ModelRisk
PYPI · MODELRISK-MCP · SCANNED SEP 21
Read, build, fit, and run Monte Carlo risk models in Excel through Vose Software's ModelRisk.
Available components
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 Security50
- Malware scan not yet available for this package.Unverified
- No known CVEs affecting this package version or its production dependencies.Pass
- Runs hatchling.build at install time, a recognised native-build step with no shell scripting around it. View diagnostics → Pass
- 1 of 35 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency6
- Repository check failed: no source repository is declared. See how to fix → View diagnostics → Fail
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- License check failed: no license is declared. See how to fix → Fail
- Actively maintained (last published 36 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability83
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 9507 tokens (~146/item across 65 items; 59 tools + 6 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 Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage88
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 58% of tool parameters carry a description.Partial
- Structured output schemas are declared (100% 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
- We read all 59 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 61 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
How do I install the ModelRisk MCP server?
ModelRisk runs locally as a PyPI package, launched with uvx modelrisk-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 · modelrisk-mcp
claude mcp add vosesoftware-modelrisk-mcp -- uvx modelrisk-mcp
{
"mcpServers": {
"vosesoftware-modelrisk-mcp": {
"command": "uvx",
"args": [
"modelrisk-mcp"
]
}
}
} {
"servers": {
"vosesoftware-modelrisk-mcp": {
"command": "uvx",
"args": [
"modelrisk-mcp"
]
}
}
} codex mcp add vosesoftware-modelrisk-mcp -- uvx modelrisk-mcp
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"vosesoftware-modelrisk-mcp": {
"type": "local",
"command": [
"uvx",
"modelrisk-mcp"
],
"enabled": true
}
}
} openclaw mcp add vosesoftware-modelrisk-mcp --command uvx --arg modelrisk-mcp
mcp_servers:
vosesoftware-modelrisk-mcp:
command: "uvx"
args: ["modelrisk-mcp"] {
"McpServers": {
"vosesoftware-modelrisk-mcp": {
"Transport": "stdio",
"Command": "uvx",
"Arguments": [
"modelrisk-mcp"
]
}
}
} assistant mcp add vosesoftware-modelrisk-mcp -t stdio -c uvx -a modelrisk-mcp
{
"mcpServers": {
"vosesoftware-modelrisk-mcp": {
"command": "uvx",
"args": [
"modelrisk-mcp"
]
}
}
} 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.
- 21 Sept 26 0
- Stability: 0.97 → pass security
- 20 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.
- 18 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.
- 16 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.
- 15 Sept 26 −3
- Stability: pass → 0.80 functional
- 14 Sept 26 −15
- Malware scan: pass → unverified ▼ security
- Stability: 0.97 → pass security
- 13 Sept 26 +16
- Malware scan: unverified → pass ▲ security
- 12 Sept 26 −15
- Malware scan: pass → unverified ▼ 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 21 Sept 2026 · Analysed pypi/modelrisk-mcp@0.4.0
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | pypi |
Background: How many MCP packages publish verified provenance →
Install scripts 1 script
| Hook | Tier | Command |
|---|---|---|
| build_backend | allowlisted | hatchling.build |
Background: Why install scripts are a supply-chain risk →
Dependencies 35 packages
| Packages resolved | 35 |
|---|---|
| No linked repository | 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 →
read_vmrs ~86
ModelRisk: Read simulation results directly from a `.vmrs` file. Convenience wrapper for `set_active_vmrs` + `get_simulation_results` that doesn't need an open workbook. Pass `output_names` to filter; leave empty to attempt enumeration of all known outputs.
| Name | Type | Req | Description |
|---|---|---|---|
| output_names | – | – | – |
| path | string | yes | Absolute path to a .vmrs file. |
Structured output declared, but exposes no named fields.
No examples provided.
replace_constant_with_distribution ~115
ModelRisk: Replace a hard-coded number in a cell with a Vose distribution wrapped by VoseInput. Use after find_hard_coded_inputs identifies candidates. This is the only tool that overwrites a non-Vose cell — it does so by design.
| Name | Type | Req | Description |
|---|---|---|---|
| cell | string | yes | – |
| dry_run | boolean | – | – |
| function_name | string | yes | – |
| input_name | string | yes | – |
| parameters | array | yes | – |
| sheet | string | yes | – |
| workbook | string | yes | – |
| Name | Type | Req | Description |
|---|---|---|---|
| cell | – | yes | – |
| formula | string | yes | – |
| previous_formula | – | – | – |
| written | boolean | yes | – |
No examples provided.
restore_cell ~110
ModelRisk: Restore a cell to its pre-write state from the audit log. Reads %LOCALAPPDATA%\VoseSoftware\modelrisk-mcp\writes.log and rewrites the oldest captured before-formula for the cell. Pass `since` (ISO timestamp) to restrict the window.
| Name | Type | Req | Description |
|---|---|---|---|
| cell | string | yes | – |
| sheet | string | yes | – |
| since | – | – | Optional ISO-8601 timestamp. Restore the oldest write captured at or after this time. |
| workbook | string | yes | – |
| Name | Type | Req | Description |
|---|---|---|---|
| cell | – | yes | – |
| formula | string | yes | – |
| previous_formula | – | – | – |
| written | boolean | yes | – |
No examples provided.
restore_deterministic_state ~131
ModelRisk: Recover a workbook that's been left in a 'frozen sample' state — VoseOutput cells stuck on per-iteration sample values instead of their deterministic baseline. Triggers a full Excel recalculation (Application.CalculateFull) which re-evaluates every formula and restores the deterministic values. Use this after `run_simulation` raises a post-condition error, or whenever `list_modelrisk_outputs` shows nonsense `current_value`s that look like a single sample draw rather than the model's deterministic answer.
| Name | Type | Req | Description |
|---|---|---|---|
| workbook_name | – | – | Workbook to recalculate. Omit for the active workbook. |
Structured output declared, but exposes no named fields.
No examples provided.
reverse_stress_test ~268
ModelRisk: Reverse stress test — start from a BAD output outcome and work back to the joint input state that produces it. Partitions the simulation's iterations into breach / no-breach (output above/below a threshold, given directly or as a percentile), then for each input reports how far its mean shifts inside the breach set (in its own standard deviations) and how concentrated breaches are in its tail — a breach-driver tornado — plus the mean input vector as a concrete named stress scenario. This is the Solvency II / PRA 'reverse stress test' and is only possible with the engine's recorded per-iteration joint sample matrix (requires a completed simulation).
| Name | Type | Req | Description |
|---|---|---|---|
| direction | string | – | Breach side: 'above' (default) or 'below' the threshold. |
| max_n | integer | – | Max samples per variable to pull. Default 100000. |
| output_name | string | yes | VoseOutput name to stress. |
| threshold | – | – | Breach threshold on the output. Omit to use threshold_percentile. |
| threshold_percentile | – | – | Breach threshold as an output percentile (0-1), e.g. 0.95. Used when `threshold` is omitted. |
| workbook_name | – | – | Workbook name. Omit for the active workbook. |
| Name | Type | Req | Description |
|---|---|---|---|
| breach_count | integer | yes | – |
| breach_probability | number | yes | – |
| direction | string | yes | 'above' or 'below' — the breach side of the threshold. |
| drivers | array | yes | Inputs ranked by how far they shift in the breach set. |
| iterations | integer | yes | – |
| note | string | yes | – |
| output_name | string | yes | – |
| scenario | – | – | The mean input vector over the breach iterations. |
| threshold | number | yes | – |
No examples provided.
run_scenarios ~218
ModelRisk: Sweep a single input cell across multiple deterministic values, running a full simulation at each. Returns per-output P5 / P50 / P95 / mean for every scenario value. Useful for what-if analysis: 'what if widget cost is $50 vs $75 vs $100'. The cell's original formula is captured before the sweep and restored afterwards (even on error), so the workbook ends in its pre-call state. Each scenario takes roughly the same time as one `run_simulation` call, so keep the values list short — 3-7 scenarios is a normal range.
| Name | Type | Req | Description |
|---|---|---|---|
| cell | string | yes | A1-style cell reference for the input to sweep. |
| samples | integer | – | Iterations per scenario. |
| seed | integer | – | Fixed seed (same seed across scenarios). |
| sheet | string | yes | Sheet name holding the input cell. |
| values | array | yes | Deterministic values to test (1-20 scenarios). |
| workbook_name | – | – | Workbook name. Omit for the active workbook. |
| Name | Type | Req | Description |
|---|---|---|---|
| cell | string | yes | – |
| original_formula | string | – | – |
| samples_per_scenario | integer | – | – |
| scenarios | array | – | – |
| sheet | string | yes | – |
| workbook_name | string | yes | – |
No examples provided.
run_simulation ~310
ModelRisk: Run a Monte Carlo simulation on the active (or named) workbook and save the results to a `.vmrs` file. Defaults to 1000 iterations with a fixed seed for reproducibility, and saves the .vmrs next to the workbook as `<book>.vmrs`. The simulation is run via the same XLL commands ModelRisk's own ribbon uses (VoseStartSimulCustom12 + VoseGetDataSZ12 with the SaveResultsToFile session), so behaviour matches what you'd see clicking 'Simulate' manually. Blocks until the simulation completes. After this returns, call get_simulation_results — the produced .vmrs is automatically pinned as the active results source.
| Name | Type | Req | Description |
|---|---|---|---|
| iterations | – | – | Alias for `samples`. ModelRisk's UI calls this 'samples'; many users call it 'iterations'. Both work. |
| samples | – | – | Iteration count. Default: 1000. Either `samples` or `iterations` is accepted (they mean the same thing). If both are passed, `samples` wins. |
| save_to | – | – | Absolute path to write the .vmrs. Default: next to the workbook as `<book_stem>.vmrs`. For OneDrive-hosted workbooks (where path resolution can fail) the default falls back to the user's Desktop fold… |
| seed | integer | – | Random seed for reproducibility (fixed seed). |
| workbook_name | – | – | Workbook file name (e.g. 'model.xlsx'). Omit for the active workbook. |
| Name | Type | Req | Description |
|---|---|---|---|
| next_step | string | yes | Suggested follow-up call for the MCP client — typically `get_simulation_results` to pull the per-output statistics. |
| samples | integer | yes | – |
| seed | integer | yes | – |
| vmrs_path | string | yes | – |
| workbook_name | string | yes | – |
No examples provided.
save_workbook_as ~114
ModelRisk: Save the workbook to a specific path on disk. Distinct from the user's Ctrl+S — the MCP server never calls Workbook.Save() implicitly. Use only when the caller explicitly named a target file. Refuses to overwrite an existing file unless overwrite=True. Returns the resolved absolute path that was written.
| Name | Type | Req | Description |
|---|---|---|---|
| overwrite | boolean | – | – |
| path | string | yes | Absolute path. Must end in .xlsx, .xlsm, .xlsb, or .xls. |
| workbook | string | yes | – |
Structured output declared, but exposes no named fields.
No examples provided.
set_active_vmrs ~100
ModelRisk: Pin a specific `.vmrs` file as the source of simulation results. Pass the absolute path of the file; subsequent calls to get_simulation_results / get_correlation_matrix / get_sensitivity_ranking will read from it instead of trying to locate a sibling file next to the workbook. Pass an empty string to clear the override.
| Name | Type | Req | Description |
|---|---|---|---|
| path | string | yes | Absolute path to a .vmrs file, or '' to clear. |
Structured output declared, but exposes no named fields.
No examples provided.
set_named_range ~90
ModelRisk: Create or overwrite a workbook-level named range. Useful for giving cells clear identities the LLM can reference by name later. The reference must be A1-style (e.g. 'Sheet1!$A$1:$A$10').
| Name | Type | Req | Description |
|---|---|---|---|
| dry_run | boolean | – | – |
| name | string | yes | – |
| range_ref | string | yes | – |
| workbook | string | yes | – |
Structured output declared, but exposes no named fields.
No examples provided.
wrap_with_input ~72
ModelRisk: Wrap an existing distribution cell with VoseInput("name")+ so it appears in the input list and the Results Viewer.
| Name | Type | Req | Description |
|---|---|---|---|
| cell | string | yes | – |
| dry_run | boolean | – | – |
| name | string | yes | – |
| sheet | string | yes | – |
| workbook | string | yes | – |
| Name | Type | Req | Description |
|---|---|---|---|
| cell | – | yes | – |
| formula | string | yes | – |
| previous_formula | – | – | – |
| written | boolean | yes | – |
No examples provided.
wrap_with_output ~71
ModelRisk: Wrap an existing output cell with VoseOutput("name")+ so it appears in the output list and Results Viewer.
| Name | Type | Req | Description |
|---|---|---|---|
| cell | string | yes | – |
| dry_run | boolean | – | – |
| name | string | yes | – |
| sheet | string | yes | – |
| workbook | string | yes | – |
| Name | Type | Req | Description |
|---|---|---|---|
| cell | – | yes | – |
| formula | string | yes | – |
| previous_formula | – | – | – |
| written | boolean | yes | – |
No examples provided.
write_formula ~238
ModelRisk: Write an arbitrary formula or value into a single cell. Use this for wiring cells (e.g. =A1*B1, =SUM(...), =IF(...), or links to other sheets) that aren't covered by the Vose-specific tools. Safety: refuses to overwrite a cell containing an existing formula unless allow_overwrite=True — that protects user-written formulas AND prior Vose distributions. Empty cells write freely. Defaults to dry_run=True; pass dry_run=False to commit. Every commit appends to the audit log so `restore_cell` can roll back.
| Name | Type | Req | Description |
|---|---|---|---|
| allow_overwrite | boolean | – | Permit overwriting a non-empty cell. Required if the cell already has any content. Without this flag the tool refuses and returns the existing formula so Claude can decide what to do. |
| cell | string | yes | A1 cell reference like 'C1'. |
| dry_run | boolean | – | – |
| formula | string | yes | Formula or value to write. Excel-style; leading '=' is optional (we'll add it if missing for non-numeric content). |
| sheet | string | yes | – |
| workbook | string | yes | – |
| Name | Type | Req | Description |
|---|---|---|---|
| cell | – | yes | – |
| formula | string | yes | – |
| previous_formula | – | – | – |
| written | boolean | yes | – |
No examples provided.
What is the ModelRisk MCP server?
ModelRisk is an MCP server listed in the public MCP registry as io.github.vosesoftware/modelrisk-mcp. Read, build, fit, and run Monte Carlo risk models in Excel through Vose Software's ModelRisk. This page covers its PyPI package (modelrisk-mcp).
Is the ModelRisk MCP server safe to use?
ModelRisk scores 62 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 September 2026. 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 ModelRisk MCP server expose?
ModelRisk exposes 59 tools: list_open_workbooks, get_active_workbook, open_workbook, close_workbook, get_workbook_summary, and 54 more. Their descriptions and schemas cost roughly 9,139 tokens of context every time the server is loaded.
Is the ModelRisk MCP server still maintained?
ModelRisk is still listed as active in the MCP registry. We last reached this channel on 21 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.