io.github.Axius-SDC/sdcmodeler
PYPI · SDCMODELER
The modeler's client for SDCStudio: search the catalog, estimate, assemble and publish SDC4 models.
Available components
Last scanned (17 hours ago)
Scores higher than 88% of PyPI servers
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
- 0 of 8 dependencies flagged as unhealthy. View diagnostics → Pass
Provenance & Transparency100
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Cryptographically verified build provenance (signed, bound to Axius-SDC/sdcmodeler). View diagnostics → Pass
- Clear OSI-approved license (Apache-2.0).Pass
- Actively maintained (last published 2 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability61
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 1385 tokens (~138/item across 10 items; 10 tools + 0 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 Coverage77
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 30% of tool parameters carry a description.Partial
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 10 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 11 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Checks we ran (16)
- Malware scan
- Known CVEs
- Install scripts
- Dependency health
- Source repository
- Provenance
- License
- Maintenance
- Security disclosure
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Does not apply to this package (2)
- Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
- Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
The score does not measure everything. What the score does not measure →
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 +15
- Malware scan: unverified → pass ▲ security
- 4 Nov 26 −14
- Malware scan: pass → unverified ▼ security
- 3 Nov 26 +15
- Malware scan: unverified → pass ▲ security
- 2 Nov 26 +1
- Schema quality: 1159 → 1385 ▼ functional
- Package version: 4.3.2 → 4.4.1 functional
- Package version: 4.3.2 → 4.4.0 functional
- 30 Oct 26 −14
- Malware scan: pass → unverified ▼ security
- 29 Oct 26 +15
- Malware scan: unverified → pass ▲ security
- 28 Oct 26 −14
- Malware scan: pass → unverified ▼ security
- 27 Oct 26 +15
- Malware scan: unverified → pass ▲ security
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/sdcmodeler@4.4.1
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 | Axius-SDC/sdcmodeler |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/Axius-SDC/sdcmodeler/.github/workflows/release.yml@refs/tags/v4.4.1 |
| Rekor log index | 3644496932 |
| Predicate type | PyPI publish attestation https://docs.pypi.org/attestations/publish/v1 |
| Subject digest | sha256:df6c7f7c8b252c8b326540fa8ea65e247dbfdab614b2484eda4850676e15e63d |
Background: How many MCP packages publish verified provenance →
Install scripts 1 script
| Hook | Tier | Command |
|---|---|---|
| build_backend | Known build tool | setuptools.build_meta |
Background: Why install scripts are a supply-chain risk →
Dependencies 8 packages
| Packages resolved | 8 |
|---|---|
| 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 →
add_supabase_kit ~202
Write a published model's governed data kit into a Supabase project: typed TypeScript for the model's records, the gate (an Edge Function that validates every record against the published model before storing it) and the migrations. The first call writes the project base too; call again for each further model. Components already in the project are never rewritten, and each migration is written once, numbered after the project's latest. Then apply them with Supabase's own CLI or MCP server (supabase db push; supabase functions deploy gate). The first download of a model by this user, kit or application, costs 1,500 credits; later downloads of the same model are free. Needs confirm_charge true, after the person has agreed.
| Name | Type | Req | Description |
|---|---|---|---|
| confirm_charge | boolean | – | – |
| ct_id | string | yes | – |
| project_dir | string | – | The project holding supabase/, relative to the server's output directory. Default: the output directory. |
No output schema declared.
No examples provided.
build_model ~263
Assemble and publish the model the person estimated and approved. Needs the estimate_id from estimate_model for the same title and tree; refuses otherwise, the server refuses a stale one too, and refuses when the estimate exceeds what the key may still spend. Spends credits: 500 for the model plus 100 per minted component or new cluster. With every leaf existing the model is published and its package generated at once (result has ct_id and artifacts); with new leaves the pipeline runs and the result has a job_ct_id to poll with job_status; when the job completes it has published and generated as asked and carries the model's links. publish false leaves a draft for a person to review. A 402 means the wallet needs funding at the wallet page; report it and stop.
| Name | Type | Req | Description |
|---|---|---|---|
| contextual | object | – | Optional contextual component references (audit, attestation, party, subject, provider, participation, protocol, workflow, acs). |
| description | string | – | – |
| estimate_id | string | yes | – |
| generate | boolean | – | Build the package after publishing (needs publish). |
| publish | boolean | – | Publish the clusters and the model (false leaves a draft for a person to review). |
| title | string | yes | – |
| tree | object | yes | – |
No output schema declared.
No examples provided.
download_package ~137
Download a model's package (the ZIP: schema, XML template and JSON instance of the Governed Data Record, JSON-LD, HTML, RDF, SHACL, GQL) into the server's output directory, with this key: it works for a model in a private project, such as the one build_model just made, where get_model and the public catalog do not. When the model is published and its package not yet built, it builds it first (free, once; it needs the right to publish the model); generate false only downloads. Free.
| Name | Type | Req | Description |
|---|---|---|---|
| ct_id | string | yes | – |
| generate | boolean | – | – |
No output schema declared.
No examples provided.
estimate_model ~124
What assembling this model would reuse, mint and cost, in credits, computed before any money moves. Takes the title and the assembly tree ({label, components: [{ct_id} to reuse or {label, data_type} to mint], clusters: [...]}). Returns estimate_id, the reused and minted leaves, problems in the tree, and total_credits (500 for the model plus 100 per mint). Show the result to the person; build_model needs the estimate_id. Free.
| Name | Type | Req | Description |
|---|---|---|---|
| title | string | yes | – |
| tree | object | yes | The assembly tree. |
No output schema declared.
No examples provided.
generate_app ~124
Generate a published model's application (lightweight or enterprise profile; a Django stack on the model package, one example of implementing on it) and download it into the server's output directory. The first download of a model by this user costs 1,500 credits; later downloads of the same model are free. Needs confirm_charge true, after the person has agreed. Prefer the model package (get_model's artifacts) when the feature lives inside an existing application.
| Name | Type | Req | Description |
|---|---|---|---|
| confirm_charge | boolean | – | – |
| ct_id | string | yes | – |
| profile | string | – | – |
No output schema declared.
No examples provided.
get_model ~69
One published data model: title, description, project, its components, and the artifact routes (xsd, xml, json, jsonld, html, ttl, shacl, gql, zip). The XSD is the contract every record validates against. Free.
| Name | Type | Req | Description |
|---|---|---|---|
| ct_id | string | yes | – |
No output schema declared.
No examples provided.
job_status ~76
One job (job_ct_id from build_model): status queued, running, completed or failed; step; cost_credits so far; on completion the model's links (dm_ct_id, catalog_url, package_url); on failure the reason. Poll every few seconds, backing off. Free.
| Name | Type | Req | Description |
|---|---|---|---|
| job_ct_id | string | yes | – |
No output schema declared.
No examples provided.
list_models ~46
Published data models in the public catalog, by words in the title. Free.
| Name | Type | Req | Description |
|---|---|---|---|
| page | integer | – | – |
| page_size | integer | – | – |
| query | string | – | – |
No output schema declared.
No examples provided.
search_components ~157
Search SDCStudio's public catalog of published components by label, with optional type (xdstring, xdcount, xdquantity, xdtemporal, cluster, party, ...) and project. Reuse first: a published component that fits is free to assemble; minting a new one costs 100 credits. Returns ct_id, label, description, component_type, project_name and reuse_ref for each result. Free; no key needed.
| Name | Type | Req | Description |
|---|---|---|---|
| page | integer | – | – |
| page_size | integer | – | – |
| project | string | – | Optional project name to filter by, e.g. a public library. |
| query | string | yes | Words from the label or description. |
| type | string | – | Optional component type to filter by. |
No output schema declared.
No examples provided.
wallet ~32
The wallet balance in credits and this key's policy: scopes, spending limit, what it has spent, expiry. Free.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
How do I install the io.github.Axius-SDC/sdcmodeler MCP server?
io.github.Axius-SDC/sdcmodeler runs locally as a PyPI package, launched with uvx sdcmodeler 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 · sdcmodeler
claude mcp add axius-sdc-sdcmodeler -- uvx sdcmodeler mcp
What is the io.github.Axius-SDC/sdcmodeler MCP server?
io.github.Axius-SDC/sdcmodeler is an MCP server listed in the public MCP registry as io.github.Axius-SDC/sdcmodeler. The modeler's client for SDCStudio: search the catalog, estimate, assemble and publish SDC4 models. This page covers its PyPI package (sdcmodeler).
Is the io.github.Axius-SDC/sdcmodeler MCP server safe to use?
io.github.Axius-SDC/sdcmodeler scores 85 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 io.github.Axius-SDC/sdcmodeler MCP server expose?
io.github.Axius-SDC/sdcmodeler exposes 10 tools: search_components, list_models, get_model, estimate_model, build_model, and 5 more. Their descriptions and schemas cost roughly 1,230 tokens of context every time the server is loaded.
Is the io.github.Axius-SDC/sdcmodeler MCP server still maintained?
io.github.Axius-SDC/sdcmodeler 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 io.github.Axius-SDC/sdcmodeler MCP server under?
io.github.Axius-SDC/sdcmodeler declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.
What did VerifyMCP test on the io.github.Axius-SDC/sdcmodeler MCP server?
VerifyMCP ran 16 checks on io.github.Axius-SDC/sdcmodeler, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. Endpoint Security and Transport & Reachability do not apply to a PyPI package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.