Capability reference

MCP Documentation

What jobs are you doing?

Each job names the capability that does it and what you get back. Open a job for its steps, and select any step to read its contract in Reference.

16 tools·133 resources·12 prompts

Screen an unfamiliar targetA one-page brief, with every norm-derived figure declared.3 steps
Shape a technology diligence before the LOIA starter agenda with attention areas, ready for the wizard.2 steps

Thirteen dimensions in, a prioritised agenda out. Supply only the target name and the agenda widens conservatively rather than guessing.

Create an information request list for a companyA configured workbook to send, plus the Hub page to download it from.3 steps
Populate a request list from available informationA populated workbook, each answer sourced, the blanks left as the ask.2 steps

The same list answered from what you already hold, a data room export, filings, or an earlier session, so the ask left to the target is only what is genuinely missing.

Extract useful context from an IRLA portable record, self-dated, that a later session can drive the tools from.1 step

One fact per answered row, plus the payloads the analysis tools take, projected without calling any of them.

Drive company assessment from a populated IRLA partner-level dossier, sections (A) to (J), gaps named.3 steps
Benchmark the spendA zone verdict, a maturity score, and the investigation list.2 steps
Review the architectureA per-layer memo plus the risks that cascade between layers.2 steps
Map the regulatory exposureA citation-anchored brief with cross-jurisdictional themes.4 steps
Find comparable engagementsThree to five comparables, each with its lesson and a deeplink.3 steps
Check the newsA briefing you can take into the morning call.3 steps
Handover an assessmentA handoff memo, not a stitched-together set of results.2 steps

Agenda, comparables and VDR follow-ups combined into one document the deal team can act on without reading the tool output.

generate_diligence_agenda

Tool

Turns a target profile into a prescriptive diligence agenda: the topics to cover, the questions to ask under each, and the attention areas the profile makes material.

Arguments

click a value to copy it
NameExampleRequirement
transactionTypeenum. full-acquisition · majority-stake · business-integration · carve-out · venture-series.
productTypeenum. b2b-saas · b2c-marketplace · on-premise-enterprise · deep-tech-ip · tech-enabled-service.
techArchetypeenum. modern-cloud-native · hybrid-legacy · self-managed-infra · datacenter-vendor. The largest single driver of which questions surface.
headcountordinal enum. Company size band. Questions can gate on a minimum band rather than an exact match.
revenueRangeordinal enum. Revenue band, gated the same way.
growthStageenum. Where the company sits in its funding and growth arc.
companyAgeordinal enum. Age band, gated the same way.
geographiesenum array. The only multi-select input. Two or more specific regions auto-adds multi-region.
businessModelenum. How the target earns.
scaleIntensityenum. Load and growth pressure on the platform.
transformationStateenum. How much change the estate is already carrying.
dataSensitivityenum. Drives the privacy and security question set.
operatingModelenum. How engineering and operations are organized.

All thirteen dimensions are required: the engine has no defaults, and a missing field is rejected before it runs. Each accepts a fixed identifier set; call the tool with an invalid value and the error names the valid ones.

Example

complete and valid as written
generate_diligence_agenda({
  "transactionType": "full-acquisition",
  "productType": "b2b-saas",
  "techArchetype": "modern-cloud-native",
  "headcount": "51-200",
  "revenueRange": "5-25m",
  "growthStage": "scaling",
  "companyAge": "5-10yr",
  "geographies": ["eu"],
  "businessModel": "productized-platform",
  "scaleIntensity": "moderate",
  "transformationState": "stable",
  "dataSensitivity": "high",
  "operatingModel": "product-aligned-teams"
})

Returns

  • A prioritized agenda: topics, and per topic the questions the profile makes worth asking.
  • Attention areas, the themes this particular combination of dimensions puts at risk.
  • deeplink. Opens the Diligence Machine wizard populated with the same thirteen answers.

Availability

Included in all tiers. Rate ceilings are per-client capability limits, not contractual quotas.

Related

Used in jobs

search_portfolio

Tool

Searches GST's anonymized engagement record by free text, theme, and engagement side, so a current deal can be framed against work already done.

Arguments

click a value to copy it
NameExampleRequirement
searchstring, optional. Free text matched against code name, industry, summary, and technologies. Substring match, not fuzzy.
themestring, optional. One of the values list_portfolio_facets returns, or "all". Defaults to "all".
engagementstring, optional. Buy-Side · Sell-Side · all. Defaults to "all".

The empty call returns every engagement. There is no limit argument: the tool mirrors the website filter surface exactly, and the website renders the full set.

Example

complete and valid as written
search_portfolio({
  "search": "healthcare",
  "theme": "Healthcare",
  "engagement": "Buy-Side"
})

Returns

  • matches. The engagements passing all three filters, each with its summary, challenge, and solution.
  • totalMatched and returned.
  • deeplink. Opens the M&A portfolio filtered the same way.

Availability

Included in all tiers. Rate ceilings are per-client capability limits, not contractual quotas.

Related

Used in jobs

list_portfolio_facets

Tool

Lists the values the portfolio filters accept. Call it before search_portfolio rather than guessing a theme name.

Arguments

Takes no arguments.

Example

complete and valid as written
list_portfolio_facets({})

Returns

  • themes and engagementCategories. The two filterable dimensions.
  • growthStages and years. Not filterable today, exposed for orientation.

Availability

Included in all tiers. Rate ceilings are per-client capability limits, not contractual quotas.

Related

Used in jobs

search_regulations

Tool

Queries 123 regulatory frameworks by jurisdiction, category, and free text. The curated corpus carries current effective dates, scope language, key requirements, and statutory penalty bands.

Arguments

click a value to copy it
NameExampleRequirement
jurisdictionstring or string array, optional. Lowercase codes: "eu", "us", "us-ca", "ca-qc". An array combines matches in one call.
categorystring or string array, optional. data-privacy · ai-governance · cybersecurity · industry-compliance.
querystring, optional. Matches name, curated aliases, summary, and id. Common short forms resolve to the statute they name.
limitnumber, optional. Default 20, maximum 120.

Keep limit at or near its default and narrow by category. Broad multi-jurisdiction queries return very large responses, and raising the limit is how a result outgrows a client rather than how it gets more useful. When an array holds more than one value, the response omits that filter from its deeplink, because the website uses single-select chips.

Example

complete and valid as written
search_regulations({
  "jurisdiction": "eu",
  "category": "ai-governance"
})

Returns

  • Framework records: name, jurisdiction, category, effective date, key requirements, penalties. The corpus carries no article numbers.
  • Each match resolves its Regulatory Map resource URI, so the full document can be read next.
  • deeplink. Opens the Regulatory Map filtered to the same region and category.

Availability

Included in all tiers. Rate ceilings are per-client capability limits, not contractual quotas.

Related

Used in jobs

list_regulation_facets

Tool

Lists the jurisdictions and categories the regulatory corpus actually indexes, plus the total framework count. The recovery call when a jurisdiction code does not resolve.

Arguments

Takes no arguments.

Example

complete and valid as written
list_regulation_facets({})

Returns

  • jurisdictions and categories. Every value search_regulations will accept.
  • totalFrameworks. The size of the indexed corpus.

Availability

Included in all tiers. Rate ceilings are per-client capability limits, not contractual quotas.

Related

Used in jobs

assess_infrastructure_cost_governance

Tool

Scores cloud cost governance maturity across six domains and returns a prioritized improvement list. Wraps the engine behind the Hub wizard.

Arguments

click a value to copy it
NameExampleRequirement
answersmap of question id to a score. Keys take the form q1_1, q1_2 … q6_N across the six domains.
companyStageenum, optional. Canonical funding stage (seed · series-a · series-b · series-c · pe · enterprise) or one of the four native bands. Adds a benchmark band; never changes the score.

The scale is 0 Not in place · 1 Ad hoc · 2 Established · 3 Optimized, with -1 meaning Not sure. The map is sparse: missing questions count as zero, so a partial assessment reports an honest absence of information rather than failing. Only an explicit -1 is reported as skipped.

Example

complete and valid as written
assess_infrastructure_cost_governance({
  "answers": {}
})

Returns

  • overallScore and maturityLevel. Reactive · Aware · Optimizing · Strategic.
  • domainScores. One per domain, with the raw and normalized score.
  • showFoundationalFlag. Set when visibility or attribution scores low, independent of the overall score.
  • recommendations. Sorted by impact, then effort, then domain.
  • answeredCount, totalQuestions, skippedCount. How much of the assessment was actually answered.
  • deeplink. Opens the wizard on the results view with the same answers.

A high overall score can hide a foundational gapTwo of the six domains, visibility and tagging plus account structure and attribution, are foundational: everything else rests on them. If either scores at or below a third, the result raises its foundational flag no matter how strong the overall number looks.

Availability

Included in all tiers. Rate ceilings are per-client capability limits, not contractual quotas.

Related

Used in jobs

compute_techpar

Tool

Benchmarks total technology cost against stage-adjusted ranges and projects a 36-month trajectory. Wraps the TechPar engine behind the Hub wizard.

Arguments

click a value to copy it
NameExampleRequirement
arrnumber > 0. Annual recurring revenue, dollars. Drives every percentage-of-revenue calculation.
stageenum. Canonical funding stage: seed · series-a · series-b · series-c · pe · enterprise. Selects the per-stage benchmark band.
modeenum, no default. quick reads rdOpEx directly; deepdive synthesizes R&D OpEx as engCost + prodCost + toolingCost.
capexViewenum. cash includes rdCapEx in totals; gaap excludes it.
growthRatenumber. Annual revenue growth, as a percentage; drives the 36-month projection.
exitMultiplenumber, zero or more. Translates the cumulative gap to exit value. 12x is the SaaS convention.
infraHostingAnnualnumber, zero or more. Annual infrastructure and hosting cost, dollars. Must be above zero.
infraPersonnelnumber, zero or more. Annual infrastructure personnel cost, dollars.
rdOpExnumber, zero or more. R&D OpEx. Read in quick mode; discarded in deepdive.
rdCapExnumber, zero or more. Capitalized R&D.
engFTEnumber, zero or more. Engineering headcount; yields revenue per engineer.
engCostnumber, zero or more. Annual engineering personnel cost. deepdive only.
prodCostnumber, zero or more. Annual product personnel cost. deepdive only.
toolingCostnumber, zero or more. Annual tooling cost. deepdive only.

All 14 fields are required in both modes; the engine ignores the fields the selected mode does not read. All money fields are annual dollars on one currency basis. A zero arr or infraHostingAnnual returns invalid-input, never a stack trace.

Example

complete and valid as written
compute_techpar({
  "arr": 18400000,
  "stage": "series-b",
  "mode": "quick",
  "capexView": "cash",
  "growthRate": 31,
  "exitMultiple": 12,
  "infraHostingAnnual": 732000,
  "infraPersonnel": 640000,
  "rdOpEx": 4100000,
  "rdCapEx": 450000,
  "engFTE": 84,
  "engCost": 0,
  "prodCost": 0,
  "toolingCost": 0
})

Returns

  • total, totalCash, totalGAAP, totalTechPct. Annual technology cost and its share of revenue.
  • zone. underinvest · ahead · healthy · above · elevated · critical, against the stage benchmark band.
  • categories and kpis. Per-category breakdown plus unit-economics KPIs including revenue per engineer.
  • gap. cumulative36, exitValue, underinvestGap. The 36-month projection.
  • deeplink. Opens the TechPar wizard populated with the same inputs.

Availability

Included in all tiers. Rate ceilings are per-client capability limits, not contractual quotas.

Related

Used in jobs

estimate_tech_debt_cost

Tool

Estimates the annual carrying cost of accumulated technical debt from team size, salary, maintenance burden, and delivery cadence.

Arguments

click a value to copy it
NameExampleRequirement
teamSizeinteger above zero. Engineering headcount. A direct multiplier on the carrying cost.
salarynumber above zero. Average fully loaded annual engineering salary, dollars.
maintenanceBurdenPctnumber 0 to 100. Share of engineering capacity consumed by maintenance and debt servicing. The headline input.
deployFrequencyenum. Multiple/day · Daily · Weekly · Bi-weekly · Three-week · Monthly · Quarterly+ · Bi-annually · Annually. Sets the DORA tier and the velocity multiplier.
incidentsinteger, zero or more. Production incidents per month.
mttrHoursnumber, zero or more. Mean time to recovery, hours per incident.
remediationBudgetnumber, zero or more. Capital available for debt paydown, dollars.
arrnumber, zero or more. Annual recurring revenue, used to express the cost as a share of revenue.
remediationPctnumber 0 to 100. Expected reduction in debt cost from the remediation.
contextSwitchOnboolean. Whether to model the context-switching overhead surcharge.

These are business values, not wizard slider positions: pass the precision you actually have. An arr of zero is allowed and reports the revenue share as zero rather than dividing by it.

Example

complete and valid as written
estimate_tech_debt_cost({
  "teamSize": 84,
  "salary": 165000,
  "maintenanceBurdenPct": 28,
  "deployFrequency": "Weekly",
  "incidents": 3,
  "mttrHours": 8,
  "remediationBudget": 900000,
  "arr": 18400000,
  "remediationPct": 65,
  "contextSwitchOn": true
})

Returns

  • totalMonthly and annualCost. The carrying cost, and its split across steady-state burden, context switching, and incident time.
  • hoursLostPerEng and costPerEng. The same number expressed per engineer.
  • doraLabel. The DORA tier the deploy cadence lands in, and the multiplier it applied.
  • debtPctArr. Annual cost as a share of revenue, the usual deal-discussion framing.
  • paybackMonths and monthlySavings. What the remediation budget buys back.
  • deeplink. Opens the Tech Debt calculator with the same inputs.

Availability

Included in all tiers. Rate ceilings are per-client capability limits, not contractual quotas.

Related

Used in jobs

generate_information_request_list_xlsx

Tool

Builds the blank information request list as an XLSX workbook, configured for the engagement. This is the ask GST hands a target before diligence tools can run.

Arguments

click a value to copy it
NameExampleRequirement
targetNamestring, optional. The target the list is addressed to.
companyNamestring, optional. Composed into the workbook title.
projectNamestring, optional. Composed into the title alongside companyName.
transactionContextenum, optional. sell-side · buy-side · value-creation · unknown. Fires the authored skip-if directives, removing questions that do not apply.
includeSectionsarray of two-digit section ids, optional. Keeps whole sections. Defaults to all ten.
excludeRequestsarray of NN-II keys, optional. Removes individual questions. Call list_irl_requests to find the keys.
customRequestsarray, optional. Extra questions, each with a section and its text.
showCanonicalReferenceboolean, optional. Whether to print the canonical reference column.

Every field is optional: the empty call produces the full canonical workbook. The three subtractions compose, and surviving questions keep their reference ids, so the gaps read as deliberate rather than as an incomplete list.

Example

complete and valid as written
generate_information_request_list_xlsx({
  "targetName": "Northwind Health",
  "transactionContext": "buy-side",
  "includeSections": ["00", "03"],
  "excludeRequests": ["03-08"]
})

Returns

  • filename and the workbook bytes.
  • sectionCount and bulletCount. What the configuration actually produced.
  • downloadUrl. The Hub generator with this call's arguments pre-filled, which is the surface to hand a person.
  • canonicalUrl. The library article the questions come from.

Availability

Included in all tiers. Rate ceilings are per-client capability limits, not contractual quotas.

Related

Used in jobs

fill_information_request_list_xlsx

Tool

Builds the same workbook already populated from evidence the model holds, writing each answer and the source it rests on into the row. Removes the wait for a third party wherever the information already exists.

Arguments

click a value to copy it
NameExampleRequirement
fillsarray of 1 to 200 entries, each { ref, fileLocation, comments }. All three are required per entry.
refThe workbook Reference value for the row being answered, for example 0-03. Must exist in the configured workbook, and cannot repeat.
fileLocationWhat the answer rests on: a document reference and optional locator, or a bracketed origin note. A reference, never an excerpt.
commentsThe answer itself, as single-line prose. Under the extraction rules an entry here is a real answer, never a placeholder.
targetNamestring, optional. Same scoping arguments as the blank generator, minus productSummary.
transactionContextenum, optional. sell-side · buy-side · value-creation · unknown.

Requiring both a source and an answer on every entry is structural: a row cannot be answered without saying what it rests on. The shape of the reference is checked; whether the referenced document exists is deliberately not, because that is what the human reviewer verifies.

Example

fill_information_request_list_xlsx({
  "targetName": "UAT Eleven Corp",
  "transactionContext": "buy-side",
  "fills": [
    { "ref": "0-01", "fileLocation": "VDR/00/entity-chart.pdf, page 1", "comments": "Delaware C-corp, single operating entity." },
    { "ref": "1-01", "fileLocation": "[inferred from product-overview.pdf + demo session]", "comments": "Single multi-tenant SaaS surface." },
    { "ref": "9-01", "fileLocation": "[User stated this in session chat]", "comments": "Five-member board, two independent seats." }
  ]
})

Returns

  • filename and the workbook bytes, identical in behavior to a target-returned file.
  • filledRowCount and filledRefs. The operator review checklist.
  • blankRowCount. What remains to ask for, which is the follow-up list.

Blank rows are the askRows the evidence cannot support stay empty on purpose. Filling them from inference would produce a workbook that looks complete and is not, so the unanswered rows are what goes back to the target.

Availability

Included in all tiers. Rate ceilings are per-client capability limits, not contractual quotas.

Related

Used in jobs

list_irl_requests

Tool

Returns the canonical question set behind the information request list, with the key for each question. The only way to map "drop that question" onto the key the generator accepts.

Arguments

Takes no arguments.

Example

complete and valid as written
list_irl_requests({})

Returns

  • requests. Each with its NN-II key, section, section title, question text, and any engagement contexts that auto-remove it.
  • sectionCount and bulletCount.

Availability

Included in all tiers. Rate ceilings are per-client capability limits, not contractual quotas.

Related

Used in jobs

prepare_irl_body

Tool

Registers a completed information request list with the server and returns a short hash for it. Everything downstream in the dossier pipeline refers to the document by that hash instead of resending it.

Arguments

NameRequirement
filledIrlstring, required. The populated list, entire markdown body, at least 200 characters.

The hash is computed byte for byte with no normalization, so the same body always produces the same hash. Do not hand-compute it: the downstream tools accept only the value this call returns.

Example

prepare_irl_body({ "filledIrl": "<the populated body, verbatim>" })

Returns

  • irlBodyHash. The reference every later call uses.
  • byteLength. What the server actually received.
  • mintedAt. When the server first saw this body, which is what lets a later record say the timestamp was witnessed rather than asserted.

Availability

Included in all tiers. Rate ceilings are per-client capability limits, not contractual quotas.

Related

validate_irl_provenance

Tool

Checks every claim in a draft back to the request list it cites, and reports which citations actually hold. Run it to see the verdicts before they are written into a deliverable.

Arguments

NameRequirement
citationsarray, required. Each entry pairs the claim path with the citation supporting it. A citation may be one string or up to eight.
irlBodyHashstring. The hash from prepare_irl_body.
filledIrlstring. The body itself, as an alternative to the hash.

One of irlBodyHash or filledIrl must be supplied; the body wins when both are. Prefer the hash: passing the body re-sends the whole document on every call. Where a claim is genuinely synthesized from several bullets, the array form checks each and aggregates conservatively, so one unverified element makes the whole citation unverified.

Example

validate_irl_provenance({
  "irlBodyHash": "<the hash prepare_irl_body returned>",
  "citations": [
    { "path": "financials.arr", "citation": "0-03 Annual recurring revenue" }
  ]
})

Returns

  • verified. The cited text is present in the list.
  • verified-fuzzy. Not verbatim, but a long enough run of words matches to tolerate light paraphrase.
  • partner-supplied. Cited to the partner directly, with no list text to check against.
  • unverified. Neither. Treat it as fabricated: pull the claim or re-cite it.

Availability

Included in all tiers. Rate ceilings are per-client capability limits, not contractual quotas.

Related

Used in jobs

compose_dossier_envelope

Tool

The terminus of the dossier pipeline: takes the run's claims, gaps, and tool outcomes and returns the audit sections the finished dossier carries. Driven by the ingestion prompt rather than called by hand.

Arguments

click a value to copy it
NameExampleRequirement
irlBodyHashstring, required. From prepare_irl_body. The sole reference to the document.
claimsarray, required. Every load-bearing claim the dossier will make, each with its citation and tier.
gapsarray. What the run could not answer, categorized. May be empty.
fillRatioobject. How much of the list came back answered, and whether that is enough to proceed.
gatesPassed / gatesElidedarrays. Which tools ran, and which were skipped with the reason and the section that would have fed them.
modeenum. full · extract-only.
auditLevelenum. standard · enhanced · debug. Selects which audit blocks come back.

The array fields are required but may be empty; omitting one is an error, passing an empty array is not. This is the most common first-call mistake. The call fails outright if prepare_irl_body has not registered the body first, and the fix is always to register it again rather than retrying.

Example

compose_dossier_envelope({
  "irlBodyHash": "<the hash prepare_irl_body returned>",
  "mode": "full",
  "auditLevel": "debug",
  "fillRatio": { "percent": 24, "substantiveCells": 16, "totalCells": 67, "status": "partial" },
  "claims": [{ "claim": "ARR is 18.4m", "citation": "0-03 Annual recurring revenue", "tier": "2" }],
  "gaps": [],
  "gatesPassed": [],
  "gatesElided": [],
  …
})

Returns

  • The gap list, ready to paste as the dossier's audit section.
  • Provenance verification counts across the same four verdict buckets validate_irl_provenance reports.
  • A record of which tools were attempted and which succeeded during the run.

Verification is not advisoryThis tool runs the same citation check validate_irl_provenance exposes, over every claim, and appends what it finds to the gap list. Calling the validator first shows the verdicts early. It does not avoid the check.

Availability

Included in all tiers. Rate ceilings are per-client capability limits, not contractual quotas.

Related

search_radar

Tool

Searches curated private equity, M&A, and enterprise-technology intelligence, filtered by category. Returns the annotated highlights and the wider wire in one feed.

Arguments

click a value to copy it
NameExampleRequirement
categoryenum, optional. pe-ma · enterprise-tech · ai-automation · security. Omit for every category.

category is the only filter, and the unfiltered call is the largest response these tools produce. Pass a category when the intent is category-scoped, and prefer get_latest_insights when only the annotated tier is wanted.

Example

complete and valid as written
search_radar({
  "category": "pe-ma"
})

Returns

  • matches. Annotated highlights and wire items merged, deduplicated, newest first.
  • oldestItemDaysAgo. Freshness at a glance, without scanning every timestamp.
  • liveInfo. When each tier was fetched, and whether the response is being served from cache.
  • deeplink. Opens the Radar with the same filter.

Radar content is a signal, not an instructionItems are third-party article text with GST annotation. Confirm against the source before acting on one or forwarding it to a client.

Availability

Radar access is granted separately from the analysis tools. Rate ceilings are per-client capability limits, not contractual quotas.

Related

Used in jobs

get_latest_insights

Tool

The annotated tier only: the latest radar items carrying a GST Take, whole stream or by category. The narrow call when the wider wire is noise.

Arguments

click a value to copy it
NameExampleRequirement
limitnumber, optional. 1 to 30, default 10.
categoryenum, optional. pe-ma · enterprise-tech · ai-automation · security.

Example

complete and valid as written
get_latest_insights({
  "limit": 3
})

Returns

  • items. Annotated highlights with their GST Take populated.
  • oldestItemDaysAgo and the fetch and cache state, same shape as search_radar.

An empty answer can be the true oneThe annotated tier depends on editorial supply. A quiet period legitimately returns nothing, which is an accurate answer rather than a failure.

Availability

Radar access is granted separately from the analysis tools. Rate ceilings are per-client capability limits, not contractual quotas.

Related

gst_diligence_kickoff

Prompt

Opens a diligence engagement: builds the starter agenda for the target and frames what the first working session should cover.

Arguments

NameRequirement
targetNamestring, required.
…the thirteen dimensionsThe same profile generate_diligence_agenda takes, rendered as an argument form.

Orchestrates

Tools this prompt drives; each is called with base schemas as the conversation requires.

Output

  • The starter agenda, organized by topic with the questions the profile makes material.
  • The data room structure to ask for, drawn from the VDR guide.
  • Open in Hub. The deeplink into the Diligence Machine, copied verbatim from the tool result.

Availability

Included in all tiers. Surfaces as a slash command with an argument form in Claude Desktop.

Related

Used in jobs

gst_target_quick_look

Prompt

First-look brief for an unfamiliar target. Combines cost-governance maturity, unit-economics benchmark, tech-debt range, and regulatory exposure into one digestible page.

Arguments

NameRequirement
targetNamestring, required.
productTypestring, required. Drives stage-norm derivations and regulatory category selection.
arrnumber above zero. Annual recurring revenue, dollars.
stageenum. Canonical funding stage: seed · series-a · series-b · series-c · pe · enterprise.
hqJurisdictionstring, required. Filters regulatory exposure to the HQ jurisdiction.

Orchestrates

Tools this prompt drives; each is called with base schemas as the conversation requires.

Output

  • Header. Target, product type, ARR, stage, HQ jurisdiction.
  • Cost-governance read. Overall score, maturity level, top recommendations.
  • Unit economics. TechPar zone with the mode it ran and one line on why.
  • Tech-debt range. Annual cost, payback, DORA tier; extraction-only fields named plainly.
  • Assumptions and unknowns. One consolidated list of every value supplied from stage norms rather than evidence.
  • Regulatory exposure. Applicable frameworks for the HQ jurisdiction.
  • Open in Hub. Deeplinks into all four wizards, copied verbatim from tool results.

Two branchesWith a GST extract record in context the brief resolves real figures from evidence; with the five arguments alone it derives conservative stage norms and discloses every derivation. A form-derived figure and an evidence-backed one never read alike.

Availability

Included in all tiers. Surfaces as a slash command with an argument form in Claude Desktop.

Related

Used in jobs

gst_diligence_handoff_memo

Prompt

Produces the memo a deal team hands onward: the agenda, the comparable engagements, and the data room follow-ups in one document.

Arguments

NameRequirement
targetNamestring, required.
…the thirteen dimensionsThe target profile, as in the kickoff prompt.
agendaJsonstring, optional. A pre-generated agenda. Absent, the prompt generates one.
comparablesJsonstring, optional. Pre-generated comparables. Absent, the prompt searches for them.

The two optional arguments exist so a memo can be built from work already done in the session rather than re-running it.

Orchestrates

Tools this prompt drives; each is called with base schemas as the conversation requires.

Output

  • The agenda, condensed to what the receiving team needs to act on.
  • Comparable GST engagements and what they imply for this deal.
  • Data room follow-ups still outstanding.

Availability

Included in all tiers. Surfaces as a slash command with an argument form in Claude Desktop.

Related

Used in jobs

gst_comparable_engagements_memo

Prompt

Frames a target against three to five comparable past GST engagements, drawn from the anonymized record and read analogically rather than as a list.

Arguments

NameRequirement
targetDescriptionstring, required. Industry, theme, and deal-shape signal in free text.
themestring, optional. A thematic hint to steer the search, for example "vertical SaaS consolidation". Defaults to deriving one from the description.
engagementCategoryenum, optional. Buy-Side · Sell-Side. Defaults to both unless the description clearly implies one.

Orchestrates

Tools this prompt drives; each is called with base schemas as the conversation requires.

Output

  • The comparable engagements, each with why it is comparable.
  • What each one implies for the deal in hand.

Availability

Included in all tiers. Surfaces as a slash command with an argument form in Claude Desktop.

Related

Used in jobs

gst_irl_create

Prompt

Assembles the blank information-gathering ask GST hands a target before diligence tools can run, configured for the engagement and delivered as a workbook to fill in.

Arguments

NameRequirement
targetName / companyName / projectNamestrings, optional. Composed into the workbook title.
transactionContextenum, optional. sell-side · buy-side · value-creation · unknown. Also fires the authored skip-if directives.
includeSectionsarray of two-digit section ids, optional.
excludeRequestsarray of NN-II keys, optional. See list_irl_requests for the keys.
customRequestsstring, optional. Extra per-section requests.
showCanonicalReferenceboolean, optional.

Orchestrates

Tools this prompt drives; each is called with base schemas as the conversation requires.

Output

  • The configured request list, section by section.
  • The workbook to send, plus the Hub page for a one-click download.

This one issues, it does not answerThe workbook comes back empty, for the target to complete. When the answers are already in your own evidence, a data room export or filings or an earlier conversation, use gst_irl_populate instead: it produces the same workbook already populated, and leaves only the rows it could not support blank.

Availability

Included in all tiers. Surfaces as a slash command with an argument form in Claude Desktop.

Related

Used in jobs

gst_irl_populate

Prompt

Populates the request list from evidence already in the conversation, a data room export, filings, or prior sessions, instead of waiting for the target to return one. Stops at the artifact for the operator to review.

Arguments

NameRequirement
targetName / companyName / projectNamestrings, optional. Composed into the workbook title.
transactionContextenum, optional. sell-side · buy-side · value-creation · unknown.
includeSections / excludeRequests / customRequestsThe same scoping the blank generator takes.

Orchestrates

Tools this prompt drives; each is called with base schemas as the conversation requires.

Output

  • An inventory of the evidence found, before anything is written.
  • The populated workbook, each answered row carrying the source it rests on.
  • The blank rows, which are the remaining ask to the target.

It stops at the artifactThe prompt does not run the diligence sweep. The operator reviews the populated workbook first, then runs gst_irl_sweep on it exactly as for a target-returned one. Re-running with new evidence extends the file rather than overwriting it.

Availability

Included in all tiers. Surfaces as a slash command with an argument form in Claude Desktop.

Related

Used in jobs

gst_irl_extract

Prompt

Distills a populated request list into a portable extract record plus the per-tool payloads derived from it. Makes no tool calls, so the record can be saved and pasted into later sessions and other GST prompts.

Arguments

NameRequirement
filledIrlstring, optional. The populated list, entire markdown body. Omit it when the list is attached to the conversation or was pasted earlier.

Pasting into a single-line client field collapses the line breaks. The run still works: what the record is checked against normalizes whitespace before matching.

Output

  • The extract record: one fact per answered row, with the section it came from.
  • Derived payloads for the nine analysis tools, projected from the record without calling any of them, ready to hand over in a later session.
  • A self-dating header recording when the record was made and whether the server witnessed the time.

It calls nothingThis prompt runs no tools. It reads the list and produces a record, which is what makes the record portable: it survives the conversation, and any later session can drive the analysis tools from it. For the full sweep in one turn, use gst_irl_sweep.

Availability

Included in all tiers. Surfaces as a slash command with an argument form in Claude Desktop.

Related

Used in jobs

gst_irl_sweep

Prompt

Ingests a populated request list and drives every applicable Hub tool to a unified engagement dossier, sections (A) through (J).

Arguments

NameRequirement
filledIrlstring, optional. The populated Information Request List, entire markdown body. Omit when the list is attached to the conversation or pasted earlier.

Target name and engagement context are inferred from the list itself; the only hard stop is no list present anywhere, a blank-template halt, or tools unavailable.

Orchestrates

Tools this prompt drives; each is called with base schemas as the conversation requires.

Output

  • (A) Target snapshot · (B) Diligence agenda · (C) Architecture and paradigm assessment.
  • (D) Infrastructure cost governance · (E) Technical debt · (F) Regulatory exposure.
  • (G) Comparable engagements · (H) Market signal · (I) Synthesis and recommendation.
  • (J) Gaps and assumptions. The audit surface of the run: unanswered rows, elided tools, every assumption and conversion applied.
  • Every tool-backed section closes with its deeplink, copied verbatim.

Trust the operatorA populated GST request list is trusted input: no provenance apparatus, no hashing, no citation loops. The model-authored gap list is what keeps the run honest. For the portable extract record without tool calls, use gst_irl_extract.

Availability

Included in all tiers. The market-signal section renders only where radar tools are granted.

Related

Used in jobs

gst_irl_ingestion

Prompt

The provenance-instrumented ingestion workflow: the same dossier sweep, plus hashing, citation verification, and a structured audit envelope.

Arguments

NameRequirement
filledIrlstring, optional. The populated list.
modeenum. full runs the whole sweep; extract-only produces the record and stops.
auditLevelenum. standard · enhanced · debug. Selects how much of the audit surface comes back.

Orchestrates

Tools this prompt drives; each is called with base schemas as the conversation requires.

Output

  • The same dossier sections gst_irl_sweep produces.
  • A provenance footer: what was verified, what was not, and what was assumed.
  • The audit envelope, at the level the run asked for.

Coexists with gst_irl_sweepBoth are registered. Reach for gst_irl_sweep when the operator vouches for the document, which is the usual case. Reach for this one when the run has to carry its own citation-level audit trail.

Availability

Included in all tiers. Surfaces as a slash command with an argument form in Claude Desktop.

Related

Used in jobs

gst_architecture_layer_review

Prompt

Walks a target through GST's five architectural layers, software, operations, product, organization, and industry, and surfaces the risks that sit in each.

Arguments

NameRequirement
targetSummaryFree text describing the target's architecture: product and software stack, infrastructure and hosting, data estate, engineering org shape, and industry context. The more architectural detail supplied, the sharper the per-layer read.

Orchestrates

Tools this prompt drives; each is called with base schemas as the conversation requires.

Output

  • A read per layer, with the risks that layer carries for this target.
  • How those risks cascade between layers, which is where the framework earns its keep.

Availability

Included in all tiers. Surfaces as a slash command with an argument form in Claude Desktop.

Related

Used in jobs

gst_regulatory_exposure_brief

Prompt

Compiles the regulatory frameworks that apply to a target, with summaries and a resource link per framework, so counsel starts from an exposure list rather than an open question.

Arguments

NameRequirement
targetJurisdictionsarray, required. Where the target operates, collects, or processes data, for example ["eu", "us-ca"].
dataCategoriesarray, required. Which categories to assess: data-privacy · ai-governance · industry-compliance · cybersecurity.
productTypestring, required. Informs which frameworks apply beyond jurisdiction alone.

Orchestrates

Tools this prompt drives; each is called with base schemas as the conversation requires.

Output

  • The applicable frameworks, grouped by jurisdiction.
  • A summary per framework, taken from the corpus rather than from memory.
  • The resource URI for each, so the full document can be read next.

Availability

Included in all tiers. Surfaces as a slash command with an argument form in Claude Desktop.

Related

Used in jobs

gst_radar_brief_today

Prompt

The day's radar, briefed: the most recent annotated items summarized in the GST Take voice, for a morning read or a pre-meeting scan.

Arguments

NameRequirement
categoryenum, optional. pe-ma · enterprise-tech · ai-automation · security. Omit for all categories.

Orchestrates

Tools this prompt drives; each is called with base schemas as the conversation requires.

Output

  • The recent annotated items, with what GST makes of each.
  • A provenance line: radar items are not independently verified, so confirm against the source before acting or sharing with a client.

Availability

Radar access is granted separately from the analysis tools. Rate ceilings are per-client capability limits, not contractual quotas.

Related

Used in jobs

gst://library/…

Resource family

The four reference guides behind GST's diligence method, readable in full: the architecture framework, the data room structure, the information request list, and the mapping from request to tool input.

URI shape

gst://library/<guide>

Returns

  • Business and technology architectures. The five layers and how they cascade into business outcomes.
  • Virtual data room structure. Nine folder categories, with the common pitfalls.
  • Information request list. The intake checklist, organized by the same taxonomy.
  • Request-to-tool mapping. Which line of a completed list feeds which tool input.

Availability

Included in all tiers. Browsable from the resource library in any MCP client that surfaces resources.

Related

Used in jobs

gst://regulations/…

Resource family

123 framework documents, one per regulatory framework, each readable in full.

URI shape

gst://regulations/<jurisdiction>/<framework>

Returns

  • One document per framework: requirements, penalties, effective dates.
  • Four categories: data privacy · AI governance · cybersecurity · industry compliance.

Resources are host-loadedA prompt cannot read a resource. The host application loads resources as context, so they are in the conversation before the model needs them; workflows that need canonical text embed it server-side.

Availability

Included in all tiers. Browsable from the resource library in any MCP client that surfaces resources.

Related

Used in jobs

gst://radar/…

Resource family

Six feeds: the annotated highlights, the whole wire, and the wire split by each of the four categories.

URI shape

gst://radar/<tier>/<latest|category>

Returns

  • The annotated tier, each item carrying its GST Take.
  • The wire, whole or filtered to private equity and M&A, enterprise technology, AI and automation, or security.

Availability

Radar access is granted separately from the analysis tools. Rate ceilings are per-client capability limits, not contractual quotas.

Related

Used in jobs

Authentication

Operations

OAuth 2.1 for both shapes of client: client credentials for a machine client, and authorization code with PKCE for a person connecting a desktop AI client.

Returns

  • Machine clients receive a client id and secret, and exchange them for a short-lived access token.
  • A person connecting a desktop client is taken through a consent screen and never handles a token by hand.
  • Every call carries its token; there is no anonymous surface beyond the health check.

Clients are registered, not self-serviceThere is no dynamic client registration and no user directory. Credentials are issued through a conversation with GST, which is also how scopes and a tier get set correctly the first time.

Availability

Request access to be provisioned. See the request-access path on the MCP Server page.

Related

Rate limits

Operations

Per-client capability ceilings by tier, applied per minute and per day, with the radar tools metered separately from the analysis tools.

Returns

  • Every response carries standard rate-limit headers, including the caller's own ceilings, so a client can self-diagnose its budget without first hitting a limit.
  • A warning surfaces as the budget approaches its ceiling, ahead of any refusal.
  • Over the ceiling, calls are refused with the time to wait rather than failing opaquely.

Tunable, not contractualThese are abuse and capacity limits, adjustable per client, not ratified service quotas. No rate commitment is contractually made. The current per-tier ceilings are published on the MCP Server page.

Availability

Applies to every tier. A tier change takes effect on the next window.

Related

Status

Operations

A public status page over the same health data the server reports: dependency state, per-tool latency, and request volume.

Returns

  • Dependency status, including whether the intelligence feed is reachable.
  • Per-tool latency and request volume.
  • The build actually serving traffic.

Availability

Public, no credentials required.

Related