MCP.Market

text-to-reality MCP server

by ai-wes·io.github.ai-wes/text-to-reality·v0.1.1

Turn an idea into a device anyone can build: parts, printed parts, wiring, code and a picture guide.

A92/100grade A
What users say
No reviews yet
Be the first
Safety scan
A92/100

full report

Adoption
Growing

0 stars282 downloads/wk

Reviews

Write one

Nobody has reviewed text-to-reality yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

text-to-reality tools (13, 1 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • board_headers

    Header rows (pins per row) for common boards and modules: XIAO, Pico, ESP32 DevKit, Arduino Nano, SSD1306 OLED and more.

  • build_history

    Everything that happened to a build: files recorded, revisions, outcomes.

  • check_package

    Check the build is complete and consistent: every stage finished, files unchanged since recorded, bom.json and wiring.json valid, JIG_ connectors in the parts list, an assembly guide present. Returns problems to fix and links to get the JIG_ parts the build uses.

  • connector_guidance

    Read this before planning header wiring. Returns what JIG_ connectors are (a base that holds each wire's plug in order plus a snap-on cover), which headers they fit, how many to use, how to list them, and the steps to load them and plug them on.

  • connectors_for_boards

    Which JIG_ wire connectors a build needs: one per header row, sized to the whole row. `boards` is a list of {"board": name, "quantity": n}, or {"board": label, "rows": [pins, ...], "quantity": n} for a board that isn't in the catalog. `size` is small or large, matching the jumper wire plugs. row_checks lists what to confirm on the real board. Custom `headers` take the catalog row fields plus gende

  • create_projectwrite action

    Start a build. `brief` is the idea in plain words plus anything known: size, power, budget, parts the person already owns, and how they'll know it works. Creates a folder with brief.md.

  • find_jig_parts

    Look up JIG_ parts that remove soldering, crimping and breadboards: wire connectors, a XIAO battery adapter, and complete kits. Empty query lists everything.

  • list_projects

    List builds in the projects folder.

  • log_outcome

    Record what happened when the build was tried: worked, partly_worked or failed, with what was learned. Read it back with build_history before designing the next one.

  • new_revision

    Start a new revision after a design change. Re-record files you change in it.

  • project_status

    Show each stage, its files, what to do next, and files edited since they were recorded.

  • record_files

    Record files you've written (paths relative to the project folder) under a stage: requirements, parts, mechanical, electronics, firmware, assembly or testing. Recording fingerprints each file so later edits are caught.

  • set_stage

    Set a stage to todo, done or not_applicable. not_applicable needs a reason (for example, a printed-only object has no electronics).

Public scan report

scanner v0.1.10 · 2026-10-14 · same rubric, same numbers if you re-run it

no findings
  • Code scan13 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 7 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 92/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How text-to-reality compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
92/100
higher than 95% of 48,255 servers
Tools
13
the typical server has 7
Tools that change things
8%
typical: 0%. Fewer write tools means less an agent can break
Downloads a week
282
more than 80% of 12,191 servers with a package

What its tools let an agent do: 10 read · 2 create · 1 change

Install text-to-reality in Claude Code, Cursor or VS Code

claude mcp add text-to-reality -- uvx text-to-reality
Add to Cursor

What the publisher says

From the text-to-reality repository's README, as published. We do not edit it. Read it on GitHub

<!-- mcp-name: io.github.ai-wes/text-to-reality -->

text-to-reality

Give your agent the power to build real things.

text-to-cad makes a part. text-to-reality makes the working device.

Describe something you want to exist. Your agent turns it into a build package anyone can put together by following pictures:

  • a parts list you can order, using parts that plug together
  • 3D-printable parts for the case and mounts
  • the wiring, every wire and which connector it goes in
  • the code, ready to load
  • a step-by-step picture guide written for someone who has never built electronics
  • tests, so you know it works

No soldering, no breadboard, no electronics experience required. It runs on your machine: no account, no API key, and your projects are plain folders you own.

Example: Agent Meter

*"Build me a little desk character that shows what my coding agent is doing and

how much of my Claude allowance is left."*

Agent Meter illustrates this workflow: a Seeed Studio XIAO ESP32-S3 and a small screen inside a printed character, wired with plug-on connectors, with firmware and a picture guide. Its face shows when your agent is working, finished or waiting on you, plus your remaining allowance.

Get the Agent Meter kit →

Install

Ask your agent

Install text-to-reality from https://github.com/ai-wes/text-to-reality

Or install it yourself. text-to-reality runs through uv: check it's installed with uv --version, or use uv's installer. Then run the commands for your agent and restart it.

Claude Code

claude plugin marketplace add ai-wes/text-to-reality
claude plugin install text-to-reality@ai-wes

To update: claude plugin marketplace update ai-wes, then claude plugin update text-to-reality@ai-wes.

Codex

codex plugin marketplace add ai-wes/text-to-reality
codex plugin add text-to-reality@ai-wes

Cursor

Cursor also loads the Claude Code plugin; if that's installed, skip this.

git clone --depth 1 https://github.com/ai-wes/text-to-reality ~/.cursor/plugins/local/text-to-reality

Claude Desktop

Add the server to Claude Desktop's config (Settings > Developer > Edit Config), then restart. If it can't find uvx, use its full path (which uvx).

{
  "mcpServers": {
    "text-to-reality": {
      "command": "uvx",
      "args": ["--no-config", "--managed-python", "--python", "3.13", "--from", "text-to-reality==0.1.1", "text-to-reality", "mcp"]
    }
  }
}

Projects are saved in text-to-reality/ in the folder the app starts in; set TEXTTOREALITY_DIR in env to choose another folder.

Other agents

npx skills add ai-wes/text-to-reality

Then add the MCP server above to your agent's MCP config.

Works with text-to-cad

text-to-reality plans the whole device; text-to-cad is great at the printed parts. Install both, and the agent uses text-to-cad for the printed parts when it's available.

How it works

Each build is a folder. The agent fills in seven stages and checks them:

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

text-to-reality: common questions

Is text-to-reality MCP server safe?
Yes, by our scan: it is graded A (92/100). Read the text-to-reality safety report
How do I install text-to-reality?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does text-to-reality need an API key?
No secret keys are declared. It reads 1 setting from the environment.
Is text-to-reality maintained?
The last commit was 28 days ago (2026-10-07). The latest release is v0.1.1.
How does text-to-reality compare with other MCP servers?
safety score 92/100 (higher than 95% of 48,255 servers); tools 13 (the typical server has 7); tools that change things 8% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.