# Primavera

> Primavera is a paid MCP server for maps and travel. Hosted MCP server to build B2B prospect lists from Google Maps businesses. It runs as a hosted remote server, so there is nothing to install locally.

- **Kind:** MCP server
- **Pricing:** Paid
- **Platforms:** API
- **Website:** https://primaverapp.com/docs/api
- **Repository:** https://github.com/primavera-saas/primavera-mcp
- **MCP Registry name:** com.primaverapp/primavera
- **Categories:** maps and travel, sales and CRM, marketing and SEO
- **Listing updated:** 2026-11-14

## About

Prospecting starts with a request in plain words, such as independent car repair shops around Lyon with an email. The server turns it into categories and an area, counts and previews the matches, tells the cost, creates a list of up to 50,000 rows once you agree, and exports it as CSV or Excel.

Rows come from Google Maps places in France and other countries, read together with their websites for emails, phones, social networks and technologies. Jobs can run on a list: find executives, summarise a site, ask the website a question, AI filtering and email verification. Lookups, counts and estimates are free; paid calls take a maxCredits cap and an idempotency key so nothing is charged twice.

Access needs a Pro or Agency plan and an API key as a bearer header, and the same balance and prices as the web app apply.

## Features

- **Target to categories:** Suggests categories and an area for a request.
- **Free previews:** Counts, figures and estimates cost nothing.
- **Large lists:** Create lists of up to 50,000 rows.
- **List jobs:** Executives, website summary, AI filter and email verification.
- **Spend caps:** maxCredits and idempotency keys prevent double charges.

## Good for

- Build a lead list for a local trade
- Verify emails on a list
- Estimate list cost first
- Export prospects to Excel

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http primavera https://primaverapp.com/api/mcp
```

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
https://primaverapp.com/api/mcp
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "primavera": {
      "url": "https://primaverapp.com/api/mcp"
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "primavera": {
      "type": "http",
      "url": "https://primaverapp.com/api/mcp"
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "primavera": {
      "serverUrl": "https://primaverapp.com/api/mcp"
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "primavera": {
      "type": "http",
      "url": "https://primaverapp.com/api/mcp"
    }
  }
}
```

## Tools

- `get_account`: Plan, credit balance, Agency fair use per country and rate limits of the Primavera account that owns the API key. Call it first: it tells what the account can afford. Free. Same call as GET /api/v1/account of the REST API.
- `find_areas`: Find an area from a place as written: region, département, commune, postal code, or a radius around a town ("Lyon", "33", "30 km around Nantes"). Use the "area" field of a result (or of "match" when its status is "resolved") as the area of suggest_categories or as search.area. Free. Same call as GET /api/v1/areas of the REST API.
- `suggest_categories`: Entry point for ANY target: call it before any search, and never invent category ids. Give the target in plain words, WITHOUT the place ("independent car repair shops", "restaurants that could use an online booking tool") and the area from find_areas. Primavera's engine picks the Google Maps categories in groups and counts them in the area. Returns "selection" (groups, categories left out and why,
- `find_categories`: Look up a single Google Maps category by name (French or English), with its number of places. To build a target, use suggest_categories instead; use this only to check or add one category id to search.categories.ids. Free. Same call as GET /api/v1/categories of the REST API.
- `find_networks`: Look up a brand, franchise or network by name. Use its id in search.filters.networks ({ "mode": "only" | "exclude", "ids": [...] }); mode "exclude" without ids removes every known network (independent businesses only). Free. Same call as GET /api/v1/networks of the REST API.
- `count_search`: Count the places of a search (the "search" returned by suggest_categories). Its input describes the search object in full (target, area, filters one by one, sort): read it to edit a search. Places already delivered to the account are left out unless search.excludeDelivered is false. When "exact" is false, say "≈ N". Free. Same call as POST /api/v1/search/count of the REST API.
- `get_search_metrics`: The figures of a search in one call: total, places with an email address, a phone number, a website, and the estimated number of email addresses. Free. Same call as POST /api/v1/search/metrics of the REST API.
- `preview_search`: Up to 25 sample places of a search (name, city, category, rating, reviews). Contact details are booleans here: email addresses, phone numbers and websites only come with a list (create_list). Free. Same call as POST /api/v1/search/preview of the REST API.
- `estimate_list`: Rows, cost in credits and balance after, for a list of N rows of a search (up to 50,000). Tell the user the cost, then send "cost" as maxCredits to create_list with the same search, rows and withEmail. In a rarely searched area it returns kind "zone": the list fills itself after creation (create_list with maxCredits ≥ zoneEstimate.creditCap). Free. Same call as POST /api/v1/search/estimate of the 
- `create_list`: Export the places of a search into a new list, with their contact details (up to 50,000 rows). Price: 1 credit per place never delivered to this account (Agency: included under fair use); withEmail: only places with an email address (found ones first, then guessed and verified ones); verifyEmails: plus 1 credit per address verified. maxCredits is never exceeded: send the "cost" of estimate_list, o
- `list_lists`: The lists of the account, newest first, page by page (send nextCursor back as cursor). Free. Same call as GET /api/v1/lists of the REST API.
- `get_list`: Status of a list (creating, ready, filling, failed), rows, credits spent, progress of the export, of the guessed email addresses and of the email verification (progress.emailCheck.unverified = what verify_list_emails would cost), contents and latest jobs. While it is not ready, call it again every 10 seconds or more. Free. Same call as GET /api/v1/lists/{id} of the REST API.
- `get_list_items`: Rows of a ready list with every contact detail, page by page (nextCursor). Keep limit small (50 or less) and choose columns: large pages flood the conversation. For the whole list, use prepare_list_file. Free. Same call as GET /api/v1/lists/{id}/items of the REST API.
- `complete_list`: Add places to a list from its original search; places already in the list are skipped. Priced as an export: 1 credit per place never delivered to the account (Agency: included under fair use). Paid: maxCredits (the most credits this call may spend, never exceeded) and idempotencyKey (a new UUID v4 for this operation) are required; without them nothing runs. To retry after an error or a timeout, se
- `prepare_list_file`: Prepare the CSV file (every column) or the Excel file (the columns you choose) of a ready list. Then call get_list_file until the file is ready. A file stays available 7 days. Free. idempotencyKey (a new UUID v4) is required; reuse it only to retry the very same call. Same call as POST /api/v1/lists/{id}/files of the REST API.
- `get_list_file`: Status of a prepared file. Once it is ready, "url" is a download link valid 120 seconds: download it at once or give it to the user, and call again for a new link. Free. Same call as GET /api/v1/lists/{id}/files/{fileId} of the REST API.
- `estimate_list_job`: Estimate a job on a list before starting it: places eligible and the most credits it can spend. Jobs: executives (company executives, France and the United States only), summary (a 3-sentence summary of each website), question (a yes/no question asked to each website), filter (a criterion judged on the data we hold, no website read). Free. Same call as POST /api/v1/lists/{id}/jobs/estimate of the 
- `start_list_job`: Start a job on a list; it runs in the background. Each place is billed on its result, never beyond maxCredits nor the estimate: send estimate.maxCredits of estimate_list_job, with the same tool, question, criterion and scope. Follow it with get_job; results land in get_list_items. Paid: maxCredits (the most credits this call may spend, never exceeded) and idempotencyKey (a new UUID v4 for this ope
- `get_job`: Progress of a job: status, places done and billed, credits spent; for a finished filter or question job, the places per verdict. Free. Same call as GET /api/v1/jobs/{id} of the REST API.
- `verify_list_emails`: Verify the email addresses of a ready list (deliverable, risky, undeliverable): 1 credit per address that gets a verdict; the credits of the others are returned. maxCredits is the number of addresses you accept to verify: send progress.emailCheck.unverified of get_list. Paid: maxCredits (the most credits this call may spend, never exceeded) and idempotencyKey (a new UUID v4 for this operation) are

## FAQ

### Which plans can use it?

Pro or Agency.

### Is anything free?

Lookups, counts, previews and estimates are free; the category suggestion costs 100 credits.

### Is a deletion reversible?

No. Deleting a list is final and refunds nothing.

### Is Primavera free?

No. Primavera is a paid product.

### How do I add Primavera to Claude Code?

Run this command in your terminal: claude mcp add --transport http primavera https://primaverapp.com/api/mcp

### What are the best alternatives to Primavera?

The closest alternatives to Primavera are Google Ads + Meta Ads + SEO/GEO MCP, Calven, CompanyData, MisarReach MCP Server and NeuralVerge.

## Alternatives

- [Google Ads + Meta Ads + SEO/GEO MCP](https://ai-powered.com/mcp/google-ads-meta-ads-seo-geo-mcp): Google Ads + Meta Ads + SEO/GEO MCP is a freemium MCP server for marketing and seo.
- [Calven](https://ai-powered.com/mcp/calven): Calven is an MCP server for marketing and seo.
- [CompanyData](https://ai-powered.com/mcp/companydata): CompanyData is a paid MCP server for analytics and data.
- [MisarReach MCP Server](https://ai-powered.com/mcp/misarreach-mcp-server): MisarReach MCP Server is a freemium MCP server for sales and crm.
- [NeuralVerge](https://ai-powered.com/mcp/neuralverge): NeuralVerge is an MCP server for web search and scraping.
- [Tutu eSIM](https://ai-powered.com/mcp/tutu-esim): Tutu eSIM is a paid MCP server for maps and travel.
- [MCP](https://ai-powered.com/mcp/mcp-mwhffe53): MCP is a freemium MCP server for marketing and seo.
- [Red Center Studio free tools](https://ai-powered.com/mcp/red-center-studio-free-tools): Red Center Studio free tools is a free MCP server for marketing and seo.

---
Source: https://ai-powered.com/mcp/primavera
