Benchside
OfficialClick on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Benchsidewhere did I leave off?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Benchside
A workshop journal that remembers the next step, interruption note and exact location of loose parts. A real MCP server and web workbench share the same durable state. The local app keeps a file on your computer; the hosted app keeps a separate online workspace for each browser.

Hosted app
Open Benchside. The online workshop is scoped to a private browser cookie; clearing cookies loses access. Other browsers get separate workshops. There is no account login or recovery. Use fictional data for this public prototype and download a copy of anything you want to retain. See hosting boundaries and build.
The hosted MCP endpoint is https://benchside.dgkv.chatgpt.site/api/mcp. Compatible clients must retain the returned workshop cookie between requests. All nine tools below are available through the genuine SDK transport.
Related MCP server: Abbie MCP Server
Run locally
Requires Node.js 22 or newer.
npm ci
npm startOpen http://127.0.0.1:4318. Start a project with your own steps or try the explicitly labeled sample. Record a completion, stash a part, pause with a next-action note, reload and ask where you left off. Resume and undo a mistaken completion.
There is no API key, paid service, live language model, Echo connection or Alexa certification. The command simulator uses a finite grammar and is labeled accordingly. Physical completion records only what the user reports. Sample steps and actions are illustrative.
Actual MCP integration
The official @modelcontextprotocol/sdk implements protocol 2025-11-25 over Streamable HTTP at http://127.0.0.1:4318/mcp. Any compatible local MCP client can initialize, list tools and call them. The workbench itself calls these tools over HTTP; it does not use a separate mock data path.
Tool | Purpose |
| List recorded project progress |
| Create user-authored steps |
| Read current revision, steps, parts and history |
| Read the exact saved checkpoint and parts locations |
| Record the current step complete |
| Reopen the last completed step |
| Record/update a named part, quantity and location |
| Save interruption and next-action notes |
| Resume without losing context |
Read the project before writing. Writes require its current expected_revision, a unique UUID request_id, and the relevant identifiers. Retry the exact payload with the same request ID after an ambiguous response. Stale revisions fail; a duplicate request cannot skip another step. Tool descriptions instruct an agent to record completion only on explicit user confirmation.
The transport is stateless JSON-response mode: POST is supported; standalone GET/SSE and DELETE return 405. This is permitted by the 2025-11-25 transport specification.
Command simulator
where did I leave off?
done
undo
resume
stash 6 brass screws @ blue tray
pause: the phone rang | next: label the left trayUnknown commands are rejected without changing state. Optional browser speech synthesis reads the exact briefing; it is not speech recognition or a voice assistant connection.
Persistence and boundaries
Data is saved by atomic file replacement to data/workshop.json; BENCHSIDE_DATA_DIR chooses another directory. Only one server may use a data directory. A normal Ctrl-C releases its lock. After an abrupt crash, first confirm the old process is gone, back up the directory, then remove only the abandoned workshop.lock. Corrupt data causes startup to fail without changing it. A project export is a readable copy; there is no UI import feature. Back up the full data directory for recovery.
The local service binds to loopback only and rejects unexpected Host/Origin headers. It has no authentication and must not be exposed as a public multi-user server. The separate hosted build provides browser-cookie isolation; it is not account-authenticated Alexa connectivity and has not been tested with Alexa. Limits: 20 projects, 50 steps per project, 100 named parts, 1,000 history events/receipts per project, 4 MB persisted store, 64 KB HTTP request. Atomic replacement protects against partial writes in ordinary process failures; power-loss durability is not guaranteed.
Verify
npx playwright install chromium
npm test
npm run test:browser
npm run test:hostedThe 2026-09-27 hosted pass ran 14 local/domain/recovery tests, seven browser journeys and seven actual workerd/D1 tests, all passing. The six original domain/HTTP tests and seven redesign browser journeys are retained. Checks include actual protocol negotiation, server restart, checkpoint accuracy, parts locations, keyboard recovery and phone/enlarged-text reflow. Browser tests use an isolated temporary data directory. See QA evidence, design rationale, research and plan, developer feedback and submission draft.
New application code began on 2026-09-26. Codex researched, designed, wrote and verified this prototype under autonomous delegation; no human maker trial, usage metric, device test or competition acceptance is claimed. Existing dependencies are disclosed in package.json and package-lock.json. MIT license; no affiliation with Amazon or the MCP project is implied.
This server cannot be deployed
Maintenance
Related MCP Connectors
Read and write shared BitsWeave context, projects, tasks, and work sessions through MCP.
Minimal issue tracker: projects, objectives and trackable plans, written by agents over MCP.
System-of-record notebook for AI coding agents: pages, datastores, tasks, skills over MCP.
Durable, shareable and governed project memory with smart triage and explicit project composition.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceA filesystem MCP server that journals every file operation (write, delete, move, mkdir) and outbound commands (exec, http) into an append-only ledger, enabling undo and compensation of actions.MIT
- AlicenseNot gradedqualityBmaintenanceProvides tools for governed project work, including project setup, workspace management, and task execution, with credential-safe MCP wiring.MIT
- FlicenseNot gradedqualityAmaintenanceTurns local project directories into persistent MCP workspaces, allowing AI agents to read files, modify code, run commands, manage Git, and save session progress across conversations.-
- AlicenseNot gradedqualityBmaintenanceEnables managing local repositories, CLIs, MCP servers, and skills via MCP tools, with inventory tracking, guarded updates, and Docker-sandboxed trials.MIT