mcp.vasco.app/mcp

Deploy your agent anywhere.

Ground it on Vasco.

Claude or your own stack. Wherever your agent runs, it needs the same revenue-data substrate underneath: consistent metrics, account timeline from lead to cash, your actual plan, integrity. One MCP endpoint. 58 tools. Three layers.

Quick start · ~30 seconds

One command. You're in. Then ask anything.

~/revenue-ops claude
vasco mcp

1 - Install

$ claude mcp add-json vasco '{"type":"http","url":"https://mcp.vasco.app/mcp","oauth":{...}}'

> Added http MCP server vasco to local config

 ▐▛███▜▌
▝▜█████▛▘
  ▘▘ ▝▝

Claude Code v2.1.145

Opus 6.7 (1M context) · Claude Team

~/revenue-ops

/mcp

Authentication successful. Connected to vasco.

58 tools loaded · acme-corp · scopes: read:metric, read:context, read:plan

2 - Ask

❯ What's the win rate for expansion this quarter, and which at-risk accounts should we prioritize?

⏎ Thinking…

query-metric-engine expansion_win_rate, period=2026Q2 → 0.42 (n=12)

query-metric-engine expansion_win_rate, period=2026Q1 → 0.38 (n=13)

get-plan-forecast expansion arr_target=$90k → $82.5k booked (+2pt vs pace)

query-context-graph at_risk_expansion · signal=champion_change in_last=60d → 3 accts

Expansion · Q2 2026 · win rate 42% (+4pt QoQ)

Expansion ARR Won $82,500 / $90k forecast
92% attainment
Expansion Deals Won 5 / 8 forecast
63% attainment
Q3 SAL Pipeline $180k / $540k forecast
33% attainment

On track on dollars: $82.5k of the $90k target booked and win rate up to 42% (+4pt QoQ) — fewer but larger deals (5 of 8 by count).

Red flag: Q3 SAL pipeline is critically light at 33% coverage; 3 accounts also show champion-change in the last 60 days.

───

Accounts to prioritize

1. Heliox — HIGH

Champion left in March; renewal in 45d with no exec sponsor identified. Multithread to a new owner this week.

2. Nimbus — MEDIUM

Usage flat two quarters; expansion talk stalled on a pending SDK auth fix. Unblock to reopen the conversation.

↑ Stratos — EXPANSION-READY

Usage up 3× this quarter, added 2 seats, asked about the enterprise tier. Strong upsell to close this month.

───

Bottom line: Q2 dollars are on track — 42% win rate (+4pt QoQ), $82.5k of $90k booked on fewer, bigger deals. The red flag is Q3 pipeline at 33% coverage — get ahead of it now. Multithread Heliox before its renewal and close the Stratos upsell.

REQUIRES: Authenticated Vasco user · Trial or paid workspace · Sources connected: onboarded

Onboarding takes ~10 min · we wire reconciliation for you.

Ready to get started?

Vasco works with any MCP-compatible client. Pick yours below and you're connected in under a minute.

# Get your clientId and callbackPort from app.vasco.app after sign-up.
# OAuth opens in browser. Reads auto-approved · writes need confirmation.

$ claude mcp add-json vasco '{"type":"http","url":"https://mcp.vasco.app/mcp","oauth":{"clientId":"$VASCO_CLIENT_ID","callbackPort":$VASCO_CALLBACK_PORT}}'

What you'd have to build

Six categories of work between your agent and a real answer.

Each is its own engineering project. Tap through to see what each layer actually contains — and what it costs to build before you have one.

01 / 06
01 · IDENTITY RESOLUTION realistic v1 · 6–8 weeks

One account.
Seven systems. No link.

Acme Corp is account_8842 in Salesforce, cus_K9aBz in Stripe, workspace_117 in your product, plus 47 contacts scattered across Gong, Slack and Outreach. Your agent reasons over seven strangers, not one company.

You'd build
account-level resolutiondomain → account matchingcontact rollupsmerge-survivalcontinuous (not batch)
02 · ACCOUNTS' TIMELINE realistic v1 · 10–14 weeks

Account timeline, with every
conversation placed in stage.

Deal in CRM. Calls in Gong. Tickets in Zendesk. Threads in Slack. Contracts in DocuSign. Without reconstruction and conversation placement, your agent sees fragments — not Lead → MQL → SAL → Won.

You'd build
per-account journey graphconversation placementevent-level extractionout-of-order mergestage attribution
03 · METRICS DEFINITION realistic v1 · 4–6 weeks

One question.
Three different numbers.

"MQL conversion rate?" returns 23%, 31%, or 18% depending on which dashboard your agent reads. None match what your team actually agreed an MQL is.

You'd build
semantic layerdefinition → SQL translationversioningaudit historymulti-team support
04 · PLANNING realistic v1 · 3–5 weeks

$180K closed sounds fine.
The target was $240K.

Numbers without targets are noise. Your agent has no way to read the plan, so every answer is missing the most important context: variance.

You'd build
plan storetargets by Q · segment · repvariance computere-forecastingwhat-if scenarios
05 · MEMORY realistic v1 · 8–12 weeks

Flagged at-risk.
Doesn't know it's lost 4-of-4.

The agent flags a deal. It has no idea that stalled stage 3 + no exec sponsor + competitor named has lost four of the last four times.

You'd build
historical pattern storeoutcome tagginganalogous-deal retrievalcontinuous learning
06 · CAUSALITY realistic v1 · research project

You can see it stalled.
You can't see why.

The "why" lives in a Slack thread, a Gong call, an email exchange. Linking "competitor mentioned Mar 14""velocity dropped 60% Mar 21" isn't a query — it's a research project.

You'd build
unstructured → structured extractioncausal linkingcross-channel attributioncauses (not correlations)

Total realistic build: ~9 months for v1.

Vasco ships this on day one. One MCP endpoint. Same data layer underneath every agent we've built and every one you'll build.

End-to-end pipeline

Sources in. Reconciled. Layered. Served.

vasco · data flow · sources → reconcile → layers → mcp → clients

Sources

HubSpot CRM
Salesforce CRM
Stripe Billing
Gong Calls
Snowflake Warehouse
+44 more

Vasco · Reconcile

Reconciliation Pipeline runs continuously · ≤60s lag
Reconcile Clean Dedupe Structure Map Radar
Unified Store

Layers

L01 · Foundation GTM Model · Mappings · Integrity · Metric Engine what — definitions & actuals
L02 · Plan Goals · Scenarios · Inputs · Forecasts · Benchmarks where — direction & pacing
L03 · Context Context Graph · Artifacts · Saved Queries · Reports why — relationships & cause

MCP Server

mcp.vasco.app /mcp
Streamable http OAuth 2.1 Org Scoping Read Auto-OK Write Confirm Rate Limits Citations Audit Trail
Tool Router
Artifacts

Clients

Gama Vasco's Agent
Claude Code Terminal
Claude Desktop Team/Pro
Cursor IDE
ChatGPT via MCP
Custom Any MCP Client

Three layers · one coherent answer

The revenue data architecture, exposed as MCP.

Every tool call falls into one of three layers — and they compose. The example above used all three: Foundation for the actuals, Plan for the gap, Context for the at-risk accounts. Pick any layer and the others fall in behind.

"What is the business? How does it perform?"

GTM Model

Stages, channels, motions, functions, employees, dimensions, journeys.

Source Mappings

CRM → GTM entity mapping. Preview-before-save. Versioned.

Integrity Radar

Data quality score, issues, rules, auto-reconciliation.

Metric Engine

Actuals, trends, conversions, breakdowns. Deterministic.

Why this works for GTM teams

The same data layer, governed by RevOps.

Builders connect once. Then every rep, every agent, every seat reasons against the same definitions, the same plan, the same graph. RevOps governs what the agent sees — without re-platforming the org.

Shared One set of metric definitions across every Claude session in the org.
Governed RevOps owns scopes, definitions, plan inputs — agents inherit them.
Audited Every tool call logged with org, user, scope, citations.
Unified Marketing and Sales agents see the same customer journey, end-to-end.

More than 50 tools across 3 layers. Full reference in our docs.

Every tool — name, signature, scope, response shape — lives in one place. Browse the foundation, plan, and context tools, plus how artifacts and citations work.