meshy-mcp-server: Instructions file for Claude Code

CLAUDE.md

meshy-mcp-server CLAUDE.md is an instructions file for Claude Code from gwizards/meshy-mcp-server. It costs 729 tokens per session, scanned A, original, MIT.

A project instruction guide for a Meshy MCP server, a program that lets coding agents use Meshy through a standard tool connection. It documents how the server is built, run, tested, and organised.

In plain words
What is it for?
Use it when building, running, testing, or modifying the server’s TypeScript code, API task handlers, validation, and error handling.
Why use it?
It gives an agent the project’s working rules and important implementation details, reducing guesswork when changing or testing the server.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is gwizards/meshy-mcp-server's own configuration. It tells Claude Code how to work on meshy-mcp-server itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything meshy-mcp-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to gwizards/meshy-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/gwizards/meshy-mcp-server/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/gwizards/meshy-mcp-server

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for meshy-mcp-server CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/gwizards/meshy-mcp-server/claude-md/github.svg)](https://agentmods.dev/instructions/gwizards/meshy-mcp-server/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/gwizards/meshy-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/gwizards/meshy-mcp-server/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for meshy-mcp-server CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/gwizards/meshy-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/gwizards/meshy-mcp-server/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 729 This file is loaded in full into every session.
When invoked 729 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00729 $0.00729
Opus 5.5 $0.00292 $0.00292
Sonnet 5.5 $0.00146 $0.00146
Haiku 4.5 $0.00073 $0.00073

Measured 2mo ago against content hash 72d765454e6a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

meshy-mcp-server CLAUDE.md 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 2mo 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.

CLAUDE.md · 50 lines

How it starts

The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Meshy MCP Server

Build & Run

  • npm run build — compile TypeScript to dist/
  • npm run dev — run with tsx (hot reload)
  • npm test — run tests with vitest
  • npm start — run compiled server

Architecture

Two source files:

  • src/index.ts — MCP server setup, 36 tool definitions (34 CRUD + wait_for_task + get_balance), validation, error handling. Exports createServer(apiKey?) for testing. Version read from package.json at runtime. Rigging and animation have no list tools (Meshy API does not expose list endpoints for these types).
  • src/meshy-client.ts — Meshy API HTTP client with retry logic. Exports TaskType union and TASK_TYPES const. Public API: createTask(taskType, params), getTask(taskType, id), deleteTask(taskType, id), listTasks(taskType, pageNum, pageSize, sortBy?), getBalance()

Key Patterns

  • taskId and paginationSchema are module-level constants — created once, not per createServer() call
  • Repetitive GET/DELETE/LIST handlers use makeGetHandler, makeDeleteHandler, makeListHandler factories
  • taskCreated(id, taskType) formats all create success messages consistently with a typed TaskType param
  • All tool handlers wrap in try-catch and return { isError: true } on failure
  • MeshyClient.request() computes backoffDelay once per retry iteration, used by both network and HTTP error paths
  • Retry logic retries 429/5xx with exponential backoff; respects Retry-After header on 429
  • wait_for_task checks remaining time before sleeping (not after) to avoid timeout overshoot
  • MeshyClient.listPath() builds paginated query strings — used by all 7 list methods
  • Task IDs validated with regex /^[a-zA-Z0-9_-]+$/ and encoded with encodeURIComponent() in URL paths
  • Create handlers validate result.result exists before returning task ID
  • Conditional validation in create tools (e.g., prompt required for preview mode)
  • Content-Type header only sent when request body is present
  • Non-JSON API responses and empty bodies (on non-DELETE) throw descriptive errors

Read the full file on GitHub · 50 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. 2mo ago First seen · 50 lines · 729 tokens per session scan A 72d765454e6a

Subscribe to this mod's changes

meshy-mcp-server CLAUDE.md is an instructions file published in the GitHub repository gwizards/meshy-mcp-server (1 stars, last pushed 7mo ago), licensed MIT. It adds 729 tokens to every session, about $0.0029 per session on Opus 5.5. 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 2026-08-31.

Related

meshy-mcp-server CLAUDE.md compared with instructions from other repositories

meshy-mcp-server CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
meshy-mcp-server CLAUDE.mdgwizards/meshy-mcp-serverInstructions file17mo agoMITA729Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode