call get_section(file, header) for each result you want to read in full. Data sourced from bundled Pine Script v6 documentation.

  Parameters:

  • query (required) — string — Search terms (case-insensitive). Multi-word queries match sections containing ALL terms.
  • max_results — integer — Maximum sections to return.

  Hints: read-only yes · destructive not declared · idempotent yes · open-world no

• get_functions read-only

  USE WHEN browsing valid Pine Script v6 functions, optionally filtered to a namespace. Returns function names grouped by namespace (e.g. ta.*, strategy.*) or filtered to the requested namespace. AFTER calling this tool, call validate_function(fn_name) to check a specific name, or get_section() to read its documentation. Data sourced from bundled pine_v6_functions.json.

  Parameters:

  • namespace — string — Filter by namespace (e.g., 'ta', 'strategy', 'request'). Empty string returns all functions grouped by namespace.

  Hints: read-only yes · destructive not declared · idempotent yes · open-world no

• validate_function read-only

  USE WHEN confirming a Pine Script v6 function name is valid before using it in code. Returns a valid/invalid verdict with namespace suggestions or known replacement hints (e.g. ta.adx → ta.dmi, security → request.security). AFTER calling this tool, call get_functions(namespace) to list all valid functions in the relevant namespace if the function is invalid. Data sourced from bundled pine_v6_functions.json.

  Parameters:

  • fn_name (required) — string — Function name to validate (e.g., 'ta.sma', 'strategy.entry', 'plot').

  Hints: read-only yes · destructive not declared · idempotent yes · open-world no

• resolve_topic read-only

  USE WHEN looking up an exact Pine Script API term or known concept keyword. Returns the best-matching doc paths with matched keywords and a retrieval suggestion (get_doc or list_sections + get_section). AFTER calling this tool, follow the suggestion: call get_doc() for small files or list_sections() + get_section() for large files. For natural language questions use search_docs() instead. Data sourced from bundled TOPIC_MAP and doc file content scan.

  Parameters:

  • query (required) — string — Exact Pine Script term or known concept keyword (e.g., 'ta.rsi', 'strategy.entry', 'repainting').

  Hints: read-only yes · destructive not declared · idempotent yes · open-world no

• list_prompts

  List all available prompts. Returns JSON with prompt metadata including name, description, and optional arguments.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• get_prompt

  Get a prompt by name with optional arguments. Returns the rendered prompt as JSON with a messages array. Arguments should be provided as a dict mapping argument names to values.

  Parameters:

  • name (required) — string — The name of the prompt to get
  • arguments — Optional arguments for the prompt

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

Publisher website Repository

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.