What is mcp AGENTS.md?

Instructions for working with the generated Typeship package, which resolves API definitions and keeps related SDKs, command-line tools, and agent targets current.

Using the Typeship API or MCP server, authenticating with a bearer token, reading its API references, and avoiding edits that regeneration would erase.

They explain the package's rules, authentication, generated-code limits, and available interfaces so agents can use it safely and correctly.

How typeship-ax/mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to typeship-ax/mcp. 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/typeship-ax/mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/typeship-ax/mcp

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/typeship-ax/mcp/agents-md/github.svg)](https://agentmods.dev/instructions/typeship-ax/mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/typeship-ax/mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/typeship-ax/mcp/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/typeship-ax/mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/typeship-ax/mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 734 This file is loaded in full into every session.

When invoked 734 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.

Model	Per session	Once invoked
Fable 5.1	$0.00734	$0.00734
Opus 5.5	$0.00294	$0.00294
Sonnet 5.5	$0.00147	$0.00147
Haiku 4.5	$0.00073	$0.00073

Measured 1mo ago against content hash b99b574076c2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp 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 1mo 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 · 42 lines

How it starts

The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Typeship: agent guide

Instructions for coding agents that call the Typeship API through this MCP server (API version 1.0.0, package version 0.23.0).

Resolve an OpenAPI or GraphQL Spec, diagnose it, and keep every selected CLI, MCP, and SDK Target current.

Every operation but one requires a bearer credential: an organization API key from the console, or an OAuth access token carrying the operation's read, generate, or write capability and the organization selected during consent. OAuth grants cannot switch organizations after consent. A browser session is not a credential for this API. The exception is POST /generate, which works anonymously with the free plan's limits.

Examples use Parcel, a fictional delivery service. Replace its domains, repository names, and resource identifiers with your own. The hosted petstore Spec is a runnable sample.

Before writing code

api.md is the tool and schema reference; api.json is the machine-readable contract: every operation's inputs, outputs, errors, safety (read, write, or destructive), and an example. Look up exact names there instead of guessing.
README.md covers installation and setup.
Zero runtime dependencies; the program runs on Node.js 20+ and platform fetch.

Authentication

Bearer token: set the TYPESHIP_TOKEN environment variable.

MCP server

README.md shows how to connect an MCP client. The server supports MCP 2025-11-25 and 2026-07-28 and picks the version automatically; clients need no protocol flags.
Clients start the server with npx -y --package @typeship-ax/mcp typeship-mcp. Set the auth environment variables in the client's configuration; --read-only removes write tools.
This package exposes the compact search_docs, read_docs, and execute surface. Find an operation, read its arguments and example with read_docs, then call execute with its name and arguments; destructive operations return CONFIRMATION_REQUIRED until repeated with confirm: true. Operation names are not directly callable tools in this mode.
Tool arguments are checked against the schema before any request (unknown or mistyped arguments are one isError result with per-argument issues); pass fields (dotted paths) to keep only the result keys you need; errors carry code and next_steps.

Read the full file on GitHub · 42 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.

1mo ago Changed b99b574076c2
1mo ago Changed · +4 lines · +46 tokens per session 6a623f45b499
1mo ago Changed f841cf09442d
1mo ago Changed · +1 lines · +7 tokens per session 741ea4d5daf4
1mo ago Changed · +4 lines · +34 tokens per session a41eff637855
1mo ago Changed · +1 lines · +48 tokens per session 93c1f2bb9a4d
1mo ago Changed a3d09a68c4d8
1mo ago Changed · +1 lines · +61 tokens per session e70e258f755a
2mo ago Changed · +14 tokens per session 417a4489dac9
2mo ago First seen · 31 lines · 524 tokens per session scan A 581cbe5efbd0

Subscribe to this mod's changes

mcp AGENTS.md is an instructions file published in the GitHub repository typeship-ax/mcp (0 stars, last pushed 23d ago), licensed MIT. It adds 734 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.

mcp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mcp AGENTS.mdtypeship-ax/mcp	Instructions file	0	23d ago	MIT	A	734	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

mcp: Instructions file for Codex