
Ascent Partners MCP server
Which MCP servers are Ascent Partners's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-18
- Registry namecom.ascent-partners/coso-mcpverified in the MCP registry
The registry name sits under ascent-partners.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-18
- Tools39
- Server calls itself@simonmak-ascent/coso-mcp
- Server version0.1.1
- Protocol version2025-06-18
On 2026-10-18 the server answered initialize and tools/list without a sign-in. First answer in 637 ms.
- Answered on only 3 of 15 daily checks.
- Its tools do none of the product's use cases we checked: Value businesses, financial instruments and intangible assets; Automate processes and price derivatives with FinCAD analytics.
Once connected
- create_engagement, add_scope_item, create_population, add_review_note change data without a sign-in: anyone with the address can call them.
- Parameters are untyped or undescribed in 33 of 39 tools: check arguments before calling.
Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.
- INITE MCP score34 of 100answers 20 · does the job 0 · definitions 69 · context 87 · use 55 · connects 100 · lowered by the warning signs below
- What an agent can do with it0 of 2 use cases
- Use270 npm downloads a week260 PyPI downloads a week · 1 GitHub stars
- Answered20% of days3 of 15 daily checks
- Median first answer799 ms
- Space in an agent's context≈ 4,919 tokensthe definitions of all its tools (39), which an agent carries on every turn
- Tool definitionsC · 69 of 100
- Typed results39 of 39 toolsdeclared outputSchema: results come typed, read once
- Parameters without a description: in 33 of 39
- Not saying whether it only reads or can destroy: 39 of 39
What an agent can do with it
- cannot · Value businesses, financial instruments and intangible assets
- not sure · Run enterprise risk, internal audit and compliance programmes
- cannot · Automate processes and price derivatives with FinCAD analytics
Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?
Worth a look
- Tools that change data, on a server that answers without a sign-in: create_engagement, add_scope_item, create_population, add_review_note
A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →
get_server_infoReturn the server identity, the COSO framework it covers, and the mandatory disclaimer.
list_componentsList the five components of the COSO Internal Control—Integrated Framework (ICIF-2013).
list_principlesList the 17 principles of the COSO ICIF-2013, optionally filtered to a single component.
get_principleReturn a single COSO principle by framework number or slug, including its paraphrased points of focus.
get_componentReturn a single COSO component by id, with its principles.
list_objective_categoriesList the three COSO objective categories (operations, reporting, compliance).
list_assertionsList the assertions used to frame control objectives: completeness, existence/occurrence, accuracy, valuation, obligations/rights, presentation/disclosure.
create_engagementCreate a new internal-control review engagement. Returns the engagement id used by all later tools.
get_engagementReturn an engagement by id.
list_engagementsList all engagement ids and titles.
add_scope_itemAdd a significant account/process to the review scope, with its objective category and assertions.
list_scope_itemsList the scope items for an engagement.
register_riskRegister a risk to objectives, with likelihood, assertions, related COSO principles and a fraud flag.
list_risksList the risks registered for an engagement.
register_controlRegister a key control with its type, frequency, linked risks, assertions and COSO principles.
list_controlsList the controls registered for an engagement.
get_audit_logReturn the append-only audit events recorded for an engagement.
compute_sample_sizeRecommend a sample size for a control from its frequency, risk and population size, with a documented rationale.
create_populationRegister the population for a control — either an explicit item list or a declared size. Bounded to 10000 items.
list_populationsList the populations registered for an engagement.
select_sampleSelect a reproducible sample from a population. Seeded (deterministic) for random/systematic/haphazard; targeted takes explicit references. Records the method, seed and references.
record_test_resultRecord attribute-level outcomes (pass/fail/na) for a tested sample, with an optional conclusion.
list_test_resultsList the test results recorded for an engagement.
note_exceptionRecord an exception identified during testing, with root cause, impact and any compensating control.
list_exceptionsList the exceptions recorded for an engagement.
assemble_workpaperAssemble a Markdown control-testing workpaper from the control, its risks, population, sample, test results and exceptions.
list_workpapersList the workpapers assembled for an engagement.
get_workpaperReturn a workpaper including its rendered Markdown.
add_review_noteAdd a reviewer note to a workpaper.
resolve_review_noteMark a review note resolved on a workpaper.
sign_offRecord a preparer or reviewer sign-off. Warns (does not block) if the same person prepared and reviewed.
get_activity_logReturn the append-only activity log for an engagement, plus a Markdown rendering.
classify_deficiencyClassify a control deficiency as deficiency / significant deficiency / material weakness from likelihood × magnitude (escalates for a pervasive control).
list_deficienciesList the deficiencies recorded for an engagement.
aggregate_deficienciesGroup related deficiencies by control, flag combinations that may aggregate, and report the overall severity.
assess_principleReport data-driven coverage indicators for one COSO principle (controls, risks and deficiencies mapped to it).
assess_componentReport coverage indicators for one COSO component, aggregating its principles.
framework_integration_checkCheck that all five COSO components have some recorded coverage and that principles are addressed.
generate_reportGenerate a Markdown internal-control review report: scope, risks, controls, testing, workpapers, deficiencies and COSO coverage.
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"coso-mcp": {
"type": "http",
"url": "https://internal-control.ascent-partners.com/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http ascent-partners https://internal-control.ascent-partners.com/mcpclaude.ai, ChatGPT and other clients: add https://internal-control.ascent-partners.com/mcp as a custom connector in the settings.
Also shipped through: npm
- com.ascent-partners/esg-hubanswers, 12 toolsverified in the MCP registry
- com.ascent-partners/fair-valueanswers, 14 toolsverified in the MCP registry
- com.ascent-partners/hkex-filingsnot asked yetverified in the MCP registry
- com.ascent-partners/intangible-valuationnot asked yetverified in the MCP registry
- com.ascent-partners/opencode-workbenchnot asked yetverified in the MCP registry
- com.ascent-partners/startup-valuationnot asked yetverified in the MCP registry
- com.ascent-partners/vision-driven-designnot asked yetverified in the MCP registry
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.
Cookies
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.