What is llmconveyors-mcp CLAUDE.md?

A set of project instructions for working on llmconveyors-mcp, an MCP server that gives AI coding tools access to LLM Conveyors features. It describes the project structure, authentication, tools, and shared error handling.

Use it when developing or maintaining llmconveyors-mcp and its TypeScript tool groups, settings, sessions, documents, or related utilities.

It gives coding agents the project-specific context needed to make consistent changes in the right files.

How ebenezer-isaac/llmconveyors-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to ebenezer-isaac/llmconveyors-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/ebenezer-isaac/llmconveyors-mcp/master/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/ebenezer-isaac/llmconveyors-mcp

Made for: Claude Code.

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/ebenezer-isaac/llmconveyors-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/ebenezer-isaac/llmconveyors-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/ebenezer-isaac/llmconveyors-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/ebenezer-isaac/llmconveyors-mcp/claude-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/ebenezer-isaac/llmconveyors-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/ebenezer-isaac/llmconveyors-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,331 This file is loaded in full into every session.

When invoked 2,331 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	$0.02331	$0.02331
Opus 5	$0.01166	$0.01166
Sonnet 5	$0.00466	$0.00466
Haiku 4.5	$0.00233	$0.00233

Measured 12d ago against content hash 6deca140e0d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

llmconveyors-mcp CLAUDE.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 12d 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.

CLAUDE.md · 209 lines

How it starts

The opening of the file, as written. The whole thing — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.

llmconveyors-mcp

MCP server that exposes all LLM Conveyors platform capabilities as 66 tools for AI agents (Claude Code, Claude Desktop, Cursor, etc.).

Architecture

Protocol: Model Context Protocol (MCP) via @modelcontextprotocol/sdk
Transport: stdio (standard for MCP servers)
SDK: Uses the llmconveyors npm package (TypeScript SDK) as the API client
Auth: LLMC_API_KEY env var (prefix llmc_)
Base URL override: Optional LLMC_BASE_URL env var

Project Structure

src/
  index.ts              — Entry point: creates MCP server, wires up all 12 tool groups
  utils/
    error-handler.ts    — Shared error handler (LLMConveyorsError, RateLimitError, NetworkError, TimeoutError)
  tools/
    agents.ts           — FULLY IMPLEMENTED (6 tools)
    ats.ts              — FULLY IMPLEMENTED (1 tool)
    resume.ts           — FULLY IMPLEMENTED (10 tools)
    upload.ts           — FULLY IMPLEMENTED (3 tools)
    sessions.ts         — FULLY IMPLEMENTED (9 tools)
    settings.ts         — FULLY IMPLEMENTED (16 tools)
    content.ts          — FULLY IMPLEMENTED (6 tools)
    shares.ts           — FULLY IMPLEMENTED (4 tools)
    documents.ts        — FULLY IMPLEMENTED (1 tool)
    referral.ts         — FULLY IMPLEMENTED (3 tools)
    privacy.ts          — FULLY IMPLEMENTED (3 tools)
    health.ts           — FULLY IMPLEMENTED (4 tools)

Shared Utilities

`src/utils/error-handler.ts`

All tool handlers use handleToolError(err) instead of inline try/catch formatting. It:

Extracts structured fields from LLMConveyorsError (code, statusCode, hint, details, requestId, retryable, timestamp, path)
Extracts retryAfterSeconds, retryAfterMs, and rateLimitInfo from RateLimitError
Handles NetworkError and TimeoutError with retryable: true signal
Falls back to plain error message for unknown errors
Always returns { content, isError: true } in MCP format

How to implement a tool

Follow the pattern established across all tool files:

Read the full file on GitHub · 209 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.

12d ago First seen · 209 lines · 2,331 tokens per session scan A 6deca140e0d3

Subscribe to this mod's changes

llmconveyors-mcp CLAUDE.md is an instructions file published in the GitHub repository ebenezer-isaac/llmconveyors-mcp (1 stars, last pushed 5mo ago), licensed MIT. It adds 2,331 tokens to every session, about $0.0117 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 2026-08-30.

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

llmconveyors-mcp: Instructions file for Claude Code