IBM Sales Guidance MCP Server
Enables Bob to ask questions to IBM AskSales, search playbooks and competitive intel, generate client roadmaps, and check Watson + AskSales connectivity status.
README
IBM Sales Guidance Tool — MCP Server
An MCP (Model Context Protocol) server that exposes the IBM Sales Guidance Tool as tools Bob can invoke directly from chat.
Once registered, Bob can:
- Ask the IBM AskSales AI assistant questions about products, deals, and competitors
- Search IBM AskSales content (playbooks, battle cards, competitive intel)
- Generate a full 4-section Client Roadmap for any named account
- Check live Watson Assistant + AskSales connectivity status
Tools
| Tool | Description |
|---|---|
sales_guidance_diag |
Check Watson + AskSales connectivity and latency — run this first when debugging |
sales_guidance_chat |
Ask the AskSales Watson Assistant a question (product knowledge, objections, strategy) |
sales_guidance_asksales |
Search IBM AskSales content library for playbooks or competitive intel |
sales_guidance_roadmap |
Generate a full 4-section IBM Client Roadmap (takes 30–90s) |
Setup
1. Install dependencies and build
cd sales-guidance-mcp
npm install
npm run build
2. Register with Bob
Add the following to your .bob/mcp.json (workspace scope):
{
"mcpServers": {
"sales-guidance": {
"command": "node",
"args": ["/absolute/path/to/sales-guidance-mcp/build/index.js"],
"env": {
"SALES_GUIDANCE_URL": "https://ibm-sales-guidance-tool.2ck01rg2j69e.us-east.codeengine.appdomain.cloud",
"SELLER_EMAIL": "your.email@ibm.com"
}
}
}
}
Replace /absolute/path/to/sales-guidance-mcp with the real path on your machine.
3. Verify
Ask Bob: "Check the sales guidance tool status" — it will call sales_guidance_diag and report Watson + AskSales connectivity.
Configuration
All config is via environment variables in the env block of mcp.json:
| Variable | Required | Default | Description |
|---|---|---|---|
SALES_GUIDANCE_URL |
✅ Yes | — | Base URL of the deployed Sales Guidance Tool |
SELLER_EMAIL |
No | ibm-bob@ibm.com |
IBM seller email passed to Watson as user_id and email_address skill variable |
REQUEST_TIMEOUT_MS |
No | 100000 |
HTTP timeout in ms. Roadmap calls can take up to 90s — keep this above 90000. |
Architecture
Bob (chat) ──── MCP tool call ────► sales-guidance-mcp (stdio)
│
│ HTTPS
▼
IBM Sales Guidance Tool
(Code Engine, us-east)
│
┌──────────┴──────────┐
│ │
Watson Assistant IBM AskSales
(AskSales skill) (when configured)
The MCP server is a thin HTTP client — it calls the deployed Next.js app's API routes over HTTPS. No local services, no Docker, no credentials stored in this repo.
Known issues
Watson Assistant / AskSales outage (2026-07-21)
IBM reported degradation on IBM product queries in Watson Assistant / AskSales. Symptoms: sales_guidance_chat and sales_guidance_roadmap time out. Run sales_guidance_diag — if watson.latencyWarning is set, the outage is still active. Retry later.
AskSales search returns empty results
sales_guidance_asksales requires real AskSales credentials on the server side (ASKSALES_API_URL, ASKSALES_API_KEY). Run sales_guidance_diag — if asksales.enabled is false, placeholder credentials are in use and this is expected.
Roadmap timeout
The sales_guidance_roadmap tool has a 100s client timeout (default). Watson takes 30–90s to generate a full 4-section roadmap. If you consistently hit timeouts, set REQUEST_TIMEOUT_MS=120000 in the env block.
Development
npm run build # compile TypeScript → build/index.js
npm run dev # watch mode
The source is a single file: src/index.ts. Each tool is registered with server.registerTool() using the MCP SDK v2 API.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.