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.
npx agentmods add instructions/supavec/mcp-server/claude-mdgit clone --depth 1 https://github.com/supavec/mcp-serverWrote 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/supavec/mcp-server/claude-md)<a href="https://agentmods.dev/instructions/supavec/mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/supavec/mcp-server/claude-md.svg" alt="Measured on agentmods" 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 | $0.00612 | $0.00612 |
| Opus 5 | $0.00306 | $0.00306 |
| Sonnet 5 | $0.00122 | $0.00122 |
| Haiku 4.5 | $0.00061 | $0.00061 |
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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
This is a Model Context Protocol (MCP) server that enables AI assistants to interact with Supavec's embeddings API. The server provides two main tools:
fetch-embeddings: Retrieves relevant content from Supavec files using embeddingslist-user-files: Lists all files uploaded to a user's Supavec account
Commands
Build & Development
# Build the project (compiles TypeScript to build/ directory)
npm run build
# Build and watch for changes during development
npm run watch
# Test the server with MCP Inspector
npm run inspector
# Test the CLI directly
npm run build && node build/index.js --help
Running the Server
# With API key argument
node build/index.js --api-key your_api_key
# With environment variable
SUPAVEC_API_KEY=your_key node build/index.js
# Show help
node build/index.js --help
Architecture
Entry Point (src/index.ts)
- Handles CLI argument parsing and API key validation
- Creates and starts the MCP server
- API key priority:
--api-keyargument >SUPAVEC_API_KEYenvironment variable
Core Components
Server Setup (src/utils/server.ts)
- Creates MCP server instance using
@modelcontextprotocol/sdk - Configures server with stdio transport for MCP communication
- Sets up tool handlers
Tool Definitions (src/tools/index.ts)
- Defines the two MCP tools with their schemas
- Handles tool execution by calling Supavec API endpoints
- Returns structured JSON responses to AI assistants
API Layer (src/utils/api.ts)
- Centralized HTTP client for Supavec API (
https://api.supavec.com) - Handles authentication via
authorizationheader - Provides error handling and type-safe responses
CLI Utilities (src/utils/cli.ts)
- Parses command line arguments (supports
--api-keyand--help) - Displays help information
Type Definitions (src/types/index.ts)
Embeddings: Response structure for embedding queriesUserFile: Individual file metadata from SupavecUserFilesResponse: Paginated response for file listingsUserFilesRequest: Request parameters for file listings
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.
- 3d ago First seen · 90 lines · 612 tokens per session scan A 50c26f9dbd01
mcp-server CLAUDE.md is an instructions file published in the GitHub repository supavec/mcp-server (4 stars, last pushed 1y ago), licensed MIT. It adds 612 tokens to every session, about $0.0031 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.
Other instructions, from other repositories
PixelRAG CLAUDE.md
Instructions for StarTrail-org/PixelRAG, covering pixelrag, layout and conventions.
gpt-rag-ingestion azure-boundaries.instructions.md
Instructions for Azure/gpt-rag-ingestion, a project described as: The GPT-RAG Data Ingestion service automates processing of diverse documents—PDFs, images, spreadsheets, transcripts, and SharePoint—readying them for Azure AI Search. It applies smart chunking, generates text and image embeddings, and enables rich…
OpenDocuments AGENTS.md
Instructions for joungminsung/OpenDocuments, covering agents.md, project overview, monorepo structure, common commands and 특정 패키지만.
pdf-inline-image-rag-mcp AGENTS.md
AGENTS.md instructions for Joncallim/pdf-inline-image-rag-mcp, covering pdf inline image rag mcp agent guide, invariants, repository map, focused workflow and validation.
doctree-mcp CLAUDE.md
Claude Code instructions for joesaby/doctree-mcp, covering claude.md — doctree-mcp, project overview, architecture, key design decisions and data flow.
google-drive-rag-mcp AGENTS.md
AGENTS.md instructions for asamiile/google-drive-rag-mcp, covering google drive rag mcp — agent instructions, project overview, key files, running the server and install dependencies.