mcp-ts AGENTS.md

mcp-ts AGENTS.md is an instructions file for Codex, OpenCode from zonlabs/mcp-ts. It costs 1,690 tokens per session, scanned A, original, MIT.

A TypeScript monorepo for building MCP applications. A monorepo is one repository containing several related packages, including a client SDK, a tool router and sandboxed programmatic tool execution.

In plain words
What is it for?
Building MCP clients and servers, storing sessions across different backends, adding OAuth 2.1, connecting React or Vue interfaces, adapting agents and running tools in a sandbox.
Why use it?
It groups the shared building blocks for MCP clients and servers in one codebase. Tool routing can help avoid loading every available tool description into an AI model at once.

Instructions file for CodexOpenCode

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 instructions/zonlabs/mcp-ts/agents-md
Clone the repo
git clone --depth 1 https://github.com/zonlabs/mcp-ts

Made for: Codex, OpenCode.

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 mcp-ts AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/zonlabs/mcp-ts/agents-md.svg)](https://agentmods.dev/instructions/zonlabs/mcp-ts/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/zonlabs/mcp-ts/agents-md"><img src="https://agentmods.dev/badge/instructions/zonlabs/mcp-ts/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,690 This file is loaded in full into every session.
When invoked 1,690 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 $0.01690 $0.01690
Opus 5 $0.00845 $0.00845
Sonnet 5 $0.00338 $0.00338
Haiku 4.5 $0.00169 $0.00169

Measured 4d ago against content hash b01e071fe0b5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-ts AGENTS.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 4d 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.

AGENTS.md · 153 lines

How it starts

The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — mcp-ts Monorepo

What is this?

mcp-ts is a TypeScript monorepo for building MCP (Model Context Protocol) applications. It provides:

  • @mcp-ts/client — core Client SDK with multi-backend session storage, OAuth 2.1, SSE handlers, React/Vue hooks, and agent framework adapters
  • @mcp-ts/tool-router — on-demand tool discovery to reduce LLM context bloat
  • @mcp-ts/codemode — sandboxed programmatic tool execution

The Client package is consumed by mcp-client (Next.js, hosted on Vercel) and mcp-server (Hono, hosted on Railway).

Repository Structure

mcp-ts/
  .github/workflows/   # CI/CD — release.yml auto-publishes to npm on version bumps
  .claude/              # Claude settings
  docs/                 # Mintlify documentation (docs.mcp-assistant.in)
  benchmarks/           # tool-router performance benchmarks
  AGENTS.md             # ← this file — project guide for AI agents and contributors
  README.md             # public-facing readme (npm-published for Client)
  package.json          # npm workspace root ("workspaces": ["packages/*"])
  packages/
    client/             # @mcp-ts/client
      src/
        server/
          storage/      # pluggable backends: neon, supabase, sqlite, redis, memory, file
          mcp/          # oauth-client, storage-oauth-provider, tool-policy-gateway
          handlers/     # sse-handler, nextjs-handler
        client/
          react/        # useMcp hook, McpAppRenderer, OAuth popup
          vue/          # Vue composable
          core/         # sse-client, app-host
        adapters/       # AI SDK, LangChain, Mastra, AG-UI
        shared/         # types, events, utils, constants
        bin/            # CLI (mcp-ts supabase-init)
      tests/            # Playwright tests per-backend + integration
      migrations/       # SQL migrations (neon/, supabase/, v2.3.4/)
      tsup.config.ts    # build config (multi-entry)
      playwright.config.ts
    code-mode/          # @mcp-ts/codemode
    tool-router/        # @mcp-ts/tool-router

Read the full file on GitHub · 153 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. 4d ago First seen · 153 lines · 1,690 tokens per session scan A b01e071fe0b5

Subscribe to this mod's changes

mcp-ts AGENTS.md is an instructions file published in the GitHub repository zonlabs/mcp-ts (24 stars, last pushed yesterday), licensed MIT. It adds 1,690 tokens to every session, about $0.0085 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.

Related

Other instructions, from other repositories

typescript-sdk CLAUDE.md

Claude Code instructions for modelcontextprotocol/typescript-sdk, covering claude.md, build & test commands, run a single package script (examples), breaking changes and code style guidelines.

modelcontextprotocol/typescript-sdk · 3,530 tokens

zypher-agent CLAUDE.md

Instructions for corespeed-io/zypher-agent, covering claude.md, development commands, code quality, architecture overview and monorepo structure.

corespeed-io/zypher-agent · 856 tokens

nestjs-starter interfaces.instructions.md

Instructions for hmake98/nestjs-starter, covering interface conventions, request interfaces (src/common/request/interfaces/), response interfaces (src/common/response/interfaces/) and rules.

hmake98/nestjs-starter · 287 tokens

own-planner frontend.instructions.md

Instructions for am-space/own-planner, covering frontend instructions, technology, coding rules and change preferences.

am-space/own-planner · 189 tokens

nestjs-starter controllers.instructions.md

Instructions for hmake98/nestjs-starter, a project described as: Production-ready NestJS boilerplate — JWT auth, Prisma, Redis, BullMQ, Swagger, i18n, and full AI developer workflows (Claude Code + GitHub Copilot) with spec-driven feature scaffolding.

hmake98/nestjs-starter · 193 tokens

nestjs-starter repositories.instructions.md

Instructions for hmake98/nestjs-starter, a project described as: Production-ready NestJS boilerplate — JWT auth, Prisma, Redis, BullMQ, Swagger, i18n, and full AI developer workflows (Claude Code + GitHub Copilot) with spec-driven feature scaffolding.

hmake98/nestjs-starter · 182 tokens