What is tool-pattern?

A set of coding rules for adding tools to a ZapSign MCP server. MCP is a standard way for AI assistants to call external tools and services.

Use it when implementing or reviewing ZapSign tools, especially their server registration, authentication checks, permission checks, input schemas, and response handling.

It keeps tool files, registration, authentication, permissions, error handling, and safety metadata consistent across the codebase.

tool-pattern — Cursor rule by ZapSign

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/zapsign/api-mcp/tool-pattern

Clone the repo

git clone --depth 1 https://github.com/ZapSign/api-mcp

Made for: Cursor.

Per session 0 Nothing until a file matches its globs; then the whole rule loads.

When invoked 525 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.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.00525
Opus 5	$0.00000	$0.00262
Sonnet 5	$0.00000	$0.00105
Haiku 4.5	$0.00000	$0.00052

Measured yesterday against content hash 56feba05cf58, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tool-pattern 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 yesterday.

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/tool-pattern.mdc · 48 lines

What it actually says

Tool Implementation Pattern

File Structure

Each file exports ONE function: registerXxxTool(server: McpServer): void
The registry (src/tools/registry.ts) is the ONLY file that imports tool modules

Required Imports

McpServer from @modelcontextprotocol/sdk/server/mcp.js
getMcpAuthContext from agents/mcp
ZapSignClient from ../../api/client
formatToolSuccess, formatToolError from ../../utils/tool-response
AuthProps from ../../auth/types
ZapSignMcpError from ../../errors/base
requireScope from ../../utils/scope
Schemas from ./schemas

server.registerTool() Call

Use registerTool (NOT deprecated server.tool()):

server.registerTool('tool_name', { title, description, inputSchema: XxxSchema.shape, annotations: { readOnlyHint, destructiveHint, idempotentHint, openWorldHint: true } }, handler)

Handler Pattern (5 steps)

const auth = getMcpAuthContext() — no generic (SDK does not support it)
Guard: if (!auth) return formatToolError('Authentication required...')
const props = auth.props as unknown as AuthProps — cast needed, SDK types props as Record
requireScope(props.grantedScope, 'scope:level') — enforced per tool
const client = new ZapSignClient(props.zapSignApiUrl, props.zapSignApiToken)
const result = await client.method(args)
return formatToolSuccess(JSON.stringify(result)) — compact JSON, no pretty-print

Error Handling

Catch ZapSignMcpError → formatToolError(error.message)
Catch unknown → formatToolError('An unexpected error occurred')
NEVER throw from a tool handler — always return formatToolError

Annotations (required on every tool)

readOnlyHint: true for GET tools, false for write tools
destructiveHint: true only for DELETE tools
idempotentHint: true for GET and PATCH tools
openWorldHint: true (all tools call external ZapSign API)
title: human-readable name for Claude.ai display

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.

yesterday First seen · 48 lines · 0 tokens per session scan A 56feba05cf58

Subscribe to this mod's changes

tool-pattern is a cursor rule published in the GitHub repository ZapSign/api-mcp (1 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 525 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.

tool-pattern

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

Tool Implementation Pattern

File Structure

Required Imports

server.registerTool() Call

Handler Pattern (5 steps)

Error Handling

Annotations (required on every tool)

What this file has done since we first saw it

Other cursor rules, from other repositories

angular-20

dev-standard

typescript

coolify-ai-docs

python_lib

specs