mcp-server CLAUDE.md

mcp-server CLAUDE.md is an instructions file for coding agents from Repliers-io/mcp-server. It costs 1,225 tokens per session, scanned A, original, MIT.

A set of Claude Code instructions for an MCP server that exposes a real-estate listing API to AI agents. An API is a structured way for software to request data and actions from another service.

In plain words
What is it for?
Use it when developing or maintaining the server, running it over standard input or HTTP, testing it, listing available tools, or regenerating tools from the API specification.
Why use it?
It gives agents the project's architecture, commands, testing guidance, and rules for changing generated API tools safely.

Instructions file

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/repliers-io/mcp-server/claude-md
Clone the repo
git clone --depth 1 https://github.com/Repliers-io/mcp-server

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 mcp-server CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/repliers-io/mcp-server/claude-md.svg)](https://agentmods.dev/instructions/repliers-io/mcp-server/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/repliers-io/mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/repliers-io/mcp-server/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,225 This file is loaded in full into every session.
When invoked 1,225 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 5.1 $0.01225 $0.01225
Opus 5 $0.00613 $0.00613
Sonnet 5 $0.00245 $0.00245
Haiku 4.5 $0.00122 $0.00122

Measured yesterday against content hash d7c62f01a8ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

mcp-server 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 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.

CLAUDE.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repliers MCP Server — Agent Instructions

MCP server exposing the Repliers MLS API to AI agents (claude.ai connectors, IDE agents, custom clients). Node.js 22+, ESM, @modelcontextprotocol/sdk. Two transports in one entry point: stdio (default) and Streamable HTTP.

Commands

node mcpServer.js            # stdio transport
node mcpServer.js --http     # Streamable HTTP on PORT (default 3001), endpoint /mcp
npm test                     # node --test test/**/*.test.js
npm run list-tools           # print the tool roster (index.js CLI)
npm run generate             # regenerate tools/…/generated/ from openapi.json

Architecture

Path Role
mcpServer.js Server entry: both transports, session handling, attaches _feedback nudges to every tool response via lib/feedbackHints.js, serves instructions from lib/serverInstructions.js
lib/tools.js discoverTools() — loads every .js from tools/repliers/repliers-api/{generated,custom}/ exporting apiTool
tools/repliers/repliers-api/generated/ 39 tools generated from openapi.json (npm run generate) — CRM, estimates, locations, saved searches… Do not edit by hand
tools/repliers/repliers-api/custom/ 6 hand-written tools: search-listings (NLP search + appliedFilters enrichment), refine-search, send-feedback, statistics, get-parameter-enumerations, get-listing-image
lib/apiBase.js apiBaseUrl() / apiOrigin() — the only place the API host is written. Generated tools import it (the codegen template emits the call, so regeneration preserves it); never hardcode the host anywhere else
lib/appliedFilters.js Parses the NLP-built listing URL into the human-readable appliedFilters summary, and flags params the API discards in appliedFilters.unrecognized (checked against the /listings parameter set in openapi.json, read lazily — /nlp reports unrecognizedParams: [] even when /listings rejects the param)
lib/feedbackHints.js Failure detectors (no-location-filter, zero-results, api-error…) + eagerness levels → _feedback block
lib/feedbackCard.js, lib/trello.js Feedback card formatting + Trello REST delivery
test/ Unit tests (node:test), one file per lib/tool module

Read the full file on GitHub · 56 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 · 56 lines · 1,225 tokens per session scan A d7c62f01a8ec

Subscribe to this mod's changes

mcp-server CLAUDE.md is an instructions file published in the GitHub repository Repliers-io/mcp-server (17 stars, last pushed today), licensed MIT. It adds 1,225 tokens to every session, about $0.0061 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 2026-09-04.

Related

Other instructions, from other repositories

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 · 5,182 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

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

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

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens