Borrowing it
Nothing to install: this file belongs to marccyberleda/openwebui-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/marccyberleda/openwebui-mcp-server/main/CLAUDE.mdgit clone --depth 1 https://github.com/marccyberleda/openwebui-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/marccyberleda/openwebui-mcp-server/claude-md)<a href="https://agentmods.dev/instructions/marccyberleda/openwebui-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/marccyberleda/openwebui-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 5.1 | $0.00712 | $0.00712 |
| Opus 5 | $0.00356 | $0.00356 |
| Sonnet 5 | $0.00142 | $0.00142 |
| Haiku 4.5 | $0.00071 | $0.00071 |
Grade A, and why
openwebui-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 6d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — openwebui-mcp-server
Project Overview
Open-source MCP server connecting Claude Code and Claude Desktop to Open WebUI.
GitHub: https://github.com/marccyberleda/openwebui-mcp-server
npm: npx openwebui-mcp-server
Stack
- Node.js >= 18 (ESM, native fetch)
@modelcontextprotocol/sdk(MCP protocol)- Zero other runtime dependencies
Rules
- NEVER use
pythonorpy— usenode -efor JSON operations - All code is ESM (
import/export, NOTrequire) - Node.js >= 18 — use native
fetch(no axios, no got) - Tests use Node's built-in test runner (
node --test) - Tool names are prefixed with
openwebui_ - All destructive operations (delete) require
confirm: trueparameter - No hardcoded URLs or API keys anywhere — only
process.env DEBUG=openwebui-mcpenables request logging to stderr
Architecture
src/
├── index.js MCP server entry point, tool registration, dispatch
├── api-client.js Open WebUI REST API wrapper (all HTTP calls here)
├── tools/
│ ├── chats.js 5 tools: list, search, get, delete, tags
│ ├── knowledge.js 6 tools: list, get, create, update, add-file, remove-file
│ ├── files.js 4 tools: list, upload, get-info, delete
│ ├── functions.js 5 tools: list, get, create, update, delete
│ ├── models.js 1 tool: list
│ ├── prompts.js 4 tools: list, create, update, delete
│ └── system.js 1 tool: get-status
└── utils/
├── errors.js APIError class
└── validators.js requireParam, requireConfirm, toPage helpers
Testing
cp .env.example .env
# Fill in OPENWEBUI_URL and OPENWEBUI_API_KEY
npm test
Tests call the real API. They create and delete test resources. Do not run against production.
Adding a new tool
- Add the API method to
src/api-client.js - Add tool definition to the appropriate
src/tools/*.jsarray - Write tests in
src/tools/*.test.js - Document in
docs/TOOLS.md - Update
CHANGELOG.mdunder [Unreleased]
API endpoint conventions
- All endpoints verified against Open WebUI 0.8.x
- Auth:
Authorization: Bearer <OPENWEBUI_API_KEY>on every request - Files use
multipart/form-data(FormData + Blob) - Prompts identified by
command(string starting with/) - Functions identified by
id(user-defined string, path:/api/v1/functions/id/{id})
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.
- 6d ago First seen · 70 lines · 712 tokens per session scan A 5cd7eb6cba51
openwebui-mcp-server CLAUDE.md is an instructions file published in the GitHub repository marccyberleda/openwebui-mcp-server (2 stars, last pushed 6mo ago), licensed MIT. It adds 712 tokens to every session, about $0.0036 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
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.
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.
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).
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).
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.
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.