DokaAI MCP Service POC
The DokaAI MCP Service POC provides a unified TypeScript service for business intelligence and customer analytics. You can:
Access business data via MCP tools and REST endpoints:
get_indian_users– fetch all Indian test users for segmentation, location, plan, and profile analysis.get_orders– retrieve all orders for revenue, category, delivery, payment, and risk analysis.get_user_orders– get orders for a specific user (e.g.,usr_001).get_user_business_profile– obtain a user's full profile including subscription, orders, invoices, payments, refunds, and health metrics.get_business_summary– aggregate business metrics and risk counts.REST API endpoints (e.g.,
/api/users,/api/orders) for HTTP integration.
Generate AI-guided reports using reusable MCP prompts for business summaries, customer segmentation, orders analysis, user orders, and customer health.
Leverage pre-computed metrics like
daysSinceLastLogin,overallCustomerHealth,failedPaymentCount, and risk signals for accurate analysis.Understand data context through
evidenceGuideanddataLimitationsfields returned with major responses.Authenticate securely using OAuth (PoC) or static bearer tokens/API keys.
Integrate with AI clients (e.g., Claude Desktop) via local stdio MCP or a Vercel-hosted HTTP MCP endpoint.
Deploy as a hosted service on Vercel with health, data, and MCP endpoints.
Deploys the MCP server as a serverless HTTP endpoint, allowing remote access to the business data tools via REST APIs and MCP protocol.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@DokaAI MCP Service POC show me the business summary"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
DokaAI MCP Service POC
Unified TypeScript service with:
local stdio MCP server for Codex / Claude Desktop
Vercel-ready HTTP MCP endpoint
REST APIs backed by the same in-memory business data
Phase 1 production structure for auth, routes, logging, errors, computed metrics, and evals
Setup
npm install
npm run buildRelated MCP server: flipkart-seller-mcp
Local MCP
Run the stdio MCP server:
npm startCodex / Claude Desktop can still use:
{
"command": "node",
"args": ["/Users/ayushsrivastava0609/Doka-AI/mcp-server-poc/dist/index.js"]
}Vercel Deployment
Deploy this folder as the Vercel project root:
/Users/ayushsrivastava0609/Doka-AI/mcp-server-pocHosted endpoints:
GET /healthGET /api/usersGET /api/ordersGET /api/users/:userId/ordersGET /api/users/:userId/business-profileGET /api/business/summaryPOST /mcpGET /mcpDELETE /mcp
Authentication
For hosted connector authentication, the service exposes a POC OAuth flow:
/.well-known/oauth-protected-resource/mcp/.well-known/oauth-authorization-server/oauth/register/oauth/authorize/oauth/token
When ChatGPT or Claude connects to /mcp without a token, the server returns 401 with a WWW-Authenticate header pointing to the OAuth protected-resource metadata. The connector client can then start the OAuth flow.
Set this environment variable in Vercel:
OAUTH_SIGNING_SECRET=your-long-random-signing-secretDuring OAuth authorization, the demo page asks for:
DokaAI Username
DokaAI PasswordDefault mock login:
username: dokaai_demo_user
password: dokaai_demo_passwordOverride it in Vercel with:
MOCK_DOKAAI_USERNAME=your-demo-username
MOCK_DOKAAI_PASSWORD=your-demo-passwordFor this POC, a successful login creates a short-lived signed OAuth token. For production, replace this with a real user/session system.
You can also set this legacy static token for private API testing:
MCP_AUTH_TOKEN=your-long-random-token/health, /api/health, OAuth metadata, and OAuth endpoints stay public. Everything else requires either an OAuth bearer token or:
Authorization: Bearer your-long-random-tokenor:
x-api-key: your-long-random-tokenExample:
curl https://your-app.vercel.app/api/users \
-H "Authorization: Bearer your-long-random-token"MCP Tools
get_indian_users: Fetch all Indian test users from the backend API.get_orders: Fetch all business orders.get_user_orders: Fetch orders for one user, such asusr_001.get_user_business_profile: Fetch one user with subscription, orders, invoices, payments, refunds, computed metrics, risk signals, data limitations, and evidence guidance.get_business_summary: Fetch aggregate business metrics, risk counts, summary signals, data limitations, and evidence guidance.
The AI client can handle filtering, lookup, grouping, summaries, and cross-dataset reasoning from the returned data.
For better answer accuracy, important calculations are returned by the backend instead of being left to the model:
daysSinceLastLogin
daysSinceLastOrder
daysUntilRenewal
failedPaymentCount
overdueInvoiceCount
riskOrderCount
financialRisk
engagementRisk
renewalRisk
overallCustomerHealthEvery major MCP response also includes:
evidenceGuide
dataLimitationsPhase 1 Structure
The code is split by responsibility:
src/auth OAuth-shaped auth and token helpers
src/config runtime constants
src/http request/response utilities
src/logging structured JSON logger
src/mcp MCP tools, prompts, evidence, server setup
src/routes hosted MCP and REST route handlers
src/services mock data, business metrics, data limitations
src/vercel.ts thin deployment entrypointSee:
docs/phase-1-production.md
docs/evals.md
docs/usability.mdMCP Prompts
Prompts are reusable workflows the client can run.
business_summary_report: Guides the AI to produce a simple business report with overview, revenue snapshot, risk signals, patterns, recommended actions, and evidence used.customer_segmentation_report: Guides the AI to analyze users by location, plan, profession, support, and billing signals.orders_analysis_report: Guides the AI to analyze revenue, product categories, payments, fulfillment, sales channel, and order risks.user_orders_report: Guides the AI to analyze orders for one user. RequiresuserId.customer_health_report: Guides the AI to analyze one customer using profile, subscription, orders, invoices, payments, refunds, and metrics. RequiresuserId.
Available Tools
5 toolsget_business_summaryGet Business SummaryA
Fetch aggregate business metrics across users, orders, invoices, payments, refunds, and subscriptions.
Inputs: no named parameters.
get_indian_usersGet Indian UsersA
Fetch all Indian test users. Use this for customer segmentation, location analysis, plan analysis, and profile lookup.
Inputs: no named parameters.
get_ordersGet OrdersA
Fetch all business orders. Use this for revenue, product category, delivery, payment, and risk analysis.
Inputs: no named parameters.
get_user_business_profileGet User Business ProfileA
Fetch one user with their subscription, orders, invoices, payments, refunds, and business metrics.
Inputs: userId (required).
get_user_ordersGet User OrdersC
Fetch all orders for a single user, such as usr_001.
Inputs: userId (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 5 tools
Tools are mostly distinct: one for Indian users, one for all orders, one for user-specific orders, one for full user profile, and one for aggregate summary. Some overlap exists between get_orders and get_user_orders, but names clarify scope. get_user_business_profile includes user info, overlapping with get_indian_users but with different granularity.
All tools follow a consistent 'get_<noun>' pattern using snake_case. The nouns are descriptive and the pattern is uniform, making it easy to predict tool behavior from names.
With 5 tools, the server is well-scoped for a proof-of-concept. It covers key data access patterns without unnecessary bloat, balancing coverage and simplicity.
The tool set is read-only, missing create/update/delete operations. It lacks a tool to fetch a single order by ID or a simple user lookup without full profile. For a POC, these gaps may be acceptable, but the surface feels incomplete for production use.
Maintenance
Related MCP Connectors
Unified MCP server for 70+ eCommerce platforms: products, orders, customers, and more.
Real-time data APIs for 50+ commerce, grocery, social and maps platforms over one OAuth MCP server
Unified.to MCP server — one API for 500+ B2B SaaS integrations across 28+ categories
Related MCP Servers
- AlicenseAqualityDmaintenanceAn API-only MCP server for Blinkit that enables automated shopping on the Indian quick-commerce platform, supporting login, search, cart, checkout, and payment via UPI.252MIT
- AlicenseAqualityCmaintenanceA token-optimized MCP server that enables AI agents to manage Flipkart Seller operations including order fulfillment, inventory, returns, ad campaigns, and financial settlements via the Flipkart v3 API.58 npm2MIT
- AlicenseAqualityDmaintenanceMCP server for deploying projects to multiple cloud platforms (Vercel, Railway, Neon, MongoDB Atlas, Docker) and running local dev servers, with orchestration for full-stack deployments.8MIT
- FlicenseNot gradedqualityDmaintenanceMCP server for Akij Resource Digital Management team providing KPI summaries and utility tools (time, echo, calculation) over Streamable HTTP, deployable to Vercel.-