# com.ascent-partners/coso-mcp (npm · @simonmak-ascent/coso-mcp)

Open COSO internal-control review MCP: scope, risk, controls, sampling, testing, workpapers.

- Trust score: 68/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-17

## Components

- remote · `internal-control.ascent-partners.com`: 65/100, [markdown](https://verifymcp.io/servers/com-ascent-partners-coso-mcp/internal-control.md), [page](https://verifymcp.io/servers/com-ascent-partners-coso-mcp/internal-control)
- npm · `@simonmak-ascent/coso-mcp`: 68/100 (this document), [markdown](https://verifymcp.io/servers/com-ascent-partners-coso-mcp/simonmak-ascent-coso-mcp.md), [page](https://verifymcp.io/servers/com-ascent-partners-coso-mcp/simonmak-ascent-coso-mcp)

## Channel facts

- Registry: `npm`
- Package: `@simonmak-ascent/coso-mcp`
- Version: `0.1.2`
- Transport: `stdio`

## Trust breakdown

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. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-17.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 0 of 6 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 48/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 2 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 72/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (fair).
  - Tool/resource definitions use about 1978 tokens (~49/item across 40 items; 39 tools + 1 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 74/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 8% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 39 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 40 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### How do I install the com.ascent-partners/coso-mcp server?

com.ascent-partners/coso-mcp runs locally as an npm package, launched with npx -y @simonmak-ascent/coso-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add com-ascent-partners-coso-mcp -- npx -y @simonmak-ascent/coso-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "com-ascent-partners-coso-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@simonmak-ascent/coso-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-ascent-partners-coso-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@simonmak-ascent/coso-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add com-ascent-partners-coso-mcp -- npx -y @simonmak-ascent/coso-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-ascent-partners-coso-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@simonmak-ascent/coso-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-ascent-partners-coso-mcp --command npx --arg -y --arg @simonmak-ascent/coso-mcp
```

### Hermes

```yaml
mcp_servers:
  com-ascent-partners-coso-mcp:
    command: "npx"
    args: ["-y", "@simonmak-ascent/coso-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "com-ascent-partners-coso-mcp": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@simonmak-ascent/coso-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-ascent-partners-coso-mcp -t stdio -c npx -a -y @simonmak-ascent/coso-mcp
```

### Other

```json
{
  "mcpServers": {
    "com-ascent-partners-coso-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@simonmak-ascent/coso-mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-15 (score 68, +28)

- [security improvement] Injection markers: unverified → pass
- [security] First check of Judged manipulation: pass
- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] Schema quality: unverified → 100
- [functional improvement] MCP protocol: unverified → pass
- [functional] First check of Schema quality: pass
- [functional] First check of Tool coverage: 100
- [functional] First check of Schema quality: fail
- [functional] First check of Schema quality: fair
- [functional] First check of Tool coverage: 8
- [functional] First check of Destructive annotations: pass

### 2026-10-14 (score 40)

First indexed and scored.

## MCP tools (39)

### `get_server_info` (~26 tokens)

Return the server identity, the COSO framework it covers, and the mandatory disclaimer.

Output parameters:

- `description` (string)
- `disclaimer` (string)
- `framework` (string)
- `name` (string)
- `title` (string)
- `version` (string)

### `list_components` (~28 tokens)

List COSO components

List the five components of the COSO Internal Control—Integrated Framework (ICIF-2013).

Output parameters:

- `components` (array)
- `count` (number)
- `framework` (string)

### `list_principles` (~46 tokens)

List COSO principles

List the 17 principles of the COSO ICIF-2013, optionally filtered to a single component.

Input parameters:

- `component` (string): Restrict to a single component id.

Output parameters:

- `count` (number)
- `framework` (string)
- `principles` (array)

### `get_principle` (~45 tokens)

Get a COSO principle

Return a single COSO principle by framework number or slug, including its paraphrased points of focus.

Input parameters:

- `id` (string)
- `number` (integer)

Output parameters:

- `found` (boolean)
- `principle`

### `get_component` (~28 tokens)

Get a COSO component

Return a single COSO component by id, with its principles.

Input parameters:

- `id` (string, required)

Output parameters:

- `component`
- `found` (boolean)

### `list_objective_categories` (~24 tokens)

List COSO objective categories

List the three COSO objective categories (operations, reporting, compliance).

Output parameters:

- `count` (number)
- `objectiveCategories` (array)

### `list_assertions` (~37 tokens)

List audit assertions (CEAVOP)

List the assertions used to frame control objectives: completeness, existence/occurrence, accuracy, valuation, obligations/rights, presentation/disclosure.

Output parameters:

- `assertions` (array)
- `count` (number)

### `create_engagement` (~90 tokens)

Create an engagement

Create a new internal-control review engagement. Returns the engagement id used by all later tools.

Input parameters:

- `entity` (string, required): Entity or business unit under review.
- `id` (string): Optional explicit engagement id.
- `materiality` (object)
- `period` (string): Review period, e.g. 2025 or 2025-H2.
- `title` (string, required): Engagement title.

Output parameters:

- `engagement` (object)

### `get_engagement` (~22 tokens)

Get an engagement

Return an engagement by id.

Input parameters:

- `id` (string, required)

Output parameters:

- `engagement`
- `found` (boolean)

### `list_engagements` (~17 tokens)

List engagements

List all engagement ids and titles.

Output parameters:

- `count` (number)
- `engagements` (array)

### `add_scope_item` (~75 tokens)

Add a scope item

Add a significant account/process to the review scope, with its objective category and assertions.

Input parameters:

- `area` (string, required): Significant account or process.
- `assertions` (array)
- `engagementId` (string, required)
- `inScope` (boolean)
- `objectiveCategory` (string, required)
- `rationale` (string)

Output parameters:

- `scopeItem`

### `list_scope_items` (~25 tokens)

List scope items

List the scope items for an engagement.

Input parameters:

- `engagementId` (string, required)

Output parameters:

- `count` (number)
- `scopeItems` (array)

### `register_risk` (~95 tokens)

Register a risk

Register a risk to objectives, with likelihood, assertions, related COSO principles and a fraud flag.

Input parameters:

- `assertions` (array)
- `cause` (string)
- `description` (string, required)
- `engagementId` (string, required)
- `fraud` (boolean)
- `impact` (string)
- `likelihood` (string)
- `principles` (array)
- `scopeItemId` (string)

Output parameters:

- `risk`

### `list_risks` (~26 tokens)

List risks

List the risks registered for an engagement.

Input parameters:

- `engagementId` (string, required)

Output parameters:

- `count` (number)
- `risks` (array)

### `register_control` (~101 tokens)

Register a control

Register a key control with its type, frequency, linked risks, assertions and COSO principles.

Input parameters:

- `assertions` (array)
- `description` (string, required)
- `engagementId` (string, required)
- `frequency` (string, required)
- `key` (boolean)
- `owner` (string)
- `principles` (array)
- `riskIds` (array)
- `scopeItemId` (string)
- `type` (string, required)

Output parameters:

- `control`

### `list_controls` (~24 tokens)

List controls

List the controls registered for an engagement.

Input parameters:

- `engagementId` (string, required)

Output parameters:

- `controls` (array)
- `count` (number)

### `get_audit_log` (~29 tokens)

Get the audit log

Return the append-only audit events recorded for an engagement.

Input parameters:

- `engagementId` (string, required)

Output parameters:

- `count` (number)
- `events` (array)

### `compute_sample_size` (~70 tokens)

Compute a sample size

Recommend a sample size for a control from its frequency, risk and population size, with a documented rationale.

Input parameters:

- `externalReliance` (boolean)
- `frequency` (string, required)
- `populationSize` (integer)
- `priorDeficiency` (boolean)
- `risk` (string)

Output parameters:

- `capped` (boolean)
- `effectiveRisk` (string)
- `frequency` (string)
- `populationSize` (number)
- `rationale` (string)
- `recommended` (number)
- `requestedRisk` (string)

### `create_population` (~85 tokens)

Create a population

Register the population for a control — either an explicit item list or a declared size. Bounded to 10000 items.

Input parameters:

- `controlId` (string)
- `currency` (string)
- `declaredSize` (integer)
- `description` (string, required)
- `engagementId` (string, required)
- `items` (array)
- `period` (string)

Output parameters:

- `population`

### `list_populations` (~25 tokens)

List populations

List the populations registered for an engagement.

Input parameters:

- `engagementId` (string, required)

Output parameters:

- `count` (number)
- `populations` (array)

### `select_sample` (~106 tokens)

Select a sample

Select a reproducible sample from a population. Seeded (deterministic) for random/systematic/haphazard; targeted takes explicit references. Records the method, seed and references.

Input parameters:

- `controlId` (string)
- `engagementId` (string, required)
- `method` (string, required)
- `populationId` (string, required)
- `rationale` (string)
- `sampleSize` (integer)
- `seed` (integer)
- `targetedReferences` (array)

Output parameters:

- `sample`

### `record_test_result` (~104 tokens)

Record a test result

Record attribute-level outcomes (pass/fail/na) for a tested sample, with an optional conclusion.

Input parameters:

- `attribute` (string, required): The control attribute/objective tested.
- `conclusion` (string)
- `controlId` (string, required)
- `engagementId` (string, required)
- `populationId` (string)
- `preparedBy` (string)
- `procedure` (string)
- `results` (array, required)
- `sampleId` (string, required)

Output parameters:

- `testResult`

### `list_test_results` (~26 tokens)

List test results

List the test results recorded for an engagement.

Input parameters:

- `engagementId` (string, required)

Output parameters:

- `count` (number)
- `testResults` (array)

### `note_exception` (~89 tokens)

Note an exception

Record an exception identified during testing, with root cause, impact and any compensating control.

Input parameters:

- `compensatingControl` (string)
- `description` (string, required)
- `engagementId` (string, required)
- `impact` (string)
- `reference` (string, required): The sample item reference the exception relates to.
- `rootCause` (string)
- `testResultId` (string, required)

Output parameters:

- `exception`

### `list_exceptions` (~25 tokens)

List exceptions

List the exceptions recorded for an engagement.

Input parameters:

- `engagementId` (string, required)

Output parameters:

- `count` (number)
- `exceptions` (array)

### `assemble_workpaper` (~71 tokens)

Assemble a workpaper

Assemble a Markdown control-testing workpaper from the control, its risks, population, sample, test results and exceptions.

Input parameters:

- `controlId` (string, required)
- `engagementId` (string, required)
- `testResultId` (string): Restrict to a single test result.
- `title` (string)

Output parameters:

- `workpaper`

### `list_workpapers` (~26 tokens)

List workpapers

List the workpapers assembled for an engagement.

Input parameters:

- `engagementId` (string, required)

Output parameters:

- `count` (number)
- `workpapers` (array)

### `get_workpaper` (~35 tokens)

Get a workpaper

Return a workpaper including its rendered Markdown.

Input parameters:

- `engagementId` (string, required)
- `workpaperId` (string, required)

Output parameters:

- `found` (boolean)
- `workpaper`

### `add_review_note` (~49 tokens)

Add a review note

Add a reviewer note to a workpaper.

Input parameters:

- `author` (string)
- `engagementId` (string, required)
- `text` (string, required)
- `workpaperId` (string, required)

Output parameters:

- `note`
- `workpaper`

### `resolve_review_note` (~52 tokens)

Resolve a review note

Mark a review note resolved on a workpaper.

Input parameters:

- `engagementId` (string, required)
- `noteId` (string, required)
- `resolvedBy` (string)
- `workpaperId` (string, required)

Output parameters:

- `note`
- `workpaper`

### `sign_off` (~70 tokens)

Sign off a workpaper

Record a preparer or reviewer sign-off. Warns (does not block) if the same person prepared and reviewed.

Input parameters:

- `actor` (string)
- `comment` (string)
- `engagementId` (string, required)
- `role` (string, required)
- `workpaperId` (string, required)

Output parameters:

- `warning` (string)
- `workpaper`

### `get_activity_log` (~32 tokens)

Get the activity log

Return the append-only activity log for an engagement, plus a Markdown rendering.

Input parameters:

- `engagementId` (string, required)

Output parameters:

- `count` (number)
- `events` (array)
- `markdown` (string)

### `classify_deficiency` (~119 tokens)

Classify a deficiency

Classify a control deficiency as deficiency / significant deficiency / material weakness from likelihood × magnitude (escalates for a pervasive control).

Input parameters:

- `compensatingControl` (string)
- `controlId` (string)
- `description` (string, required)
- `engagementId` (string, required)
- `exceptionIds` (array)
- `likelihood` (string, required)
- `magnitude` (string, required)
- `pervasive` (boolean)
- `remediation` (object)
- `testResultId` (string)
- `title` (string, required)

Output parameters:

- `deficiency`

### `list_deficiencies` (~25 tokens)

List deficiencies

List the deficiencies recorded for an engagement.

Input parameters:

- `engagementId` (string, required)

Output parameters:

- `count` (number)
- `deficiencies` (array)

### `aggregate_deficiencies` (~43 tokens)

Aggregate deficiencies

Group related deficiencies by control, flag combinations that may aggregate, and report the overall severity.

Input parameters:

- `deficiencyIds` (array)
- `engagementId` (string, required)

Output parameters:

- `aggregation`

### `assess_principle` (~45 tokens)

Assess a COSO principle (indicators)

Report data-driven coverage indicators for one COSO principle (controls, risks and deficiencies mapped to it).

Input parameters:

- `engagementId` (string, required)
- `number` (integer, required)

Output parameters:

- `assessment`
- `found` (boolean)

### `assess_component` (~37 tokens)

Assess a COSO component (indicators)

Report coverage indicators for one COSO component, aggregating its principles.

Input parameters:

- `engagementId` (string, required)
- `id` (string, required)

Output parameters:

- `assessment`
- `found` (boolean)

### `framework_integration_check` (~35 tokens)

Framework integration check

Check that all five COSO components have some recorded coverage and that principles are addressed.

Input parameters:

- `engagementId` (string, required)

Output parameters:

- `components` (array)
- `integration`

### `generate_report` (~41 tokens)

Generate the review report

Generate a Markdown internal-control review report: scope, risks, controls, testing, workpapers, deficiencies and COSO coverage.

Input parameters:

- `engagementId` (string, required)

Output parameters:

- `counts`
- `markdown` (string)

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/com-ascent-partners-coso-mcp/simonmak-ascent-coso-mcp#diagnostics

## Score history

- 2026-10-17: 68
- 2026-10-16: 68
- 2026-10-15: 68
- 2026-10-14: 40

## Common questions

### What is the com.ascent-partners/coso-mcp server?

com.ascent-partners/coso-mcp is listed in the public MCP registry as com.ascent-partners/coso-mcp. Open COSO internal-control review MCP: scope, risk, controls, sampling, testing, workpapers. This page covers its npm package (@simonmak-ascent/coso-mcp).

### Is the com.ascent-partners/coso-mcp server safe to use?

com.ascent-partners/coso-mcp scores 68 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 17 October 2026. It declares no install or post-install scripts. 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 com.ascent-partners/coso-mcp server expose?

com.ascent-partners/coso-mcp exposes 39 tools: get_server_info, list_components, list_principles, get_principle, get_component, and 34 more. Their descriptions and schemas cost roughly 1,948 tokens of context every time the server is loaded.

### Is the com.ascent-partners/coso-mcp server still maintained?

com.ascent-partners/coso-mcp is still listed as active in the MCP registry. We last reached this channel on 17 October 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 com.ascent-partners/coso-mcp server under?

com.ascent-partners/coso-mcp declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- npm package: https://www.npmjs.com/package/@simonmak-ascent/coso-mcp
- Socket report: https://socket.dev/npm/package/@simonmak-ascent/coso-mcp
- Repository: https://github.com/simonmak-ascent/coso-mcp
- Changelog RSS feed: https://verifymcp.io/servers/com-ascent-partners-coso-mcp/simonmak-ascent-coso-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-ascent-partners-coso-mcp/simonmak-ascent-coso-mcp.json
- HTML version of this page: https://verifymcp.io/servers/com-ascent-partners-coso-mcp/simonmak-ascent-coso-mcp