Machine Schema MCP server
com.machineschema/mcpmachineschema.comstreamable-httpv0.2.0Scanned
Cited specs for industrial robots, CNC machines, PLCs, drives, protocols and alarm codes.
10 tools: 3 change things and 7 only read.
- Reads private data · 1
- Reads text others write · 0
- Can send data out · 0
- 2 findings
Tools listed without sign-in. Remote posture
With Anlyon
3 tools here change things. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the Machine Schema MCP server can do
The Machine Schema MCP server is published by machineschema.com, a domain the MCP Registry verified. It has 10 tools. It can create or change data (3 tools: check_limits, lookup_alarm and calculate_metric), but cannot delete data. 7 tools only read.
1 tool reads private data (compare).
The fixed checks matched 2 findings (annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 14, 2026, version 0.2.0.
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 3Claude Code: ask
calculate_metricEvaluate a formula entry, such as OEE, with your inputs.1 finding
Why it is in this group
- The description's first verb is "evaluate": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "calculate_metric" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The description's first verb is "evaluate": a word for a change.
Description, as the server wrote it Evaluate a formula entry, such as OEE, with your inputs. Get the variable symbols from get_entry first.
Annotations the server declares
- title: Calculate a metric
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
check_limitsCheck planned payload, reach, TCP speed, repeatability, ambient temperature or IP rating against a robot's published limits.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Check planned payload, reach, TCP speed, repeatability, ambient temperature or IP rating against a robot's published limits. Returns pass/fail/unknown per check with the limit and its sources. Call this before generating code that moves real hardware. Requires an API key.
Annotations the server declares
- title: Check a plan against hardware limits
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
lookup_alarmFind what a controller alarm or error code means and what to check.1 finding
Why it is in this group
- The name "lookup_alarm" says "lookup": a word for reading.
- The input takes a statement or command to run (input.code), which can change anything it can reach.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "lookup_alarm" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "lookup_alarm" says "lookup": a word for reading.
Description, as the server wrote it Find what a controller alarm or error code means and what to check. Accepts a full code (SRVO-062) or a prefix, optionally limited to one controller id.
Annotations the server declares
- title: Look up an alarm code
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
Only reads 7Show 7 read-only tools
compareAlign 2 to 5 entries of the same type into one table of numeric spec values with units, plus each entry's verification status and sources.Reads private dataNo findings
Why it is in this group
- The name "compare" says "compare": a word for reading.
What it can reach
- private-dataThe description's first sentence says "table": it reads databases.
Description, as the server wrote it Align 2 to 5 entries of the same type into one table of numeric spec values with units, plus each entry's verification status and sources. Requires an API key.
Annotations the server declares
- title: Compare entries
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
find_hardwareFind hardware matching numeric limits, manufacturer, controller and supported protocols, e.g.No findings
Why it is in this group
- The name "find_hardware" says "find": a word for reading.
Description, as the server wrote it Find hardware matching numeric limits, manufacturer, controller and supported protocols, e.g. cobots with payload >= 10 kg that speak PROFINET.
Annotations the server declares
- title: Filter hardware by spec
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_entryReturn the full structured record for one id: typed spec values, sources and verification status.No findings
Why it is in this group
- The name "get_entry" says "get": a word for reading.
Description, as the server wrote it Return the full structured record for one id: typed spec values, sources and verification status.
Annotations the server declares
- title: Get an entry
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_schemaReturn the JSON Schema every entry of a type conforms to.No findings
Why it is in this group
- The name "get_schema" says "get": a word for reading.
Description, as the server wrote it Return the JSON Schema every entry of a type conforms to. Use it to validate generated configs or to build a submission.
Annotations the server declares
- title: Get a type's JSON Schema
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_facetsValid values, with counts, for find_hardware filters: categories, manufacturers, controllers and protocols.No findings
Why it is in this group
- The name "list_facets" says "list": a word for reading.
Description, as the server wrote it Valid values, with counts, for find_hardware filters: categories, manufacturers, controllers and protocols.
Annotations the server declares
- title: List filter values
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
search_entriesFull-text search across hardware, controllers, protocols, standards, alarm codes, terms and manufacturers.No findings
Why it is in this group
- The name "search_entries" says "search": a word for reading.
Description, as the server wrote it Full-text search across hardware, controllers, protocols, standards, alarm codes, terms and manufacturers. Returns ids to pass to get_entry.
Annotations the server declares
- title: Search the registry
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
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.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 16, 2026, 14:21 UTC, unchanged since Nov 2, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 3
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 3 tools that change things (3 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://machineschema.com/mcp: tools/list returned 10 tools to an anonymous client, including check_limits (write), lookup_alarm (write), calculate_metric (write)
Findings
Matches of fixed checks, with the text they matched.
- Warnlookup_alarm
The server marks "lookup_alarm" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "lookup_alarm" says "lookup": a word for reading.
- Warncalculate_metric
The server marks "calculate_metric" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The description's first verb is "evaluate": a word for a change.
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools2 changed.~2 changedView diff
- Changed:check_limitsChanges thingsdescription
- Changed:compareOnly readsdescription
Install
Pinned to version 0.2.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http machineschema https://machineschema.com/mcpclaude mcp add --transport http machineschema https://machineschema.com/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__machineschema__search_entries",
"mcp__machineschema__get_entry",
"mcp__machineschema__find_hardware",
"mcp__machineschema__list_facets",
"mcp__machineschema__compare",
"mcp__machineschema__get_related",
"mcp__machineschema__get_schema"
],
"ask": [
"mcp__machineschema__check_limits",
"mcp__machineschema__lookup_alarm",
"mcp__machineschema__calculate_metric"
],
"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 machineschema. Review it before you use it.
Capability tags behind 1 rule
- mcp__machineschema__compare 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://radar.anlyon.com/api/v1/servers/com.machineschema/mcp/verify?hash=835c1a8367c2167d869cac025707a84d19e7d54cbc4265313a31e254f8023a29" | jq -e '.changed == false'Pinned hash 835c1a8367c2, from Nov 14, 2026, 20:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.machineschema/mcp/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.machineschema/mcp)Source: MCP Registry. Synced Nov 1, 2026, 19:17 UTC.
Machine Schema MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Machine Schema MCP server safe?
- No scan can promise that. What its definitions show: 10 tools, 3 of which can change, send or delete something, and 2 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the Machine Schema MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Machine Schema MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the Machine Schema MCP server have?
- 10 tools: 3 write, 7 read. check_limits, lookup_alarm, calculate_metric, search_entries, get_entry, find_hardware, list_facets, compare and 2 more.
Does the Machine Schema MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Machine Schema MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Machine Schema MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 14, 2026. Every change is on this page and in its Atom feed.