CarMaker
PYPI · CARMAKER-MCP
Drive IPG CarMaker for Simulink: run test runs, read results, edit vehicle data and parameters.
Available components
Last scanned (11 hours ago)
Scores higher than 93% of PyPI servers
Category Testing and QA
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security100
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- Runs setuptools.build_meta at install time, a recognised build step with no custom scripting around it. View diagnostics → Pass
- 1 of 16 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency100
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Cryptographically verified build provenance (signed, bound to dimitr-io/carmaker-mcp). View diagnostics → Pass
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 3 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability78
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 8019 tokens (~138/item across 58 items; 54 tools + 4 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management57
- Stability observed for 17 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
- Structured output schemas are declared (93% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- All 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
- An AI judge read all 56 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (2026-07-28).Pass
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 5 Nov 26 +16
- Malware scan: unverified → pass ▲ security
- 4 Nov 26 −15
- Malware scan: pass → unverified ▼ security
- 2 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.
- 1 Nov 26 0
- Stability: 0.40 → unverified ▼ security
- Tool safety: pass → unverified ▼ security
- Schema quality: 106 → 138 ▼ functional
- Capabilities: pass → unverified ▼ functional
- Tool coverage: 100 → unverified ▼ functional
- Schema quality: 100 → unverified ▼ functional
- Package version: 0.2.2 → 0.3.0 functional
- 30 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.
- 27 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.
- 25 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.
- 23 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 5 Nov 2026 · Analysed pypi/carmaker-mcp@0.3.0
Provenance Verified
A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.
| Result | Verified |
|---|---|
| Ecosystem | pypi |
| Reason | Verified |
| Discovered via | Registry attestation endpoint |
| Source repo | dimitr-io/carmaker-mcp |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/dimitr-io/carmaker-mcp/.github/workflows/release.yml@refs/tags/v0.3.0 |
| Rekor log index | 3634638913 |
| Predicate type | PyPI publish attestation https://docs.pypi.org/attestations/publish/v1 |
| Subject digest | sha256:8119a31ef770373f7ce5c9f0d28754822651ceee99d356629e333db20427e6ca |
Background: How many MCP packages publish verified provenance →
Install scripts 1 script
| Hook | Tier | Command |
|---|---|---|
| build_backend | allowlisted | setuptools.build_meta |
Background: Why install scripts are a supply-chain risk →
Dependencies 16 packages
| Packages resolved | 16 |
|---|---|
| Stale | 1 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
cm_study_start Start a parameter study ~757
Run one test run several times with different parameter values, one after another, in the background. Returns a study id at once; wait with cm_study_wait. Nothing is written to project files. The answer names values that will change nothing: keys_not_found, workspace_not_found and workspace_overruled (use scope=<model>); Driver.* keys that a driver template overrides are refused (use 'driver'). Rows give valid and wall_s, the clock time of the run. A study stops at the first run that finds no CarMaker licence.
| Name | Type | Req | Description |
|---|---|---|---|
| close_open | boolean | – | standalone: first close the CarMaker programs this server left open (each holds a licence) |
| gates | – | – | 'markers': each row gets 'sectors', the times CarMaker's lap timing takes at the test run's trigger point markers, each from the last reference marker (a lap on a skid pad). Or road positions in m: '… |
| grid | – | – | Every combination of value lists, added to variations: {'driver': {'Driver.Acc.ayMax': [12, 14]}, 'driver_scale': {'Driver.Acc.GGExp': [1, 2, 4]}, 'keys': {...}, 'workspace': {...}}. driver_scale mul… |
| keep_open | boolean | – | With movie: leave the last run in IPGMovie (close it with cm_standalone_close) |
| keys | – | – | Keys for every run, e.g. {'Vehicle': 'Car_B'}; a variation's own keys win |
| max_run_s | number | – | A run is stopped after this wall time in s |
| mode | string | – | cm4sl: the MATLAB-connected session. standalone: CarMaker without MATLAB (no 'workspace' values). auto: cm4sl if MATLAB is connected |
| movie | boolean | – | mode standalone: show the runs in IPGMovie |
| quantities | – | – | Quantities to summarise per run (default: Time, Car.v). Standalone they are also all its result file stores, besides what timing needs: list every quantity to plot later |
| rerun | – | – | Runs of an earlier study again: {'study': id, 'labels': ['best']}, e.g. with movie and keep_open to show the best run; an IPGMovie window kept open is reused |
| save_logs | boolean | – | After every run, save what Simulink logged and the workspaces as that run used them to a MAT file next to its result file (mode cm4sl; logs_file per row) |
| scope | string | – | 'base' for the MATLAB base workspace, or the name of a loaded Simulink model for that model's workspace |
| speed | – | – | x real time; omit for CarMaker's maximum. Slower only if the user asks |
| testrun | – | – | Test run relative to Data/TestRun (with rerun: default its study's) |
| variations | – | – | One entry per run: {'label': 'heavy', 'keys': {'Body.mass': 320}, 'workspace': {'Kp_yaw': 1.5}, 'driver': {'Driver.Acc.ayMax': 14, 'Driver.Acc.GGExp': '10 1.5 1.5\n90 5 5'}}. 'keys': infofile keys in… |
Structured output declared, but exposes no named fields.
No examples provided.
cm_study_status Parameter study progress and results ~215
State of a study (running, done, cancelled, failed) and one row per finished run, which also maps every label to its result file. The ranking names each run's result file. To wait use cm_study_wait.
| Name | Type | Req | Description |
|---|---|---|---|
| detail | string | – | brief: per run label, valid, end status, sector or split times, abort reason. compact: also time, distance, result file and min / max / mean / last of the quantities. full: also every run's keys, wor… |
| labels | – | – | Only these rows |
| rank_by | – | – | Rank the valid runs: 'sectors' (mean sector time), 'splits' (their sum), 'sim_time', or a quantity statistic such as 'Car.v.max'; '-' first for largest first |
| study | – | – | Study id (default: the latest) |
| top | – | – | Only the best N of the ranking |
| with_studies | – | – | Rank these studies' runs together with this one's |
Structured output declared, but exposes no named fields.
No examples provided.
cm_study_wait Wait for a parameter study ~199
Wait until another run of the study has finished or the study has ended, at most timeout_s, and return the rows no earlier call returned (cm_study_status has the whole table and rank_by). Call it again while state is 'running'. Use this for studies instead of cm_wait_end.
| Name | Type | Req | Description |
|---|---|---|---|
| detail | string | – | brief: per run label, valid, end status, sector or split times, abort reason. compact: also time, distance, result file and min / max / mean / last of the quantities. full: also every run's keys, wor… |
| study | – | – | Study id (default: the latest) |
| timeout_s | number | – | Longest time to wait in s, at most 50 (larger values are cut to 50); call again if not finished |
| until_done | boolean | – | Return only when the study has ended (or at timeout_s) |
Structured output declared, but exposes no named fields.
No examples provided.
cm_wait_end Wait for the simulation to end ~113
Wait until the simulation is idle again. finished=true: end status, simulation time and distance, result_file, new log errors and warnings (settings CarMaker ignored show up there) and pop-ups. finished=false: current state and live values; call again to keep waiting.
| Name | Type | Req | Description |
|---|---|---|---|
| poll_s | number | – | Seconds between status polls |
| timeout_s | number | – | Longest time to wait in s, at most 50 (larger values are cut to 50); call again if not finished |
| Name | Type | Req | Description |
|---|---|---|---|
| distance_m | number | – | – |
| elapsed_s | number | – | – |
| end_status | – | – | – |
| finished | boolean | – | – |
| live | object | – | – |
| log_errors | array | – | – |
| log_warnings | array | – | – |
| logs_error | string | – | – |
| logs_file | string | – | – |
| note | string | – | – |
| poll_errors | integer | – | – |
| popups | array | – | – |
| result_file | – | – | – |
| sim_time_s | number | – | – |
| simulink_error | string | – | – |
| state | string | – | – |
| stop_requested | boolean | – | – |
| testrun | string | – | – |
| waited_s | number | – | – |
No examples provided.
How do I install the CarMaker MCP server?
CarMaker runs locally as a PyPI package, launched with uvx carmaker-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
pypi · carmaker-mcp
claude mcp add dimitr-io-carmaker-mcp -- uvx carmaker-mcp
What is the CarMaker MCP server?
CarMaker is an MCP server listed in the public MCP registry as io.github.dimitr-io/carmaker-mcp. Drive IPG CarMaker for Simulink: run test runs, read results, edit vehicle data and parameters. This page covers its PyPI package (carmaker-mcp).
Is the CarMaker MCP server safe to use?
CarMaker scores 90 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 2026. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the CarMaker MCP server expose?
CarMaker exposes 54 tools: cm_session_start, cm_doctor, cm_status, cm_load_testrun, cm_start_sim, and 49 more. Their descriptions and schemas cost roughly 6,980 tokens of context every time the server is loaded.
Is the CarMaker MCP server still maintained?
CarMaker is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the CarMaker MCP server under?
CarMaker declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.