buda-mcp AGENTS.md

buda-mcp AGENTS.md is an instructions file for Codex, OpenCode from gtorreal/buda-mcp. It costs 922 tokens per session, scanned A, original, MIT.

Project instructions for gtorreal/buda-mcp, an MCP server that exposes Buda.com’s public market-data API to AI assistants. It documents the project layout, commands, tests, and coding rules.

In plain words
What is it for?
Use it when developing, testing, or reviewing buda-mcp, including its TypeScript server, API client, cache, validation, tools, and marketplace files.
Why use it?
It gives coding agents the project context and constraints needed to make changes without breaking established behavior.

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/gtorreal/buda-mcp/agents-md
Clone the repo
git clone --depth 1 https://github.com/gtorreal/buda-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.

agentmods badge for buda-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/gtorreal/buda-mcp/agents-md.svg)](https://agentmods.dev/instructions/gtorreal/buda-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/gtorreal/buda-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/gtorreal/buda-mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 922 This file is loaded in full into every session.
When invoked 922 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 $0.00922 $0.00922
Opus 5 $0.00461 $0.00461
Sonnet 5 $0.00184 $0.00184
Haiku 4.5 $0.00092 $0.00092

Measured 4d ago against content hash ba6872090377, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

buda-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 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 · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — buda-mcp

MCP server exposing Buda.com public REST API v2 as tools and resources for AI assistants. No API key required (v2.0.0+).

Layout

src/index.ts          stdio MCP server entrypoint
src/http.ts           HTTP/SSE MCP server entrypoint (Express, stateless)
src/client.ts         BudaClient — fetch wrapper, 429 retry, error sanitization
src/cache.ts          In-memory TTL cache with in-flight deduplication
src/validation.ts     validateMarketId(), validateCurrency()
src/utils.ts          flattenAmount(), aggregateTradesToCandles(), etc.
src/format.ts         Shared markdown formatting helpers (liquidityBadge, fmtSlippage, fmtTimestamp)
src/version.ts        Version string (reads package.json)
src/types.ts          TypeScript types for Buda API responses
src/tools/            One file per tool — each exports register(), toolSchema, handler
test/unit.ts          Unit tests (no network)
test/run-all.ts       Integration tests (live API, skips if unreachable)
marketplace/          Listing artifacts (openapi.yaml, gemini-tools.json, claude-listing.md)
scripts/              sync-version.mjs

Commands

  • Install: npm install
  • Dev (stdio): npm run dev
  • Dev (HTTP): npm run dev:http
  • Build: npm run build
  • Test (all): npm test
  • Test (unit only): npm run test:unit
  • Test (integration): npm run test:integration
  • Sync version: npm run sync-version
  • Publish: npm publish --access public --provenance

Invariants

NEVER violate without an ADR amendment.

  • Public-only API. No authenticated/private tools exist since v2.0.0. NEVER accept or require API keys. The with-auth branch preserves legacy auth code.
  • Tool output is markdown. Every tool MUST return pre-formatted markdown via content: [{ type: "text", text }]. Use src/format.ts helpers. NEVER return raw JSON.stringify.
  • Agent passthrough. Downstream agents MUST relay tool output verbatim — no re-summary, re-table, or paraphrase unless the user asks.
  • Input validation before URL interpolation. MUST call validateMarketId() or validateCurrency() before building API paths. Validation errors MUST use static strings — NEVER embed user input.
  • Error sanitization. Internal details (paths, stack traces) go to stderr only. Callers see generic messages via formatApiError().
  • Dual entrypoint registration. New tools MUST be registered in both src/index.ts (stdio) and src/http.ts (HTTP).
  • Version in package.json only. Run npm run sync-version after bumping. NEVER hardcode version strings.

Read the full file on GitHub · 70 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 · 70 lines · 922 tokens per session scan A ba6872090377

Subscribe to this mod's changes

buda-mcp AGENTS.md is an instructions file published in the GitHub repository gtorreal/buda-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 922 tokens to every session, about $0.0046 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 2026-08-31.

Related

Other instructions, from other repositories