DynoTable
About
A local MCP server that gives Claude Code, Cursor and Codex read access to your DynamoDB schema and items, with every write staged for human review.
Details
- Author
- Unknown
- Categories
- Database, Other, AI, Knowledge Base
Jump to
TheModel Context Protocol (MCP)is an open standard that lets AI agents talk to external tools and data sources. DynoTable can act as anMCP server— so an agent running in your terminal or editor (Claude Code, Cursor, Codex, and others) can work with your DynamoDB tables directly, instead of you copying schemas and results back and forth into a chat.
When connected, the agent gets a projection of thebuilt-in assistant's gated toolkit — reading your schema, running queries and single-item reads, staging changes for review, opening views, and exporting — over a local,loopback-onlyHTTP endpoint. Read-only queries use the same index and key condition as the in-app visual filter; preview equivalent SDK code with thequery builderbefore wiring a client. A few app-local tools stay in the app and are not exposed. The agent discovers your tables, queries them, and proposes edits without ever holding your AWS credentials.
It isoff by default. Turning it on, and every individual connection, is explicitly under your control — seeSecuritybelow.
OpenSettings → MCP Serverand turn it on. DynoTable starts a server bound to127.0.0.1(loopback only — never reachable from another machine) and shows the connect command for it.
DynoTable's Settings → MCP Server pane: the DynamoDB MCP server running on a local loopback port, with the list of connected clients and their access levels.
The server is on, but no agent can connect until youexpose a profile. Open a profile'sMCPsection in Settings and turn onExpose via MCP. Each exposed profile gets its own connect command — so you can wire upone connection per profile(e.g. adynotable-devand adynotable-prod), each hard-isolated to that profile's credentials and region. A connection only ever sees the data of the profile it's bound to.
BothAWS-backedandlocal (DynamoDB-Local)profiles can be exposed. Exposing a local profile lets an agent drive yourlocal seeded tablesover MCP — handy for development. (Two local profiles on the same port share the same local database, so they see the same tables.)
A DynoTable profile's MCP section with “Expose via MCP” turned on — the per-profile connect block shows the endpoint to add to your client.
DynoTable speaks MCP overstreamable HTTP, so any MCP-capable agent can connect. Each exposed profile shows itsownconnect command in its MCP section — copy it from there. The command points athttp://127.0.0.1:<port>/mcp?profile=<slug>: the?profile=<slug>tells DynoTable which profile you want and pre-selects it in the approval prompt (it's only a hint — you still confirm). Using the profile slug in the server name (e.g.dynotable-prod) keeps two profiles' connections distinct.
The examples below useprodas the slug; substitute your profile's slug and the real port from Settings.
Run this in your project — it's the exact command shown in the profile's MCP section:
claude mcp add --transport http dynotable-prod "http://127.0.0.1:<port>/mcp?profile=prod"
To connect a second profile, repeat with that profile's command (its own slug). After connecting, restart or reload the client so it picks up the new server.
The first time a client connects, DynoTable shows aconsent promptinside the app. It names the connecting client, lets you pickwhich profilethe connection binds (pre-selected from the?profile=hint, limited to your exposed profiles), and asks you to grant ascope— or deny. Nothing is exposed until you approve.
DynoTable's in-app MCP consent prompt: a connecting client requests access, and you grant one of three scopes or deny.
A scope decides which tools the connection can see and use. They are cumulative — each tier includes the ones before it:
- Read only— read your schema, run queries, and read items. No changes.
- Read & stage— everything in Read only, plus staging changes for you to review and commit (the agent never writes to DynamoDB directly — it routes throughstaging).
- Full access— everything above, plus opening views, setting filters, and exporting results.Writes still go throughstaging— even at Full access the agent can't write to DynamoDB directly.
The connection binds theprofile you approvein the prompt — its credentials and region are pinned for the life of the connection, so it reads (and stages writes to) exactly that profile's data. The client name in the prompt isself-reportedby the connecting agent, so the profile and scope you approve are the real gate, not the name.
Every approved client is listed inSettings → MCP Server. Revoke any of them at any time — a revoked client is cut off on its next request.Un-exposing a profile immediately revokes its connectionstoo. Turning the server off stops everything.
- Loopback only.The server binds127.0.0.1; nothing off your machine can reach it.
- Off by default, approval per connection.No agent gets access until you enable the serverandapprove its connection at a scope you choose.
- Credentials stay local.Connections use your existing AWS profiles on this machine (Connect to AWS); credentials are never sent to the agent.
- One profile per connection.Each connection is pinned to the single profile you approved — it can never reach another profile's tables or credentials.
- Writes go through review.Even at Full access, changes arestagedfor you to commit — the agent can't write to DynamoDB on its own.
- Revocable.Revoke a client or turn the server off whenever you want.
The DataFast MCP server lets MCP-compatible clients such as Codex, Claude Code, and Cursor query your analytics and manage your account through natural language.
Inkrun's remote MCP server lets AI agents like Claude turn Markdown into themed, consistent and reproducible on-brand PDFs with a single tool call
Transform your scattered documentation into AI-ready knowledge that works seamlessly with Claude, Cursor, VS Code, and other AI tools.
Autofill PDF is an MCP server that connects your Instafill.ai workspace to the Claude and ChatGPT MCP clients, allowing users to upload, search, and automatically fill PDF forms directly from chat.
Share your team's Coding Best Practices with Cursor, VS Code, Claude code, Windsurf, JetBrains IDEs and other coding tools supporting remote MCP connection.
Lance is an agent that runs on its own cloud Mac and handles everything on the App Store Connect side of shipping an iOS app. It connects to coding agents like Claude Code and Codex through MCP and takes over the parts they can't do: creating apps on App Store Connect, setting up notifications / widgets, filling out listing metadata, uploading builds to TestFlight, submitting for review, and responding to App Review feedback. Because it has its own Mac, it can also build, run, and test users' apps and capture screenshots.
Persistent AI memory shared across Claude, ChatGPT, coding agents, and compatible MCP clients.
Connect your Moodle LMS to ChatGPT, Claude and other MCP clients: build courses, upload content, review grades and pull reports from the chat.
Connect your Google, Outlook and iCloud calendars to Claude, ChatGPT and any MCP client through one secure server. Let your AI assistant read your schedule, check your availability, and create, update and delete events.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
