MCP servers › io.github.partprogramming09 › metal-gpu-trace
MCP server · registry snapshot 2026-10-23 · last tested 2026-10-23
io.github.partprogramming09/metal-gpu-trace
Measure Wine and macOS programs' GPU use on Apple silicon with Metal System Trace — the publisher's description
Summary
io.github.partprogramming09/metal-gpu-trace is a local MCP server listed in the official MCP registry at version 0.7.1. On 2026-10-23 ProtocolProbe started its published package in an isolated sandbox in read-only mode and read its inventory: 16 tools, 5 resources and 1 prompt.
Record checks
7 of 8 record checks met · 1 does not apply
- met: Registry entry is active and says how to run it
- met: Source repository link opens
- met: Repository is not archived
- met: Code pushed to the repository in the 90 days before our check
- not met: Repository publishes a security policy (SECURITY.md)
- met: Package names its licence with a standard (SPDX) identifier
- met: The version the registry lists can be installed and is not withdrawn
- not applicable: npm package carries build provenance (attestation)
- met: No known critical or high advisory in the package or its dependencies
- #14,745 of 15,112 packages by monthly downloads, tied with 367 others
- Not ranked by stars: 0 stars (ranked from 10)
From public records, not a safety rating. Each check with its reason · Is it safe to install?
Key facts
- Runs
- local package
- Transport
- standard input/output
- Package
- PyPI · listed version current
- License
- MIT
- Dependencies
- no known high or critical advisories
- Repository
- public
- Tools
- 16
- Described as changing data
- 5 of 16 toolsAI-classified
- Topic
- developer-toolsAI-classified
- Last tested
- 2026-10-23
Worth knowing before you connect it
- 5 tools are described as changing something (perf_record, perf_baseline_record, perf_attach, …): our AI model's reading of the descriptions, not something we tested. We did not call them.
Each line comes from a section below, with its source and date.
How fresh this is
- Live-tested
- yes, a real session (not a text-only review)
- Last tested
- 2026-10-23
- Mode
- read-only (no tool calls)
- Latest version
- 0.7.1, published 2026-10-18 (registry, as of the 2026-10-23 snapshot)
- First listed version
- 2026-10-18 (earliest version still in the registry; older removed versions would be earlier)
- Version history
- 5 versions listed, all on 2026-10-18; 5 in the 90 days before the 2026-10-23 snapshot.(versions still listed in the registry only)
Most recent 5 versions
0.7.1· 2026-10-180.7.0· 2026-10-180.6.0· 2026-10-180.5.0· 2026-10-180.4.0· 2026-10-18
- Registry data
- snapshot 2026-10-23
- Package and repository
- checked 2026-10-23
- Engine
- mcp-runtime-engine@0.1.0 · sdk@1.32.0
Changes since the last refresh
New in the registry: not in the list of 2026-10-04, listed on 2026-10-23 with version 0.7.1 (published 2026-10-18).
Source: the official MCP Registry list on 2026-10-04 and on 2026-10-23.
What it is
What does this server offer?
Observed inventory5 of 16 tools are described as changing something (creating, editing, deleting, sending or running).
- perf_recordruns code or commandsdescribed as changing data
“Records `program` (an .exe under Wine, or a macOS binary with wine="native"), or a test program fetched with workload_fetch (workload, api, dim), for `seconds` with Metal System Trace and returns its…”
Publisher declares: read-only no · destructive yes · idempotent no · open-world no
10 inputs, 1 required
labelstringrequired“name for the run: letters, digits, '.', '_', '-'”programstring“path of the .exe, or of the macOS binary with wine=native”secondsinteger“recording length, default 20; use 30 under Wine, whose start-up takes part of it; the export afterwards takes about a minute”winestring“Wine directory holding bin/wine, or native”prefixstring“Wine prefix, default WINEPREFIX or ~/.wine; ignored with native”workdirstring“directory the program starts in, default the program's own”argsstring“program arguments as in a shell, quotes included”workloadstring“a test program from workload_list, fetched with workload_fetch, instead of program”apistring“with workload: mtl (native Metal), d3d11 or d3d12 (under wine)”diminteger“with workload drawstress: side of the cube grid, dim^3 draws per frame”
- perf_baseline_recordruns code or commandsdescribed as changing data
“Records the same program `count` times in a row with perf_record's arguments and saves the runs as the reference `name` for perf_check, returning the range each number spans across them.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world no
11 inputs, 1 required
namestringrequired“reference name: letters, digits, '.', '_', '-'”countinteger“equal recordings to make, default 3”programstring“path of the .exe, or of the macOS binary with wine=native”secondsinteger“recording length, default 20; use 30 under Wine, whose start-up takes part of it; the export afterwards takes about a minute”winestring“Wine directory holding bin/wine, or native”prefixstring“Wine prefix, default WINEPREFIX or ~/.wine; ignored with native”workdirstring“directory the program starts in, default the program's own”argsstring“program arguments as in a shell, quotes included”workloadstring“a test program from workload_list, fetched with workload_fetch, instead of program”apistring“with workload: mtl (native Metal), d3d11 or d3d12 (under wine)”diminteger“with workload drawstress: side of the cube grid, dim^3 draws per frame”
- perf_attachruns code or commandsdescribed as changing data
“Records a program that is already running, by pid or by a name in its command line (Game.exe under Wine), for `seconds` and returns the same summary as perf_record; the program keeps running.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
3 inputs, 2 required
labelstringrequired“name for the run: letters, digits, '.', '_', '-'”processstringrequired“pid, or a name in the program's command line such as Game.exe”secondsinteger“recording length, default 20; the export afterwards takes about a minute”
- perf_runsreads or searches
“Lists the saved recordings, newest first, with frames, FPS, GPU ms per frame, memory peaks and the translation layer each ran on (fingerprint and Wine, or native).”
Publisher declares: read-only yes · open-world no
2 inputs
offsetinteger“first row, default 0”limitinteger“rows per page, default 50, at most 500”
- perf_comparereads or searches
“Compares two saved recordings (names from perf_runs), a the reference and b the run after a change: the headline numbers (FPS, GPU ms, frame pacing, memory), then what changed in the GPU work and whe…”
Publisher declares: read-only yes · open-world no
3 inputs, 2 required
astringrequired“run name from perf_runs: the reference, such as the run before a change”bstringrequired“run name from perf_runs: the run to compare against a”short_usinteger“an encoder under this GPU time counts as short: 10, 25 (default), 50, 100, 250, 500 or 1000”
- perf_baselinecreates or changes datadescribed as changing data
“Names a reference for perf_check, or lists them.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
2 inputs
namestring“reference name: letters, digits, '.', '_', '-'; alone, shows that reference”runsarray“run names from perf_runs to save as this reference, ideally 3 or more equal runs; replaces a previous one”
- perf_checkreads or searches
“Judges a recording against a reference saved with perf_baseline: regressed when FPS falls under the reference's lowest FPS by more than margin_pct, GPU ms per frame rises over its highest by more tha…”
Publisher declares: read-only yes · open-world no
3 inputs, 2 required
runstringrequired“a run name from perf_runs”baselinestringrequired“a reference name from perf_baseline”margin_pctnumber“how far outside the reference's range FPS or GPU ms per frame may fall before counting, default 3”
- perf_diagnosereads or searches
“Says whether a saved recording splits its GPU work into too many short encoders, the pattern of translation layers such as DXMT, Mullion or MoltenVK, with the numbers behind it: encoders and command …”
Publisher declares: read-only yes · open-world no
4 inputs, 1 required
runstringrequired“a run name from perf_runs”min_encodersinteger“encoders per frame (median) from which the verdict can be yes, default 4”short_usinteger“an encoder under this GPU time counts as short: 10, 25 (default), 50, 100, 250, 500 or 1000”short_sharenumber“share of short encoders from which the verdict is yes, default 0.25”
- trace_tablesreads or searches
“Lists the data tables (schemas) a .trace recording holds; recordings keep their .trace only with KEEP_TRACE=1.”
Publisher declares: read-only yes · open-world no
1 input, 1 required
tracestringrequired“a run name from perf_runs whose trace_kept is true, or the path of a .trace”
- trace_countreads or searches
“Counts the rows of several tables of a kept .trace, in all and per process, so a recording's useful tables show before reading them: a table with 0 rows needs another instrument or Xcode, not a bigge…”
Publisher declares: read-only yes · open-world no
2 inputs, 1 required
tracestringrequired“a run name from perf_runs whose trace_kept is true, or the path of a .trace”tablesarray“table names from trace_tables; default the tables that matter for a translation layer”
- trace_queryreads or searches
“Returns one page of rows of one table of a .trace as {column: value}, optionally only one process's rows.”
Publisher declares: read-only yes · open-world no
5 inputs, 2 required
tracestringrequired“a run name from perf_runs whose trace_kept is true, or the path of a .trace”schemastringrequired“a table name that trace_tables lists, such as metal-gpu-intervals”pidinteger“keep only this process's rows”offsetinteger“first row, default 0”limitinteger“rows per page, default 50, at most 500”
- capture_summaryreads or searches
“Reads a Metal .gputrace capture without Xcode: command buffers, encoders, draws, debug groups, and the 100 most frequent call ids out of calls_total.”
Publisher declares: read-only yes · open-world no
1 input, 1 required
capturestringrequired“path of a .gputrace bundle saved from Xcode, inside METAL_TRACE_OUT or METAL_TRACE_READ”
Show 4 more tools
- capture_recordsreads or searches
“Returns one page of the records of a .gputrace command stream, with their Metal call names when known.”
Publisher declares: read-only yes · open-world no
3 inputs, 1 required
capturestringrequired“path of a .gputrace bundle saved from Xcode, inside METAL_TRACE_OUT or METAL_TRACE_READ”offsetinteger“first row, default 0”limitinteger“rows per page, default 50, at most 500”
- gpu_familyreads or searches
“Apple's published facts for one GPU family, by family ("Apple7") or chip ("M1 Pro"): its chips, what it adds, its limits, plus the limits shared by all families and the footnotes.”
Publisher declares: read-only yes · open-world no
1 input, 1 required
namestringrequired“a family (Apple7 to Apple10) or a chip (M1 Pro, M2, M4 Max, A17 Pro)”
- workload_listreads or searches
“Lists the test programs workload_fetch can download, such as bgfx's drawstress: what each measures, its size, license and APIs, and whether it is already downloaded.”
Publisher declares: read-only yes · open-world no
Takes no inputs.
- workload_fetchcreates or changes datadescribed as changing data
“Downloads a test program from this project's GitHub releases once, checks its SHA-256 against the one this package pins, and keeps it in ~/Library/Caches/metal-gpu-trace; later calls reuse it.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world yes
1 input, 1 required
namestringrequired“a workload name from workload_list, such as drawstress”
Each quoted sentence is the first sentence of the publisher’s own description. The kind of tool and the “changes data” mark are our AI model’s reading of that description, not something we tested: two differently worded runs had to agree, otherwise no label is shown, and nobody has checked them by hand. A tool without the “changes data” mark is described as only reading, searching or calculating, or the two runs did not agree. No tool was called. Read the publisher’s full description before relying on it. “Publisher declares” lists the hints the server itself sends with the tool (MCP annotations: read-only, destructive, idempotent, open-world); they are the publisher's claims, not checked by us. Inputs are the parameters in the tool's own input schema: name, declared type, whether it is required, and the first sentence of its description. Read 2026-10-23.
How well are its tools described?
Features #4 and #5
How clearly this server's own tool descriptions say what a tool does, and how consistent its tool list is. The first part is an AI model's yes/no reading of each description; the second part is counted. We do not turn it into a grade.
Descriptions
AI reading of each description
- Says what the tool does
- 100% of 16 tools
- Says what it returns
- 93% of 14 tools
- States limits, defaults or errors
- 60% of 15 tools
- Says when to use it
- 75% of 12 tools
- Items covered per tool
- 3.3 of 4 on average
Counted from the listing
- Parameters with a description
- 100% of 52
- Tools with a description
- 100% of 16
- Typical description length
- 288 characters
The tool set
Counted from the listing
- Tools
- 16
- Size of the list
- about 3,416 tokens for an agent to load (characters ÷ 4)
- Naming
- 16 of 16 names use snake_case
AI reading: easy to mix up
No pair found.
The AI items cover 16 of 16 tools: for a tool where two differently worded runs disagreed, that item is left out. They were not checked by hand, and no tool was called. “Easy to mix up” means two tools whose names or descriptions overlap without saying how they differ; the AI found none. We do not rate whether the tool set is complete or whether side effects are spelled out, because our AI reading of those was not reliable enough.
How do I add it to my client?
Config from the registry entry
From the PyPI package metal-gpu-trace
Our sandbox started this package on 2026-10-23 (a read-only session: no tool was called).
Add to CursorAn install link in the format Cursor documents, holding the Cursor config below. The command runs the publisher’s code on your machine.
Claude Desktop · claude_desktop_config.json (Settings → Developer → Edit Config)
{
"mcpServers": {
"metal-gpu-trace": {
"command": "uvx",
"args": [
"metal-gpu-trace==0.7.1"
]
}
}
}Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json
{
"mcpServers": {
"metal-gpu-trace": {
"command": "uvx",
"args": [
"metal-gpu-trace==0.7.1"
]
}
}
}VS Code · .vscode/mcp.json
{
"servers": {
"metal-gpu-trace": {
"type": "stdio",
"command": "uvx",
"args": [
"metal-gpu-trace==0.7.1"
]
}
}
}VS Code (command line) · Bash or zsh terminal (macOS, Linux)
code --add-mcp '{"name":"metal-gpu-trace","type":"stdio","command":"uvx","args":["metal-gpu-trace==0.7.1"]}'Claude Code
claude mcp add --transport stdio metal-gpu-trace -- uvx metal-gpu-trace==0.7.1
Try it in the MCP Inspector · runs on your machine, opens in your browser · Node 22.19+
npx @modelcontextprotocol/inspector@2.11.0 -- uvx metal-gpu-trace==0.7.1
- Optional settings the entry also lists (left out above): METAL_TRACE_OUT, METAL_TRACE_WINE.
- This runs the publisher's code on your machine (uvx). Read its README first.
- The MCP Inspector lists the server's tools, resources and prompts; a tool you call there runs for real.
Built from the server's registry entry with each client's documented format (checked 2026-10-14; the Cursor link and the VS Code command 2026-10-19; the MCP Inspector command 2026-10-21). Values in < > are yours to fill in; this page never contains a key. Where the server needs a setting the entry does not declare, it can still fail to start.
Can it be installed, and is it up to date?
Version pin · advisories
Listed version
- Registry lists
- 0.7.1
- Latest stable
- 0.7.1
- Status
- current
- Withdrawn
- no
Source: pypi.org · 2026-10-23. About the version the registry lists; a manual install may resolve to a different one.
Dependency advisories
Counted in the full dependency tree as resolved on 2026-10-23 (OSV.dev). Bars share one scale. The package itself has no known vulnerability (OSV.dev).
Integrity, provenance, license
- Integrity
- sha256-27ab2edcb483e38bb…
- License
- MIT
Source: the package registry · 2026-10-23.
Usage
- Downloads
- 0 in the last month
Source: pypistats.org · 2026-10-23.
Does the registry listing match what we found?
Feature #6The registry verifies a package once, when it is published, and does not re-check it. A difference below is about the listing, not a judgement of the publisher.
| Registry says | We found | Result | Source · date |
|---|---|---|---|
| Published package can be started | Started and answered | matches | our test · 2026-10-23 |
| Version 0.7.1 on PyPI | Exists and can be installed | matches | PyPI · 2026-10-23 |
| Repository github.com/partprogramming09/metal-gpu-trace | Opens publicly | matches | api.github.com · 2026-10-23 |
Who made it?
Feature #7 · lineage
Facts about the publisher. We do not turn them into a trust score.
- Namespace
- io.github.partprogramming09 · 2 servers
- GitHub owner
- a personal account (partprogramming09)
- Repository
- github.com/partprogramming09/metal-gpu-trace
- Stars
- 0
- Repository age
- 0–30 days
- Last push
- 0–30 days ago
- Archived
- no
- Security policy
- none found (we looked for SECURITY.md in the repository and in its owner’s .github repository)
Source: the registry entry and api.github.com · 2026-10-23; security policy read from GitHub · 2026-10-23.
Publish this server? Run these checks against it yourself before release, from your own machine: a server the command starts, or your own server at its URL after a one-time proof that you control it: npx protocolprobe-selftest.
Choosing
Record checks
Public records · not a safety rating7 of 8 record checks met · 1 does not apply
- #14,745 of 15,112 packages by monthly downloads, tied with 367 others
- Not ranked by stars: 0 stars (ranked from 10)
- MetRegistry entry is active and says how to run itActive, with a package or a remote address.
- MetSource repository link opensThe linked GitHub repository is public.
- MetRepository is not archivedNot archived.
- MetCode pushed to the repository in the 90 days before our checkLast push 0-30 days before our check.
- Not metRepository publishes a security policy (SECURITY.md)No SECURITY.md in the places GitHub reads it from.
- MetPackage names its licence with a standard (SPDX) identifierMIT
- MetThe version the registry lists can be installed and is not withdrawnThe listed version exists and is current.
- Does not applynpm package carries build provenance (attestation)PyPI packages have no npm-style attestation.
- MetNo known critical or high advisory in the package or its dependenciesNone known in the package or its dependency tree.
Read from public records only: the registry entry, npm/PyPI, GitHub and advisory databases, checked 2026-10-23. No tool was called. Only “met” and “not met” are counted, so the total differs between servers; a check that does not apply or that we could not run is listed, never counted against it. It is not a safety rating. How each check works · Leaderboards
Common questions about io.github.partprogramming09/metal-gpu-trace
Answered from the data aboveIs io.github.partprogramming09/metal-gpu-trace safe to install?
We do not rate servers as safe or unsafe. 7 of its 8 applicable record checks are met (facts from public records, each listed on this page). What the records show: Its source repository opens publicly. Its repository had a push in the last 90 days. The listed version is the latest stable release. The package itself has no known vulnerability (OSV.dev). Its full dependency tree has no known advisory. 5 of its tools describe changing data (our AI model's reading of the descriptions). These are facts with their sources on this page, not a safety guarantee, and we did not run its tools.
Has io.github.partprogramming09/metal-gpu-trace been security tested?
Partly. 4 of the 13 checks that apply to it were exercised. We started the package in an isolated sandbox and read what it declares, but this test round was read-only, so its tools were not called. No security verdict is published before verification.
What can io.github.partprogramming09/metal-gpu-trace do?
It lists 16 tools. In our AI model's reading of their descriptions (two runs had to agree, nobody checked it by hand), they include tools that read or search, create or change data and run code or commands. We did not call any tool, so this describes the text, not the behaviour.
Can io.github.partprogramming09/metal-gpu-trace change or delete data?
5 of its tools say in their description that they create, edit, delete, send or run something (our AI model's reading). We did not call any tool, so we cannot say what actually happens.
Does io.github.partprogramming09/metal-gpu-trace publish a security policy?
We found no SECURITY.md in its repository (root, .github/ or docs/) or in its owner's .github repository.
Is the listed version current?
Yes. The registry lists 0.7.1, the latest stable release on PyPI.
Where is the source code of io.github.partprogramming09/metal-gpu-trace?
In github.com/partprogramming09/metal-gpu-trace, which opens publicly.
Found this page useful?
Anonymous · no sign-inA quick, anonymous reaction — no account, no email. One per kind from your browser. The tally updates when the page is next refreshed, and it is only a rough count, never a safety rating or a measured number of people.
Similar servers
Same topic · AI-read
- io.github.cameroncooke/XcodeBuildMCPalso has tools that creates or changes data, runs code or commands, reads or searchescompare with this one
- io.github.callstack/agent-deviceagent-devicealso has tools that creates or changes data, runs code or commands, reads or searchescompare with this one
- io.github.A9T9/uivision-mcpUi.Vision MCPalso has tools that creates or changes data, runs code or commands, reads or searchescompare with this one
- io.github.Buoy-gg/mcpalso has tools that creates or changes data, runs code or commands, reads or searchescompare with this one
- io.github.jumodada/drissionpage-mcpDrissionPage MCPalso has tools that creates or changes data, runs code or commands, reads or searchescompare with this one
- io.github.tugcantopaloglu/godot-mcpGodot MCPalso has tools that creates or changes data, runs code or commands, reads or searchescompare with this one
Active servers whose topic is also “developer-tools” and that have at least one tool of the same kind; most kinds in common first, then most GitHub stars. The topic and the tool kinds are an AI model's reading of the publishers' descriptions, not checked by hand. Similar is not a recommendation.
Compare with another server
Side by side: registry entry, our read-only session, the tools and the 18 classification fields. Same values as each page; no score.
Security testing
What did we test, and what did we leave out?
18 checks · features #1, #2
Not probed (read-only run)
We started the package in an isolated sandbox and read what it declares, but this test round was read-only, so its tools were not called. No security score is given; a check we did not run is never counted as passed.
- Inventory: exercised
- Hidden instructions: exercised
- Real execution: not run · our policy
- Secret leak: not run · nothing to check it against
- Internal addresses: not run · our policy
- Unconfirmed changes: not run · our policy
- Bad input: not run · our policy
- Model requests: not run · nothing to check it against
- Sensitive questions: not run · nothing to check it against
- Folder boundary: not run · our policy
- Log leaks: not run · nothing to check it against
- Hidden content: exercised
- Fake assistant turns: exercised
- Token passthrough: not applicable
- Token audience: not applicable
- Sign-in redirect: not applicable
- Consent handling: not applicable
- Sign-in metadata: not applicable
4 exercised9 not run (reason given)5 not applicable
Each check ends in exactly one state: exercised, not run (with the reason), or not applicable (with the reason). 4 of the 13 checks that apply to it were exercised. We do not publish security-check outcomes for named servers.
- 1Inventory
tool-listReads the declared tools, resources and prompts.exercised - 2Hidden instructions
description-poisoningLooks for hidden instructions in tool descriptions.exercised - 12Hidden content
audience-hidingChecks resources that hide content from the user.exercised - 13Fake assistant turns
fake-assistant-turnChecks prompts that pose as the assistant's own words.exercised
- 3Real execution
real-executionCalls a tool and checks what really happens.This check calls the package's tools. This test round was read-only, so no tool was called; tools can act on outside services with the publisher's or a user's account.not run · our policy - 4Secret leak
canary-leakPlants a fake secret and checks whether it leaks.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 5Internal addresses
ssrfChecks whether a tool can be steered to internal addresses.This check calls the package's tools. This test round was read-only, so no tool was called; tools can act on outside services with the publisher's or a user's account.not run · our policy - 6Unconfirmed changes
write-without-confirmationChecks whether tools that change data act without asking.This check calls the package's tools. This test round was read-only, so no tool was called; tools can act on outside services with the publisher's or a user's account.not run · our policy - 7Bad input
error-handlingSends bad input and watches how the server answers.This check calls the package's tools. This test round was read-only, so no tool was called; tools can act on outside services with the publisher's or a user's account.not run · our policy - 8Model requests
samplingChecks whether the server asks the client's model to act for it.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 9Sensitive questions
elicitation-sensitive-dataChecks whether the server asks users for sensitive data.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 10Folder boundary
root-boundaryChecks whether the server reaches outside the folders it was given.This check calls the package's tools. This test round was read-only, so no tool was called; tools can act on outside services with the publisher's or a user's account.not run · our policy - 11Log leaks
logging-side-channelChecks whether log messages carry data they should not.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
- 14Token passthrough
token-passthroughChecks whether the server forwards a user's token to other services.The server runs locally over standard input/output, so there is no sign-in flow to check.not applicable - 15Token audience
token-audience-validationChecks whether tokens meant for another service are accepted.The server runs locally over standard input/output, so there is no sign-in flow to check.not applicable - 16Sign-in redirect
open-redirectChecks the sign-in redirect for abuse.The server runs locally over standard input/output, so there is no sign-in flow to check.not applicable - 17Consent handling
confused-deputyChecks consent handling when one service acts for another.The server runs locally over standard input/output, so there is no sign-in flow to check.not applicable - 18Sign-in metadata
oauth-url-schemeChecks the published sign-in metadata for unsafe URLs.The server runs locally over standard input/output, so there is no sign-in flow to check.not applicable
Source: our own test in an isolated sandbox, 2026-10-23, mcp-runtime-engine@0.1.0. Which checks count and why follows our published scoring model.
What happened during the test?
Feature #8
The steps in order, as the test record holds them.
- 0 msStarted the published package in an isolated sandbox (read-only mode)
- 739 msConnected after 0 redirects.
- Read the inventory: 16 tools, 5 resources, 1 prompt.
- 1,248 msFinished: 4 checks exercised.
Reference
How is it classified?
18 fields
One value per field, each with its source. Fields written by AI models are marked. A field with no value says why.
“Not stated” means the source did not state it; “does not apply” means it does not apply to this kind of server; “our limit” means our own lookup failed. A linked value opens the directory filtered to the same value.
Cite or correct this page
Sources and corrections
Suggested citation
ProtocolProbe. “io.github.partprogramming09/metal-gpu-trace: MCP server record.” Data checked 2026-10-23. https://protocolprobe.com/mcp/servers/io.github.partprogramming09/metal-gpu-trace
Figures are valid for the date shown. Our facts on this page are CC BY 4.0: reuse them with a link and the check date. Quoted text (the publisher’s descriptions, website quotes, tool names) is not ours to license.
As JSON: this record in the API · API documentation.
Badge for your README
[](https://protocolprobe.com/mcp/servers/io.github.partprogramming09/metal-gpu-trace)
It shows this server's record-check count: facts from public records, no tool called. It is not a security rating or a pass. It links here and updates after each data reload.
Something wrong, or is this yours?
If a fact here is wrong, tell us and we will re-check it. If you operate this server, you can run our checks on it yourself with the free self-test command; we call no server’s tools ourselves for anything shown here.
Write to hello@protocolprobe.com · corrections log · methodology