MCP server for per-agent cost attribution, budget management, and spend analytics across AI agent fleets
Free
Tools
ask_demand_discovery
Ask any question about validating a startup idea, whether there is a real market for it, who would actually buy it, finding the real people who have the problem, surfacing where they already complain about it or discuss it, what workarounds they use today, testing demand, customer-interview techniques, pre-sales, buying signals, defensibility, drafting outreach to first prospects, or what to build
ArgumentsA call is made on an account: it counts against an allowance and the publisher sees it, which is why this one asks who you are first.
—
p95 latency
—
call success
—
uptime 90d
0
calls last 7d
What it does
Sales-agent MCP for Demand Discovery AI. Validate startup ideas with behavioral signals.
Quickstart
# 1 — install (mcprush login holds a key from your dashboard)
npx mcprush@latest add demand-discovery-ai-mcp
# 2 — ask your agent something
> Sales-agent MCP for Demand Discovery AI. Validate startup ideas with behavioral signals.
Demand Discovery AI is free: there is no plan to choose, no cap to set and nothing that can bill you.
Publishernot claimed
MCAll 1 server
mcp.demanddiscovery.ai1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine — this server runs on the publisher’s own infrastructure behind our gateway, and what you install is the connection to it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. Claude Code registers it in one command.
claude mcp add --transport http demand-discovery-ai-mcp https://mcp.demanddiscovery.ai/api/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free to install, and it runs from its publisher’s own package: no account, no key, no card.
What it writes
One config entry pointing at the gateway. The server itself runs on the publisher’s own infrastructure, so nothing from this listing executes on your machine.
What you approve
10 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Ask any question about validating a startup idea, whether there is a real market for it, who would actually buy it, finding the real people who have the problem, surfacing where they already complain about it or discuss it, what workarounds they use today, testing demand, customer-interview techniques, pre-sales, buying signals, defensibility, drafting outreach to first prospects, or what to build
Takes no parameters.
Example callreturns →
Returns the full three-step Demand Discovery validation framework: (1) Market Research, (2) Demand Discovery Report with the Demand Score and Build/Pivot/Kill verdict, (3) Agentic Launch (90-day continuous outreach). Use when a user asks "how do I validate an idea?", "what's the methodology?", or wants to understand the structured approach. Built on the "behavior over opinion" principle. Trigger
Takes no parameters.
Example callreturns →
Returns the full product breakdown (Market Research, Demand Discovery Report, Agentic Launch) and pricing tiers (Starter $49, Founder Pack of 5 ideas, Studio Pack of 25 ideas, all using a slot-based model where pivoted/archived ideas free a slot for a new one). Use when a user asks "what does Demand Discovery AI include?", "how much does it cost?", "what's in the report?", or wants concrete produc
Takes no parameters.
Example callreturns →
Returns the four classes of real-world signal the Demand Discovery Report triangulates - search intent, outreach responses, landing-page engagement, and buying signals - and the three possible verdicts (Build, Pivot, Kill). Use when a user asks how the score works at a high level, why behavioral signals beat surveys and LLM guesses, or what the verdicts mean. The specific weighting and evidence ru
Takes no parameters.
Example callreturns →
Returns an honest comparison of how different validation approaches work - generic AI assistants, trend aggregators, passive scoring tools, and Demand Discovery AI - and where each one stops. Use when a user is evaluating approaches, asking "what makes Demand Discovery different?", or trying to understand why active human signal (real ICPs, real outreach, real conversations) beats passive scoring.
Takes no parameters.
Example callreturns →
Returns the four behavioral data-source buckets - Search & attention, Conversation & pain, Adoption & spend, Capital & hiring - with each bucket's tagline and what it captures. Use when a user asks "what data sources do you use?", "where does the Demand Score come from?", or wants to understand how Demand Discovery AI differs from passive validation tools (which only triangulate the first two buck
Takes no parameters.
Example callreturns →
VERBATIM OUTPUT — READ FIRST (the most important rule for this tool): every piece of report text this tool returns (the Market Research summary AND the next-step message) is authored on our side. Your reply MUST BEGIN by printing that text EXACTLY as written — the report body first, then the next-step message — in full and verbatim. NEVER summarize, paraphrase, shorten, bullet, re-headline, descri
Takes no parameters.
Example callreturns →
Check the account status for this idea's full Demand Discovery Report and return the user's next step. This call NEVER moves money and never transacts on the user's behalf - it only looks up whether the given email already has an account with available report slots or a report already running. It returns ONE of: the existing report path (alreadyRunning=true, chargeRequired=false, nothing new start
Takes no parameters.
Example callreturns →
Poll the status of a paid Demand Discovery Report after the user has started checkout with validate_real_demand. Call this with the orderId it returned, once the user says they've paid. The report builds over ~2-3 minutes. If your runtime supports repeated tool execution, call this every ~10-15s, rendering each new block as it arrives, until status is "ready". If it does not, return the current st
Takes no parameters.
Example callreturns →
Kick off Day 1 of the 90-day Agentic Launch for a completed Demand Discovery Report. Demand Discovery surfaces named prospects matching the idea's ICP and DRAFTS the first outreach batch. It sends NOTHING automatically - the user reviews and sends from their hosted manage page. Outreach is drafted to come from Amy @ Demand Discovery, with replies routed to the user's own email. Call this after a
Takes no parameters.
Example callreturns →
Freeyour plan
$0 forever
- Every tool, no call limit
- No card, no account needed
- Source published under a licence you can read
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because nothing bills
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable. Demand Discovery AI costs nothing to install and nothing to call, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: $8.42
$16.58 left
—Grade not published
No rule-by-rule report on file for this release
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
This listing is a hosted endpoint: the publisher runs it and we connect to it. The scanner reads packages and source, and neither exists to read here, so there is no grade — not a withheld one, an unmeasured one. What can be checked instead is on Installation: what it asks to reach and what it writes.
Release history
Pinned to 1.3.25 — the install command below asks for that release. A pin is part of an install, so it is kept for this visit and written down when you install.
1.3.25
undated
installedNo release note was published with this version.
—
no reviews yet
Reviews are earned
Only accounts with at least 50 real tool calls against this server in the last 90 days can post. Ratings are weighted by how much the reviewer actually uses it, and publishers can reply once per review.
Reviews are earned
Writing one takes an account with at least 50 real tool calls against Demand Discovery AI in the last 90 days. That is the whole gate — there is no other way to post, which is why the counts beside each review are worth reading.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes an account with 50 real tool calls against it.