mcp-server: Instructions file for Codex

AGENTS.md

mcp-server AGENTS.md is an instructions file for Codex, OpenCode from synchronicity-labs/mcp-server. It costs 1,944 tokens per session, scanned A, original, MIT.

Repository instructions for coding agents working on the Sync MCP server. They describe where major parts of the code live, how the hosted and local versions run, and which deployment and tool rules matter.

In plain words
What is it for?
Use them when changing the Sync server, its tools, HTTP handling, client profiles, generated API code, or deployment-related behavior.
Why use it?
They give an agent the project-specific context needed to edit the right files and respect the repository's release and access conventions.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions AGENTS.md.

This is synchronicity-labs/mcp-server's own configuration. It tells Codex and OpenCode how to work on 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 mcp-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to synchronicity-labs/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/synchronicity-labs/mcp-server/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/synchronicity-labs/mcp-server

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-server AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/synchronicity-labs/mcp-server/agents-md/github.svg)](https://agentmods.dev/instructions/synchronicity-labs/mcp-server/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/synchronicity-labs/mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/synchronicity-labs/mcp-server/agents-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 mcp-server AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/synchronicity-labs/mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/synchronicity-labs/mcp-server/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,944 This file is loaded in full into every session.
When invoked 1,944 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 $0.01944 $0.01944
Opus 5.5 $0.00778 $0.00778
Sonnet 5.5 $0.00389 $0.00389
Haiku 4.5 $0.00194 $0.00194

Measured today against content hash 6f8176915b74, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-server 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 today.

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 · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Guide for coding agents working in this repository. CLAUDE.md links here.

What this is

sync.'s MCP server. It runs two ways from the same code:

  • Hosted at https://mcp.sync.so/mcp: Streamable HTTP, OAuth proxied to api.sync.so, one Porter replica. ChatGPT, Claude.ai, Claude Code, Cursor and Codex connect here.
  • stdio through npx @sync.so/mcp-server with SYNC_API_KEY, for local clients.

Every merge to main deploys production. Treat each merge as a release. A merge that changes version in package.json also publishes that version to npm (.github/workflows/publish.yml); merges that keep the version only deploy. server.json is the MCP Registry listing. Its version must equal package.json's, and a merge that changes it publishes the listing (.github/workflows/publish-mcp-registry.yml). The registry never replaces a published version, so bump both versions in any PR that edits server.json.

Where things live

Path Owns
src/server.ts Tool assembly, HOSTED_HTTP_TOOL_ALLOWLIST, per-profile visibility (isAppOnlyTool), instructions (INSTRUCTION_PARTS), tools/list descriptors
src/client-profile.ts Maps the handshake client name to a presentation profile (chatgpt, codex, claude, generic). Presentation only, never permissions
src/tools/ Hand-written tools; generator.ts turns public OpenAPI operations into generated tools
src/openapi/ Fetches and parses api.sync.so/api-json at startup
src/http-server.ts, src/http-session.ts, src/session-registry.ts Express app, OAuth proxy routes, /mcp, /health, request-scoped MCP sessions
src/rate-limits.ts Request limits per verified user and OAuth client, plus per-address limits on rejected credentials
src/auth/ OAuth proxy provider (SDK server-legacy), bearer verification, device auth for stdio
src/chatgpt-app.ts, deploy/chatgpt/ Immutable ChatGPT UI releases built from sync-api-v2 apps/chatgpt; see docs/chatgpt-release.md
chatgpt-plugin/ ChatGPT and Codex plugin package: manifest, listing copy, and skills.source.json, the pinned commit of synchronicity-labs/skills it packages skills from; see docs/chatgpt-plugin.md
server.json MCP Registry listing: name, description, remote URL; scripts/check-server-json.mjs keeps it publishable
glama.json GitHub users who can claim and edit the Glama listing
scripts/ Memory and session suites, UI packaging, monitor, post-deploy smoke check, pre-commit size check
docs/ Maintainer notes (docs/maintainers.md), release, availability and auth details

Read the full file on GitHub · 94 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. today Changed · +11 lines · +308 tokens per session 6f8176915b74
  2. 3d ago Changed · +2 lines · +106 tokens per session b71283606224
  3. 6d ago First seen · 81 lines · 1,530 tokens per session scan A a261439d4f69

Subscribe to this mod's changes

mcp-server AGENTS.md is an instructions file published in the GitHub repository synchronicity-labs/mcp-server (1 stars, last pushed yesterday), licensed MIT. It adds 1,944 tokens to every session, about $0.0078 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 2026-10-31.

Related

mcp-server AGENTS.md compared with instructions from other repositories

mcp-server AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
mcp-server AGENTS.mdsynchronicity-labs/mcp-serverInstructions file1yesterdayMITA1,944Codex, OpenCode
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