MCP Server

Score an idea without leaving Cursor, Claude, or Codex. Same analysis as preuve.ai: viability score, competitors, source-linked evidence.

https://mcp.preuve.ai/mcp

Same key as Get started. In claude.ai, adding the connector signs you in and mints the key for you, which works on a free account. Everywhere else, create one by hand at Account → API Keys, self-serve on Founder and above.

Connect

Paste this as-is. Keep the key out of the chat.

I want to validate startup ideas with Preuve: viability score, competitors, source-linked evidence.

Add the Preuve MCP server.

1. I have a Preuve API key (prv_...) from https://preuve.ai/app?settings=apiKeys.
   Do NOT ask me to paste the key into chat. Put it in MCP config / env.

2. Add the remote server at https://mcp.preuve.ai/mcp (HTTP):
   - Claude Code:
     claude mcp add preuve --transport http https://mcp.preuve.ai/mcp \
       --header "Authorization: Bearer <key>"
   - Cursor / Claude Desktop: ~/.cursor/mcp.json (or Claude Desktop config):
     {
       "mcpServers": {
         "preuve": {
           "url": "https://mcp.preuve.ai/mcp",
           "headers": { "Authorization": "Bearer <key>" }
         }
       }
     }
   - Codex:
     export PREUVE_API_KEY=<key>
     codex mcp add preuve --url https://mcp.preuve.ai/mcp \
       --bearer-token-env-var PREUVE_API_KEY
   - Clients that only support stdio:
     npx -y mcp-remote https://mcp.preuve.ai/mcp \
       --header "Authorization: Bearer <key>"

3. Confirm these 8 tools appear: start_analysis, get_analysis,
   enrich_analysis, export_analysis, create_batch, get_batch, export_batch,
   generate_ideas.

4. First test with scanType "starter" only (it costs nothing):
   start_analysis on my idea, poll get_analysis, show me the viability score.

Read https://docs.preuve.ai/agent-skill.md first.

claude mcp add preuve --transport http https://mcp.preuve.ai/mcp \
  --header "Authorization: Bearer $PREUVE_API_KEY"

Add this to ~/.cursor/mcp.json (or the project .cursor/mcp.json):

{
  "mcpServers": {
    "preuve": {
      "url": "https://mcp.preuve.ai/mcp",
      "headers": {
        "Authorization": "Bearer prv_..."
      }
    }
  }
}

Save the key in PREUVE_API_KEY, then:

codex mcp add preuve \
  --url https://mcp.preuve.ai/mcp \
  --bearer-token-env-var PREUVE_API_KEY

In claude.ai (web or desktop): Settings → Connectors → Add custom connector. Paste:

https://mcp.preuve.ai/mcp

Sign in with Preuve and approve. No key to copy. Preuve creates one for the connector. Revoke it anytime from API key settings.

If your client cannot use a remote HTTP MCP server, bridge with mcp-remote:

{
  "mcpServers": {
    "preuve": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://mcp.preuve.ai/mcp",
        "--header",
        "Authorization: Bearer prv_..."
      ]
    }
  }
}

If you have this repo, you can run the local server instead:

claude mcp add preuve \
  --env PREUVE_API_KEY=$PREUVE_API_KEY \
  -- node /path/to/scripts/preuve-mcp-server.mjs

Tools

Tool	What it does
`start_analysis`	Start a scan. You must pass `scanType`: `starter` (free) or `deep` (paid). Deep scans also require `stage` and `budget`.
`get_analysis`	Check status, progress, and report URLs. Does not return the result itself.
`enrich_analysis`	Fill in missing sections. Safe to call twice. Can start extra modules on a deep scan.
`export_analysis`	Get the JSON result for one completed scan.
`create_batch`	Score up to 10 ideas at once.
`get_batch`	Check each item’s status.
`export_batch`	Get the JSON for the batch, plus why any item was skipped.
`generate_ideas`	Generate startup ideas from interests. Free accounts: 5 per rolling 24 hours. `pro` is a paid perk; founder-profile tailoring is automatic on paid accounts with a saved profile. Spends no scan quota.

Keeping exports small

Both export tools take verbosity: full or summary. summary drops section prose and the Google Trends data points, which together are about two thirds of a deep report, and keeps every scored field: score, verdict (including the Bottom Line narrative under details.verdict.narrative), competitors, market size, risks, pivots, citations. One subsection survives the trim: details.sections.synthesis, the report’s closing verdict (final verdict, key strengths and weaknesses, deal breakers, pivot recommendation). What it left out is listed under details.omitted. export_analysis defaults to full. export_batch defaults to summary, because a batch multiplies one report by up to ten and a full batch will not fit in the client’s tool-result limit.

Locked fields on a starter scan

A starter scan returns a real analysis, not a partial one, but it leaves the deep-tier fields null. A deep scan on the same idea fills in details.sections and details.pivots directly. Five more, details.founderFit, details.playbook, details.googleTrends, details.proofOfDemand and details.communityDemand, are opt-in modules: a deep report makes them available, and enrich_analysis generates them on request. Competitor detail, risk explanations, market segmentation (details.market.segments, industryTrends, competitivePositioning) and source citations (details.citations, details.searchContext.sources) are withheld the same way the web report withholds them from a free viewer. When anything is withheld, the export carries a top-level locked object naming each field, what unlocks it, and why. Read it before concluding a field is missing: null there means locked by tier, not a failed analysis.

Slash commands

The server also exposes two MCP prompts. They are shortcuts for you, not tools the model calls: pick one from your client (in Claude Code they are /mcp__preuve__validate_idea and /mcp__preuve__generate_ideas; in claude.ai they are under the + menu, Connectors).

validate_idea, taking the idea as its only argument, drops in a request that runs the scan and polls it to completion.
generate_ideas, taking your interests as its only argument, drops in a request that generates startup ideas - no prior report needed.

Example prompts

Validate this idea with a starter scan: "AI bookkeeping for solo lawyers in France"

Run a deep scan on my top idea, then generate the launch playbook
and proof of demand once it completes.

Batch-score these 12 ideas and rank them by viability score.

A deep scan spends the same quota as the web app. The MCP server does not add a second bill. See Quotas and billing.

Teach your agent the workflow

Your agent can keep scoring ideas without burning a paid scan. The Agent Skill is that judgment: starter vs deep, when to wait, when a retry is safe. Without it, agents often retry with a new id and spend a second deep scan. Install it once. It is a markdown file, not another key.

Getting Started

For agents

Concepts

Connect

Tools

Keeping exports small

Locked fields on a starter scan

Slash commands

Example prompts

Teach your agent the workflow

​Connect

​Tools

​Keeping exports small

​Locked fields on a starter scan

​Slash commands

​Example prompts

​Teach your agent the workflow

Connect

Tools

Keeping exports small

Locked fields on a starter scan

Slash commands

Example prompts

Teach your agent the workflow