ai-actions-server

A set of coding rules for Freshworks AI Actions server files, including request handling, error responses, and data rendering. AI Actions are server-side functions that perform tasks for an application.

In plain words
What is it for?
Use it when building or reviewing AI Actions server.js files, especially code that invokes templates, parses responses, and calls renderData.
Why use it?
It gives developers consistent patterns for handling requests and returning safe, useful errors to users.

Cursor rule

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/freshworks-developers/fw-dev-tools/ai-actions-server
Clone the repo
git clone --depth 1 https://github.com/freshworks-developers/fw-dev-tools
Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 2,699 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00000 $0.02699
Opus 5 $0.00000 $0.01350
Sonnet 5 $0.00000 $0.00540
Haiku 4.5 $0.00000 $0.00270

Measured 2d ago against content hash a759e0948c46, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ai-actions-server 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 2d 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.

skills/fw-ai-actions-app/rules/ai-actions-server.mdc · 320 lines

How it starts

The opening of the file, as written. The whole thing — 320 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Actions server.js Patterns

Platform 3.0 pattern

const __formatError = (error, functionName) => {
  console.error(`[${functionName}] Error:`, error);
  let message;
  try {
    message = error.response ? JSON.parse(error.response) : error.message;
  } catch {
    message = error.response || error.message || 'Unknown error';
  }
  const parsedMessage = message instanceof Object ? JSON.stringify(message) : message;
  return { status: error.status || 500, message: parsedMessage };
};

exports = {
  actionName: async function(args) {
    try {
      const { param1 } = args;
      const response = await $request.invokeTemplate('templateName', {
        context: { param1: param1 },
        body: JSON.stringify({ ... })  // if POST/PUT
      });
      const data = JSON.parse(response.response);
      renderData(null, data);
    } catch (error) {
      renderData(__formatError(error, 'actionName'), null);
    }
  }
};

Error messages surfaced to users

Sanitize before renderData: Vendor error payloads may contain internal URLs, stack traces, tokens, or other sensitive data. Strip or map them to short, user-safe strings for the message passed to renderData; log the full error server-side only.

renderData Signature

renderData(error, data)

  • Success: renderData(null, data) — pass parsed response directly
  • Error: renderData({ status, message }, null)

Rules

  1. Helper functions — Can be defined BEFORE exports
  2. $request.invokeTemplate() — Use only; never .post/.get/.put/.delete
  3. context — For path/query params: context: { id: args.id }
  4. body — For POST/PUT: body: JSON.stringify(requestBody)
  5. query — For GET query params: query: { page: 1 }
  6. Function name — Must match actions.json key exactly (case-sensitive)

Modular server layout

Keep server/server.js focused on SMI exports (exports = { ... }) and thin handlers. Move reusable logic into additional modules under server/services/, server/lib/, or similar, and require() them from server.js. This keeps complexity down and matches how npm dependencies are loaded from serverless code (Use external libraries).

Read the full file on GitHub · 320 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. 2d ago First seen · 320 lines · 0 tokens per session scan A a759e0948c46

Subscribe to this mod's changes

ai-actions-server is a cursor rule published in the GitHub repository freshworks-developers/fw-dev-tools (5 stars, last pushed 8d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,699 tokens. 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 2026-08-31.