mcp-server AGENTS.md

Project instructions for connecting to The Code Registry, a service that creates and analyzes code collections. They document its MCP server, available-resource discovery, authentication, and how clients should pass tool inputs.

In plain words
What is it for?
Use them when configuring the server, discovering tools and documentation, creating code vaults, or troubleshooting tool arguments and authentication.
Why use it?
They give coding agents the connection details and calling rules needed to use the service correctly, including a workaround for some client displays.

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/the-code-registry/mcp-server/agents-md
Clone the repo
git clone --depth 1 https://github.com/The-Code-Registry/mcp-server

Made for: Codex, OpenCode.

Per session 1,531 This file is loaded in full into every session.
When invoked 1,531 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 $0.01531 $0.01531
Opus 5 $0.00766 $0.00766
Sonnet 5 $0.00306 $0.00306
Haiku 4.5 $0.00153 $0.00153

Measured yesterday against content hash 74c9651735d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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.

AGENTS.md · 190 lines

How it starts

The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This project exposes an MCP server for creating and analyzing code vaults via The Code Registry - the World's first code intelligence and insight platform built for business leaders.

MCP endpoints

  • Web app: https://app.thecoderegistry.com
  • MCP server: https://integrator.app.thecoderegistry.com (POST to /api/ai/router)

Discovery

Use tools/list to discover available MCP tools and their input schemas. Use resources/list and resources/read for documentation, workflows, and examples. Use prompts/list and prompts/get for curated prompt templates.

Client compatibility note (Cursor / CallMcpTool wrappers)

  • Known issue in some clients (notably some Cursor builds): the displayed CallMcpTool schema may omit arguments even though runtime forwarding supports it.
  • For The Code Registry tools, always pass required tool inputs via CallMcpTool.arguments.
  • If a tool has no required inputs, use arguments: {} for consistency.
  • Example wrapper call shape:
{
  "server": "coderegistry",
  "toolName": "create-code-vault",
  "arguments": {
    "project_id": "<project_id>",
    "user_id": "<user_id>",
    "name": "My Code Vault",
    "source_type": "LOCAL_AGENT"
  }
}

Authentication

  • create_account does not require an API key.
  • All other MCP actions require X-API-Key using the key returned by create_account.
  • Existing users can generate an API key in the web app and provide it directly via X-API-Key.
  • If an MCP client cannot set custom headers, include api_key in the tool arguments. Header auth is preferred when available.

Plan behavior

  • Free tier is limited to 100,000 total lines of code across all vaults.
  • Free tier should still support registration, project/vault lifecycle, code sync, and summary-level analysis retrieval.
  • Paid plans unlock extended functionality and richer payloads (for example full findings, verification badges/public verification pages, and Code Score out of 1,000).
  • If a feature is plan-restricted, return the service error and direct users to upgrade in the web app.

Read the full file on GitHub · 190 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. yesterday First seen · 190 lines · 1,531 tokens per session scan A 74c9651735d3

Subscribe to this mod's changes

mcp-server AGENTS.md is an instructions file published in the GitHub repository The-Code-Registry/mcp-server (1 stars, last pushed 2mo ago), licensed MIT. It adds 1,531 tokens to every session, about $0.0077 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.