Borrowing it
Nothing to install: this file belongs to aloki-alok/mcpify. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/aloki-alok/mcpify/main/AGENTS.mdgit clone --depth 1 https://github.com/aloki-alok/mcpifyWrote 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.
[](https://agentmods.dev/instructions/aloki-alok/mcpify/agents-md)<a href="https://agentmods.dev/instructions/aloki-alok/mcpify/agents-md"><img src="https://agentmods.dev/badge/instructions/aloki-alok/mcpify/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.
<a href="https://agentmods.dev/instructions/aloki-alok/mcpify/agents-md"><img src="https://agentmods.dev/badge/instructions/aloki-alok/mcpify/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00471 | $0.00471 |
| Opus 5.5 | $0.00188 | $0.00188 |
| Sonnet 5.5 | $0.00094 | $0.00094 |
| Haiku 4.5 | $0.00047 | $0.00047 |
Grade A, and why
mcpify AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
AGENTS.md
mcpify turns an OpenAPI spec (file or URL) into a working MCP server in one command. Go. Each operation becomes one tool that proxies the real HTTP call.
Commands
- Build:
go build ./... - Test:
go test ./... - Vet:
go vet ./... - Run against a spec:
go run . ls examples/petstore.yaml(lists tools) - Serve over stdio:
go run . serve examples/petstore.yaml(mcpify helplists commands)
Layout
main.go: entry point.internal/openapi/: parses the spec and inlines local$refs. Includes Swagger 2.0 conversion.internal/tool/: turns each operation into a tool and builds its HTTP request. Also naming and filtering.internal/server/: wires the tools into an MCP server and proxies calls.internal/cli/: commands (serve,ls,upgrade, plus connect helpers) and flag parsing.internal/upgrade/,internal/ui/: self-update and terminal output.examples/petstore.yaml: a small spec for manual runs.DESIGN.md: the problem, non-goals and shape. Read it before a large change..goreleaser.yaml,install.sh: release and install. Release runs on tags.
Rules
- One operation maps to one tool, 1:1. No merged tools, synthetic workflows or response reshaping.
- Auth is pass-through. Forward the headers the user supplies. Do not store tokens or add OAuth or rate limiting.
- It is not a code generator. It runs the proxy and re-reads the spec on every start.
- Keep dependencies few. Give a reason in the PR for any new one.
- Add a test for changed behavior, mainly in
internal/openapiandinternal/tool. A wrong result there builds the wrong request. - Redact tokens in issues, tests and examples.
- Keep each PR to one concern.
Before you open a PR
CI runs these on every PR.
go vet ./...go test ./...go build ./...
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 · 42 lines · 471 tokens per session scan A 8388ee9ce268
mcpify AGENTS.md is an instructions file published in the GitHub repository aloki-alok/mcpify (2 stars, last pushed 2d ago), licensed MIT. It adds 471 tokens to every session, about $0.0019 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 2026-11-07.
mcpify AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mcpify AGENTS.mdaloki-alok/mcpify | Instructions file | 2 | 2d ago | MIT | A | 471 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |