Show, Don't Code
io.github.PugarHuda/show-dont-codePugarHudastreamable-httpv1.0.0Scanned
Lab video or protocols.io protocol to a simulator-checked Opentrons Flex/OT-2 protocol
10 tools: 2 change things and 8 only read.
- Reads private data · 1
- Reads text others write · 0
- Can send data out · 0
- No findings
Anlyon alternative
2 of these tools change something. Run those as governed actions.
Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.
Anlyon does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.
Import an OpenAPI spec →Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
10 tools
Changes things 2Claude Code: ask
crosscheck_volumesThis run's per-reaction volumes next to those of published protocols.io protocols that use the same kit, read by Muse Spark: each match has the published volume, its verbatim quote…No findings
Why it is in this group
- The description's first verb is "run": a word for a change.
Description, as the server wrote it This run's per-reaction volumes next to those of published protocols.io protocols that use the same kit, read by Muse Spark: each match has the published volume, its verbatim quote (checked to be in the protocol's text), both reagents' share of the reaction and whether they agree within 20 %.
run_on_flex_robot_serverRun the run's protocol.py end to end on Opentrons' own robot-server (the software inside a Flex, v10.1.0) in Flex simulation, with the Reactions parameter set: the robot's analysis…No findings
Why it is in this group
- The name "run_on_flex_robot_server" says "run": a word for a change.
Description, as the server wrote it Run the run's protocol.py end to end on Opentrons' own robot-server (the software inside a Flex, v10.1.0) in Flex simulation, with the Reactions parameter set: the robot's analysis, deck configuration, play to the end. Returns the robot's report (status 'succeeded', command count). About a minute the first time, then cached. Runs only the protocol this server generated, never code an agent sends.
Only reads 8Show 8 read-only tools
get_bench_cardThe illustrated bench card for training: each filmed step drawn by Muse Image from its own video frame (an edit of the real frame, no text drawn in), Muse Spark's check that the dr…No findings
Why it is in this group
- The name "get_bench_card" says "get": a word for reading.
Description, as the server wrote it The illustrated bench card for training: each filmed step drawn by Muse Image from its own video frame (an edit of the real frame, no text drawn in), Muse Spark's check that the drawing kept every object, and the step's reagent and volume from the protocol. Image links are under /api/runs/<name>/bench-card/<step>.jpg.
get_protocolThe generated Opentrons Flex protocol (Python, API 2.24), ready to import into the Opentrons App.No findings
Why it is in this group
- The name "get_protocol" says "get": a word for reading.
Description, as the server wrote it The generated Opentrons Flex protocol (Python, API 2.24), ready to import into the Opentrons App.
get_protocol_designerThe protocol as an Opentrons Protocol Designer file: import it at designer.opentrons.com to edit each step (transfers, mixes, the thermocycler program) without code.Reads private dataNo findings
Why it is in this group
- The name "get_protocol_designer" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "file": it reads files.
Description, as the server wrote it The protocol as an Opentrons Protocol Designer file: import it at designer.opentrons.com to edit each step (transfers, mixes, the thermocycler program) without code. The Opentrons App can also run it as is.
get_receiptReproducibility receipt: SHA-256 of the protocol, the video and every model output, and which models ran, anchored in Bitcoin with OpenTimestamps ('timestamp': pending calendars, o…No findings
Why it is in this group
- The name "get_receipt" says "get": a word for reading.
Description, as the server wrote it Reproducibility receipt: SHA-256 of the protocol, the video and every model output, and which models ran, anchored in Bitcoin with OpenTimestamps ('timestamp': pending calendars, or the confirming block).
get_runThe steps found in the video (with video seconds), the open questions, and the Opentrons simulator and protocol analysis results, including the deck setup, runtime parameters and t…No findings
Why it is in this group
- The name "get_run" says "get": a word for reading.
Description, as the server wrote it The steps found in the video (with video seconds), the open questions, and the Opentrons simulator and protocol analysis results, including the deck setup, runtime parameters and the thermocycler's minimum time in seconds.
get_tube_labelsThe tubes to load on the tube rack before the run: each tube's deck slot and well, how many µL to fill a source tube with (what the robot draws + 10 % + dead volume) for `reactions…No findings
Why it is in this group
- The name "get_tube_labels" says "get": a word for reading.
Description, as the server wrote it The tubes to load on the tube rack before the run: each tube's deck slot and well, how many µL to fill a source tube with (what the robot draws + 10 % + dead volume) for `reactions` copies of the filmed reaction (protocol.py's Reactions parameter, up to max_reactions), and the link its label's QR code opens. Links to the printable labels: an Avery L7160 sheet (SVG) and a Zebra thermal printer file (ZPL, 2 x 1 in).
list_runsNames of the sample runs (videos already turned into protocols).No findings
Why it is in this group
- The name "list_runs" says "list": a word for reading.
Description, as the server wrote it Names of the sample runs (videos already turned into protocols).
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged untrusted-input or outbound.
- Reads private data1
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write0
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http show-dont-code https://pugarhuda--show-dont-code-web.us-east.modal.run/mcpclaude mcp add --transport http show-dont-code https://pugarhuda--show-dont-code-web.us-east.modal.run/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__show-dont-code__list_runs",
"mcp__show-dont-code__get_run",
"mcp__show-dont-code__get_protocol",
"mcp__show-dont-code__get_protocol_designer",
"mcp__show-dont-code__get_tube_labels",
"mcp__show-dont-code__get_related_protocols",
"mcp__show-dont-code__get_bench_card",
"mcp__show-dont-code__get_receipt"
],
"ask": [
"mcp__show-dont-code__run_on_flex_robot_server",
"mcp__show-dont-code__crosscheck_volumes"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as show-dont-code. Review it before you use it.
Capability tags behind 1 rule
- mcp__show-dont-code__get_protocol_designer private-data
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://anlyon.dev/api/v1/servers/io.github.PugarHuda/show-dont-code/verify?hash=7bf065a34924e70b823a0ce741746cec7c1a4f2cdb73fd9b432020bcfdc108e6" | jq -e '.changed == false'Pinned hash 7bf065a34924, from Nov 4, 2026, 03:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://anlyon.dev/servers/io.github.PugarHuda/show-dont-code/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://anlyon.dev/servers/io.github.PugarHuda/show-dont-code)Source: MCP Registry · repository. Synced Nov 4, 2026, 03:17 UTC.