Slashmcp MCP Server

MCP-powered AI workspace for document intelligence, multi-agent orchestration, and dynamic MCP server management. Exposed over MCP by the slashmcp mcp server, that capability becomes something an assistant can invoke while it works, not something you go and do afterwards.

What it actually does

• src/components/ui/chat-input.tsx drives the menu actions (Upload Files, Document Analysis, Image OCR, Voice Assistant)
• Frontend calls supabase/functions/uploads to create a processing_jobs row and receive an S3 presigned PUT URL
• Upload progress is surfaced in the UI; processing_jobs status transitions are polled via job-status function
• vision-worker fetches the uploaded asset from S3 via presigned GET, submits to GPT‑4o (with JSON-structured prompt), and persists results to analysis_results
• Gemini fallback helpers exist and can be toggled back in if desired
• textract-worker uses AWS Textract (sync for images, async for PDFs) and stores the OCR text + raw response

Its toolset

Everything the assistant can do here goes through one of these:

• Frontend — ** Vite + React + TypeScript + Tailwind + shadcn/ui
• Storage — ** S3 bucket arn:aws:s3:::tubbyai-products-catalog
• Optional — Google Generative AI key (for Gemini fallback), Whisper / Google Cloud TTS keys for upcoming features
• vision — worker fetches the uploaded asset from S3 via presigned GET, submits to GPT‑4o (with JSON-structured prompt), and persists results to
• textract — worker uses AWS Textract (sync for images, async for PDFs) and stores the OCR text + raw response
• processing_jobs — metadata for each upload
• analysis_results — OCR + vision outputs (ensure the migration is run on the Supabase project)
• Prerequisites — The Prerequisites tool exposed by this server
• Setup — Create .env.local (Vite automatically loads VITE_* variables):

Adding it to your client

supabase on npm is all you need. Most clients run it directly, so configuration is a few lines and a restart.

Configuration

You will need 8 environment variables: VITE_SUPABASE_URL, VITE_SUPABASE_FUNCTIONS_URL, VITE_SUPABASE_PUBLISHABLE_KEY, VITE_ALPHA_VANTAGE_API_KEY, VITE_MCP_GATEWAY_URL, VITE_SUPABASE_REDIRECT_URL, TWELVEDATA_API_KEY, PROJECT_URL. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

• Node.js ≥ 18.18 (recommend using nvm) - npm ≥ 9 or pnpm/bun if you prefer (project is currently npm locked) - Supabase CLI (npm install -g supabase or npx supabase) - AWS credentials with access to Textract + S3 bucket above - OpenAI API key (GPT‑4o vision) - Optional: Google Generative AI key (for Gemini fallback), Whisper / Google Cloud TTS keys for upcoming features

When to reach for it

Plenty of cloud and infrastructure servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Slashmcp's toolset — Frontend, Storage, Optional and 6 more — is a fair guide to whether it matches your workflow. It is maintained by mcpmessenger; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Caveats

• It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
• With 9 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Slashmcp.
• Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
• MCP clients confirm each tool call by default. Leave that on until you have watched what the slashmcp mcp server does with a few real requests.