best-practices

A set of Cursor coding rules for documentation, errors, input validation, code generation, and testing. Cursor is a code editor with built-in AI assistance.

In plain words
What is it for?
Use it when writing or reviewing Pinecone MCP code, especially public methods, JSDoc comments, custom errors, validation, and tests.
Why use it?
It gives contributors consistent expectations for public APIs, error messages, invalid inputs, and preserved error causes.

Cursor rule for Cursor

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add rules/pinecone-io/pinecone-mcp/best-practices
Clone the repo
git clone --depth 1 https://github.com/pinecone-io/pinecone-mcp

Made for: Cursor.

Per session 588 This file is loaded in full into every session.
When invoked 588 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00588 $0.00588
Opus 5 $0.00294 $0.00294
Sonnet 5 $0.00118 $0.00118
Haiku 4.5 $0.00059 $0.00059

Measured 3d ago against content hash 6409c5020230, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

best-practices scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.cursor/rules/best-practices.mdc · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Documentation

  • When changing code, review nearby JSDoc comments to ensure they are up to date
  • Include @throws tags in JSDoc for all errors that methods can throw
  • Provide usage examples in JSDoc using code blocks with ```typescript for public APIs
  • Document parameter constraints and validation rules in JSDoc
  • Mark internal APIs with /** @internal */ to exclude them from public documentation

Error Handling

  • Use appropriate custom error classes from src/errors (e.g., PineconeArgumentError, PineconeBadRequestError, PineconeConnectionError)
  • All custom errors extend BasePineconeError
  • Include descriptive error messages that help users understand what went wrong
  • When wrapping errors, preserve the original cause using the constructor that accepts Error as the second parameter: new ErrorClass(message, cause)
  • Map HTTP status codes to appropriate error types using mapHttpStatusError patterns

Validation

  • Validate input parameters early in public methods, throwing PineconeArgumentError for invalid inputs
  • Provide clear, actionable error messages that reference documentation when appropriate
  • Use helper validation functions for complex validation logic that may be reused
  • Validate null, undefined, and empty strings/arrays explicitly before use
  • Leverage TypeScript's type system to catch many validation issues at compile time

Code Generation

  • Never manually edit files in src/pinecone-generated-ts-fetch/** - these are auto-generated
  • If changes are needed to generated code, update the source OpenAPI/Proto files in codegen/ and regenerate using npm run generate:openapi

Testing

  • Ensure all major requirements are captured as test cases
  • Write unit tests for validation logic and error handling paths
  • Include integration tests for end-to-end workflows (sparingly)
  • Test both success and failure scenarios, including edge cases
  • Use descriptive test names that clearly indicate what is being tested
  • Test both Node.js and Edge runtime environments when applicable

Read the full file on GitHub · 51 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 51 lines · 588 tokens per session scan A 6409c5020230

Subscribe to this mod's changes

best-practices is a cursor rule published in the GitHub repository pinecone-io/pinecone-mcp (71 stars, last pushed 7d ago), licensed Apache-2.0. It adds 588 tokens to every session, about $0.0029 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.