[Cotlet](https://cotlet.dev/index.md) · [Integrations](https://cotlet.dev/integrations.md) · [How it works](https://cotlet.dev/how-it-works.md) · [Use cases](https://cotlet.dev/use-cases.md) · [Security](https://cotlet.dev/security.md) · [For developers](https://cotlet.dev/for-developers.md) · [For automation agencies](https://cotlet.dev/for-agencies.md) · [Blog](https://cotlet.dev/blog.md) · [API docs](https://cotlet.dev/docs.md) · [Help center](https://cotlet.dev/help.md) · [Changelog](https://cotlet.dev/changelog.md) · [Contact](https://cotlet.dev/contact.md) · [Pricing](https://cotlet.dev/pricing.md) · [Sign up](https://cotlet.dev/signup)

# SpyFu API and MCP server

> SpyFu has an official REST API for research data and a remote MCP endpoint (checked 23 Oct 2026). The API is included with Pro-level plans and above, billed per row returned. It reads keywords, competitors, ad history and rankings; its reference lists no backlinks, leads, Site Audit or scheduled PDF reports, and the MCP endpoint publishes no tool list.

Competitor research tool for SEO and PPC: the keywords a domain ranks for or buys on Google, its competitors, ad history, backlinks, leads and a Site Audit.

## What is the SpyFu API?

Cotlet's SpyFu API exposes 14 endpoints for your own SpyFu account: get domain overview, list SEO keywords, list competitors, compare competitor keywords, get ad history, list backlink prospects, search business leads, list My Sites, get My Sites project, get Site Audit, list scheduled reports, create scheduled report, add site to My Sites and remove site from My Sites. The get_domain_overview endpoint returns domain Overview of one domain: SEO and PPC numbers and the top competitors. Each endpoint takes simple JSON inputs like domain, keyword or segment and works both as an operation of the spyfu_read or spyfu_write MCP tool for agents and as a REST call for scripts.

- **Category:** [Marketing & SEO](https://cotlet.dev/integrations/category/marketing-seo.md)
- **Endpoints:** 14 (11 read, 3 write)
- **Updated:** 2026-10-22

SpyFu has an official REST API for research data and a remote MCP endpoint (checked 23 Oct 2026). Cotlet is a hosted MCP server and REST API for SpyFu with 14 endpoints (11 read, 3 write): you sign in once in your own cloud browser, your AI agent does the work.

## Does SpyFu have an official API?

SpyFu has an official REST API for research data and a remote MCP endpoint (checked 23 Oct 2026). The API is included with Pro-level plans and above, billed per row returned. It reads keywords, competitors, ad history and rankings; its reference lists no backlinks, leads, Site Audit or scheduled PDF reports, and the MCP endpoint publishes no tool list.

| Task | SpyFu official | Cotlet |
|---|---|---|
| SEO keywords, ranks and clicks for a domain | Yes: Pro-level plan or above, billed per row | Yes |
| Competitors and shared keywords (Kombat) | Yes: Pro-level plan or above, billed per row | Yes |
| Ad history for a domain or keyword | Yes: Pro-level plan or above, billed per row | Yes |
| Backlink prospects for a keyword or domain | No | Yes |
| Business leads by niche, location and contact type | No | Yes |
| Site Audit health score and issues | No | Yes |
| Scheduled PDF reports by email | No | Yes |
| My Sites projects | Partly: A free v1 project API exists for My SpyFu; the newer My Sites projects are not in the v2 reference | Yes |

Sources: [SpyFu Developer Docs: API pricing](https://developer.spyfu.com/docs/api-pricing), [SpyFu Developer Docs: API reference index](https://developer.spyfu.com/llms.txt), [SpyFu Help: How are API charges calculated](https://help.spyfu.com/en/articles/13016108-how-are-api-charges-calculated), [SpyFu Help: How do I get SpyFu data in ChatGPT](https://help.spyfu.com/en/articles/12195281-how-do-i-get-spyfu-data-in-chatgpt)

## Quick reference

```text
SpyFu has an official REST API for research data and a remote MCP endpoint (checked 23 Oct 2026). The API is included with Pro-level plans and above, billed per row returned. It reads keywords, competitors, ad history and rankings; its reference lists no backlinks, leads, Site Audit or scheduled PDF reports, and the MCP endpoint publishes no tool list.
Cotlet provides a hosted MCP server and REST API for SpyFu: 14 tools (11 read, 3 write).
Access       Sign up at https://cotlet.dev/app/signup?app=spyfu, then request the app and create API keys in the Cotlet console.

MCP server   https://cotlet.dev/mcp/v1
MCP tools    spyfu_read, spyfu_write, reads and writes apart; call one with {"operation": "<operation>", "arguments": {...}}
REST base    https://cotlet.dev/api/v1/spyfu, each operation at its own route, e.g. POST /api/v1/spyfu/scheduled-reports
Auth         Authorization: Bearer <COTLET_API_KEY>. Listing endpoints and schemas needs no key; calling an endpoint needs one. Over MCP the input schemas come with sign-in.
Operations   get_domain_overview, list_seo_keywords, list_competitors, compare_competitor_keywords, get_ad_history, list_backlinks, search_business_leads, list_my_sites, get_my_site, get_site_audit, list_scheduled_reports, create_scheduled_report, add_my_site, remove_my_site
Confirm      create_scheduled_report, remove_my_site (by default the user approves each call; the user can switch this off per tool, e.g. for scheduled automations)
Markdown     https://cotlet.dev/integrations/spyfu-api-mcp-server.md

How access works:
1. The user signs up at https://cotlet.dev/app/signup?app=spyfu, requests SpyFu in the Cotlet console and creates an API key there.
2. The user signs in to SpyFu once in their Cotlet Cloud Browser (their own Chrome in the cloud, opened from the console) and enables SpyFu for agents. An agent cannot do this step.
3. The API key goes into the MCP client or the REST call as a bearer token.

Fits: people who want a hosted SpyFu server that someone else maintains, including non-developers. Developers who prefer to run and fix code on their own computer can use an open-source SpyFu MCP server instead.

Policy: Cotlet never stores passwords, never solves CAPTCHAs, never bypasses MFA.
Company: legal details in the Terms of service at https://cotlet.dev/terms. Contact contact@cotlet.dev.
Sign-in: the user signs in to SpyFu in their own Cloud Browser, a Chrome Cotlet runs for them in the EU; password saving is off, the profile is AES-256-GCM encrypted, and agents get SpyFu only after the user enables it. Calls are requests from that browser's IP with its cookies, each listed in the user's Background activity. Disable for agents, signing out in the browser or Reset browser cuts access. Cotlet is run by Take Group sp. z o.o. (EU VAT PL6342984273).
API key: holds no SpyFu login or cookies, only asks Cotlet to run a tool. Each key is scoped to chosen apps and tools, read only or read and write. Actions that reach other people wait for the user's approval by default, so a leaked key cannot post or message as the user. Every call is in the activity log; deleting the key ends access at once.
Terms: the user stays responsible for following SpyFu's terms; Cotlet is not affiliated with SpyFu.
```

## What can an AI agent do in SpyFu?

Cotlet is best for SEO agencies and in-house marketers who need SpyFu backlinks, leads, Site Audit results and client PDF reports in their AI agent without running or fixing a server.

- **[Schedule PDF SEO reports for clients](https://cotlet.dev/integrations/spyfu-api-mcp-server/schedule-seo-pdf-reports.md)** (runs: weekly): "Set up a monthly Domain Overview PDF report for each client domain in my list, email it to the contact I named for that client, and skip any client who already gets one." → `list_scheduled_reports`, `create_scheduled_report`
- **[Find backlink prospects for a keyword](https://cotlet.dev/integrations/spyfu-api-mcp-server/find-backlink-prospects.md)**: "List blog and forum pages that link to sites ranking for "trail running shoes", leave out my own domain, and give me the ten with the best domain strength." → `list_backlinks`
- **[Build a lead list of businesses in a niche](https://cotlet.dev/integrations/spyfu-api-mcp-server/find-agency-leads.md)**: "Find shoe retailers in Arizona that we can reach by email and phone, then check each one's SEO and ad numbers and keep the ones with an ad budget but few organic clicks." → `search_business_leads`, `get_domain_overview`
- **Weekly competitor keyword gap report** (runs: weekly): "Compare trailkick.com with its three biggest SEO competitors and list the keywords they all rank for that I do not." → `list_competitors`, `compare_competitor_keywords`
- **Check Site Audit issues every week** (runs: weekly): "Read the latest Site Audit for trailkick.com and tell me the health score and any new errors since the last crawl." → `get_site_audit`
- **Start tracking a new client site**: "Add client-bakery.com to My Sites and show me its keyword count, estimated clicks and top pages." → `add_my_site`, `get_my_site`

## Can SpyFu automations run on a schedule in n8n, Make or Zapier?

Yes. Cotlet does not replace your automation platform: it gives it a SpyFu connection it does not have, with the same API key as your agent. Write actions ask for your OK by default; switch that off in your dashboard for the tools you choose, for example to schedule pdf seo reports for clients, and the schedule runs on its own. Cotlet runs in the cloud, so it keeps going while your computer is off.

| Where | How to connect | How to schedule |
|---|---|---|
| Your AI agent | Add https://cotlet.dev/mcp/v1 with your API key. | A scheduled agent run, for example a Claude Code routine. |
| n8n | MCP Client node with https://cotlet.dev/mcp/v1, or an HTTP Request node with the endpoint's method and URL, such as GET https://cotlet.dev/api/v1/spyfu/scheduled-reports. | Schedule Trigger node. |
| Make | HTTP module: the endpoint's method and URL with an Authorization: Bearer header, and a JSON body for POST, PUT and PATCH. | Scenario schedule. |
| Zapier | Webhooks by Zapier, Custom Request: the same method, URL, header and body. | Schedule by Zapier trigger. |
| Your own script | GET https://cotlet.dev/api/v1/spyfu/scheduled-reports with your API key. | cron or GitHub Actions. |

## Tools

**For AI agents:** Every endpoint and its schema is public. The 14 endpoints on this page, with parameters and example responses, can be listed without an account. Calling one returns 401 without an API key and 403 while the key has no access to SpyFu.

### get_domain_overview

Domain Overview of one domain: SEO and PPC numbers and the top competitors. Access: read. REST: `GET /api/v1/spyfu/domain-overview`. MCP: `spyfu_read → get_domain_overview`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `domain` | string | yes | Domain without https://, for example trailkick.com. |

Returns what the Domain Overview page shows for one domain: organic keywords, estimated organic clicks, domain strength, paid keywords, the estimated monthly ad budget and the top competitors SpyFu loads. Estimates are SpyFu's, not the site's own numbers. SpyFu does not limit how many domains you search.

Example response:

```json
{
  "domain": "trailkick.com",
  "seo": {
    "keywords": 4180,
    "estimated_clicks": 23400,
    "domain_strength": 41
  },
  "ppc": {
    "keywords": 312,
    "estimated_monthly_ad_budget": 5400
  },
  "top_competitors": [
    "trailrunner-gear.com",
    "sole-supply.com",
    "runbarn.com"
  ]
}
```

### list_seo_keywords

Organic keywords of a domain with rank, previous rank and estimated clicks, optionally one SpyFu segment. Access: read. REST: `GET /api/v1/spyfu/seo-keywords`. MCP: `spyfu_read → list_seo_keywords`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `domain` | string | yes | Domain without https://. |
| `segment` | string | no | One of biggest_rank_gains, biggest_rank_losses, newly_ranked. Leave out for all keywords. |
| `limit` | integer | no | Maximum rows to return. |

Returns rows from SEO Keywords for one domain: the keyword, its current rank, the rank before and the estimated clicks. segment applies one of SpyFu's pre-sorts: biggest_rank_gains, biggest_rank_losses or newly_ranked; without it you get all keywords. SpyFu compares ranks with its previous monthly data, so a change reflects that period and not yesterday.

Example response:

```json
{
  "domain": "trailkick.com",
  "segment": "biggest_rank_gains",
  "keywords": [
    {
      "keyword": "trail running shoes",
      "rank": 6,
      "previous_rank": 14,
      "estimated_clicks": 2100,
      "url": "https://trailkick.com/trail-running-shoes"
    },
    {
      "keyword": "best trail shoes for mud",
      "rank": 9,
      "previous_rank": 17,
      "estimated_clicks": 640,
      "url": "https://trailkick.com/guides/mud-shoes"
    }
  ]
}
```

### list_competitors

Top SEO or PPC competitors of a domain, ranked by shared keywords. Access: read. REST: `GET /api/v1/spyfu/competitors`. MCP: `spyfu_read → list_competitors`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `domain` | string | yes | Domain without https://. |
| `type` | string | no | seo or ppc. Defaults to seo. |

Returns the competitors SpyFu finds for one domain, with the number of keywords they share. type seo ranks them by organic keywords in common, ppc by paid keywords in common. Pass the first domains of the result to compare_competitor_keywords.

Example response:

```json
{
  "domain": "trailkick.com",
  "type": "seo",
  "competitors": [
    {
      "domain": "trailrunner-gear.com",
      "shared_keywords": 1840
    },
    {
      "domain": "sole-supply.com",
      "shared_keywords": 1522
    },
    {
      "domain": "runbarn.com",
      "shared_keywords": 1207
    }
  ]
}
```

### compare_competitor_keywords

Kombat: keywords shared by two or more domains, in one SpyFu segment. Access: read. REST: `GET /api/v1/spyfu/competitor-keywords/compare`. MCP: `spyfu_read → compare_competitor_keywords`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `domains` | string | yes | Comma-separated domains, two or more, your own domain first. |
| `type` | string | no | seo or ppc. Defaults to seo. |
| `segment` | string | no | One of all_keywords, core_keywords, consider_buying, missing_keywords, possible_ad_waste. Defaults to core_keywords. |
| `limit` | integer | no | Maximum rows to return. |

Runs SpyFu's Kombat for two or more domains and returns one segment of the keywords. all_keywords is every keyword any domain ranks for or buys, core_keywords the ones all of them share, and consider_buying (ppc), missing_keywords (seo) and possible_ad_waste show gaps against your own domain. Put your own domain first for the last three; SpyFu advises starting a Kombat search with your own domain. Adding more domains shrinks core_keywords.

Example response:

```json
{
  "domains": [
    "trailkick.com",
    "trailrunner-gear.com",
    "sole-supply.com"
  ],
  "type": "seo",
  "segment": "missing_keywords",
  "keywords": [
    {
      "keyword": "waterproof trail shoes",
      "ranked_by": [
        "trailrunner-gear.com",
        "sole-supply.com"
      ]
    },
    {
      "keyword": "trail shoes vs road shoes",
      "ranked_by": [
        "trailrunner-gear.com",
        "sole-supply.com"
      ]
    }
  ]
}
```

### get_ad_history

Google ad copy a domain or keyword has used over time. Access: read. REST: `GET /api/v1/spyfu/ad-history`. MCP: `spyfu_read → get_ad_history`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `domain` | string | no | Domain without https://. Give this or keyword. |
| `keyword` | string | no | Keyword to look up. Give this or domain. |

Returns the ad variations SpyFu recorded, as shown on its Ad History pages. Give a domain to see how one advertiser changed its ads, or a keyword to see which advertisers ran ads for it. Each row has the month, headline lines and description.

Example response:

```json
{
  "domain": "trailrunner-gear.com",
  "ads": [
    {
      "month": "2026-09",
      "keyword": "trail running shoes",
      "headline": "Trail Running Shoes | Free Returns",
      "description": "Grip for mud and rock. Shop new arrivals."
    },
    {
      "month": "2026-06",
      "keyword": "trail running shoes",
      "headline": "Trail Shoes Built for Mud",
      "description": "Free shipping over a set amount. Shop now."
    }
  ]
}
```

### list_backlinks

Pages that link to sites ranking for a keyword, or the links a domain gets, with SpyFu's metrics. Access: read. REST: `GET /api/v1/spyfu/backlinks`. MCP: `spyfu_read → list_backlinks`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `keyword` | string | no | Keyword you want to rank for. Give this or domain. |
| `domain` | string | no | Competitor domain whose links you want to see. Give this or keyword. |
| `content_type` | string | no | Content type as named in SpyFu's filter, for example Blogs or Forums. |
| `exclude_domains` | string | no | Comma-separated domains to leave out, including your own. |

Runs SpyFu's Backlinks search for a keyword or a domain. A keyword returns URLs that link to sites ranking for it, a domain returns the links that domain gets. Each row has the URL, monthly organic clicks, domain strength (100 is the strongest), ranked keywords of the page and its outbound links. content_type and exclude_domains are applied by SpyFu. SpyFu shows only pages Google has indexed within the top 100 results, without duplicates, so the list is for discovery and not an audit of your own links.

Example response:

```json
{
  "keyword": "trail running shoes",
  "content_type": "Forums",
  "backlinks": [
    {
      "url": "https://trailrunnerforum.example/gear-threads",
      "domain": "trailrunnerforum.example",
      "organic_clicks": 8400,
      "domain_strength": 52,
      "ranked_keywords": 310,
      "outbound_links": 11
    },
    {
      "url": "https://shoe-lab.example/forum/best-trail-shoes",
      "domain": "shoe-lab.example",
      "organic_clicks": 3100,
      "domain_strength": 47,
      "ranked_keywords": 96,
      "outbound_links": 22
    }
  ]
}
```

### search_business_leads

SpyFu Business Leads by niche, location and contact type, with ad budget and SEO click estimates. Access: read. REST: `GET /api/v1/spyfu/business-leads/search`. MCP: `spyfu_read → search_business_leads`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `keyword` | string | yes | Niche keyword, for example shoe store. |
| `exclude_keywords` | string | no | Comma-separated keywords to leave out. |
| `industry` | string | no | Industry as named in SpyFu's filter. |
| `location` | string | no | Place to narrow the leads to, for example Arizona. |
| `contact_type` | string | no | Comma-separated contact types a lead must have, for example email, phone. |
| `technology` | string | no | Technology the lead's site uses, for example a shopping cart. |

Runs the Business Leads search from the List Builder. Each lead has its domain, SpyFu's estimated monthly ad budget, its predicted SEO clicks and the contact types SpyFu has: email, phone or social accounts. Contact details themselves come only with SpyFu's export, which has a monthly cap per plan; this tool does not export, so it does not use that cap.

Example response:

```json
{
  "keyword": "shoe store",
  "location": "Arizona",
  "total": 64,
  "leads": [
    {
      "domain": "desertsole.example",
      "estimated_monthly_ad_budget": 3200,
      "estimated_seo_clicks": 410,
      "contacts": [
        "email",
        "phone",
        "twitter"
      ]
    },
    {
      "domain": "cactus-kicks.example",
      "estimated_monthly_ad_budget": 1800,
      "estimated_seo_clicks": 150,
      "contacts": [
        "email",
        "phone"
      ]
    }
  ]
}
```

### list_my_sites

Sites in your My Sites projects with their latest daily snapshot. Access: read. REST: `GET /api/v1/spyfu/my-sites`. MCP: `spyfu_read → list_my_sites`.

No parameters.

Returns the sites you track under Projects > My Sites, each with its latest daily snapshot: organic keyword count, estimated clicks, average keyword position and domain strength. SpyFu limits how many sites each plan can track, so the list is as long as your plan allows.

Example response:

```json
{
  "sites": [
    {
      "domain": "trailkick.com",
      "keywords": 4180,
      "estimated_clicks": 23400,
      "average_position": 18.4,
      "domain_strength": 41,
      "added": "2026-10-02"
    },
    {
      "domain": "client-bakery.com",
      "keywords": 930,
      "estimated_clicks": 5200,
      "average_position": 22.1,
      "domain_strength": 28,
      "added": "2026-10-09"
    },
    {
      "domain": "example-florist.com",
      "keywords": 610,
      "estimated_clicks": 2100,
      "average_position": 25.7,
      "domain_strength": 19,
      "added": "2026-10-16"
    }
  ]
}
```

### get_my_site

One My Sites project: snapshot, recent rankings and top pages with their keywords. Access: read. REST: `GET /api/v1/spyfu/my-site`. MCP: `spyfu_read → get_my_site`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `domain` | string | yes | Tracked domain without https://. |

Returns the page of one tracked site: the latest daily snapshot, recent rankings with their change, and the top pages that drive the most organic traffic, each with the keywords it ranks for. The site must be in My Sites; add it first with add_my_site. History builds up from the day the site was added.

Example response:

```json
{
  "domain": "client-bakery.com",
  "snapshot": {
    "date": "2026-10-23",
    "keywords": 930,
    "estimated_clicks": 5200,
    "average_position": 22.1,
    "domain_strength": 28
  },
  "recent_rankings": [
    {
      "keyword": "sourdough bakery near me",
      "rank": 4,
      "change": 3
    },
    {
      "keyword": "custom birthday cakes",
      "rank": 11,
      "change": -2
    }
  ],
  "top_pages": [
    {
      "url": "https://client-bakery.com/cakes",
      "estimated_clicks": 1900,
      "keywords": [
        "custom birthday cakes",
        "cake shop near me"
      ]
    }
  ]
}
```

### get_site_audit

Latest Site Audit of a site: health score, error counts and the issue list with the kind of fix each needs. Access: read. REST: `GET /api/v1/spyfu/site-audit`. MCP: `spyfu_read → get_site_audit`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `domain` | string | yes | Audited domain without https://. |

Returns the last finished crawl of one audited site: the Site Health Score (0 to 100), the counts of errors, warnings and notices, any site-level findings SpyFu shows as red banners and the named issues. Each issue has its severity and the action it needs: auto_fixable, review, developer_fix or monitor. The score updates after each completed crawl, not continuously, and this tool does not start a crawl. The site must already be set up in Site Audit.

Example response:

```json
{
  "domain": "trailkick.com",
  "last_crawl": "2026-10-21",
  "health_score": 86,
  "counts": {
    "errors": 3,
    "warnings": 41,
    "notices": 120
  },
  "site_level_findings": [],
  "issues": [
    {
      "name": "Meta description is too long",
      "severity": "warning",
      "action": "auto_fixable",
      "pages": 18
    },
    {
      "name": "Broken internal link",
      "severity": "error",
      "action": "review",
      "pages": 3
    }
  ]
}
```

### list_scheduled_reports

Recurring PDF reports from Account Settings > Scheduled PDF Reports, with recipients and schedule. Access: read. REST: `GET /api/v1/spyfu/scheduled-reports`. MCP: `spyfu_read → list_scheduled_reports`.

No parameters.

Returns every scheduled PDF report of your account: the page it is made from, the domain or keyword, the recipients, the schedule and whether it is on. Use it before create_scheduled_report so the same report is not set up twice.

Example response:

```json
{
  "reports": [
    {
      "report_id": "rep_81b2d4",
      "page": "Domain Overview",
      "subject": "client-bakery.com",
      "recipients": [
        "owner@client-bakery.example"
      ],
      "schedule": "Monthly",
      "active": true
    },
    {
      "report_id": "rep_9c07ee",
      "page": "Ranking History",
      "subject": "example-florist.com",
      "recipients": [
        "anna@example-florist.example"
      ],
      "schedule": "Monthly",
      "active": false
    }
  ]
}
```

### create_scheduled_report

Set up a recurring PDF report from a SpyFu page, emailed to the recipients you name. Access: write, asks the user first. REST: `POST /api/v1/spyfu/scheduled-reports`. MCP: `spyfu_write → create_scheduled_report`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `page` | string | yes | Page the report is made from, as SpyFu names it, for example Domain Overview, SEO Keywords, Ranking History, Ad History. |
| `subject` | string | yes | Domain or keyword the report is about. |
| `recipients` | string | yes | Comma-separated email addresses. |
| `schedule` | string | yes | Label of an option in the report dialog, for example Monthly. |
| `title` | string | no | Title for the front page of the PDF. |
| `exclude_sections` | string | no | Comma-separated section names to leave out of the PDF. |

Does what Create Report with the email and schedule options does: builds the report from one SpyFu page for a domain or keyword and sets up recurring emails to the recipients. It includes every section of the page unless you list some in exclude_sections. schedule is the label of an option in SpyFu's report dialog. A custom title is a white label feature that SpyFu limits to certain plans. The PDF goes to people outside your account. By default you confirm each call; you can switch that off for this tool.

Example response:

```json
{
  "report_id": "rep_3f9a1c",
  "page": "Domain Overview",
  "subject": "trailkick.com",
  "recipients": [
    "maria@trailkick.com"
  ],
  "schedule": "Monthly",
  "status": "scheduled"
}
```

### add_my_site

Start tracking a domain under Projects > My Sites. Access: write. REST: `POST /api/v1/spyfu/my-sites`. MCP: `spyfu_write → add_my_site`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `domain` | string | yes | Domain without https://. |

Adds one domain to My Sites, where SpyFu records daily snapshots of its keywords, estimated clicks and average position. It reaches nobody and remove_my_site undoes it, so it does not wait for your OK. SpyFu limits how many sites each plan can track; past that limit the call fails with SpyFu's message. History starts on the day you add the site.

Example response:

```json
{
  "domain": "client-bakery.com",
  "status": "tracking",
  "added": "2026-10-23"
}
```

### remove_my_site

Delete a site from your My Sites projects. Access: write, asks the user first. REST: `DELETE /api/v1/spyfu/my-sites`. MCP: `spyfu_write → remove_my_site`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `domain` | string | yes | Tracked domain without https://. |

Deletes one site from Projects > My Sites, as the site options menu does. The site stops being tracked. It reaches no one, but it takes the site out of your projects, so each call waits for your OK. By default you confirm each call; you can switch that off for this tool.

Example response:

```json
{
  "domain": "example-florist.com",
  "status": "removed"
}
```

## How do I connect SpyFu to Claude Code, Codex or Cursor?

Connecting SpyFu takes three steps: sign up, sign in to SpyFu once in your Cloud Browser and enable it for agents, then add one MCP server or call the REST API with the same key.

### Connect SpyFu to your agent.

1. **Create an account** Sign up and add SpyFu in the console. Your API key is there too.

2. **Sign in to SpyFu in your Cloud Browser** Open your Cloud Browser in the console: your own Chrome in the cloud. Sign in to SpyFu there yourself, the way you always do, then press Enable for agents, read only or read and write. We never save your password, and your agent keeps working even when your computer is off.

3. **Add Cotlet to your agent** Paste the snippet for your client. The same server and key serve every app you connect, so you do this once.

   Claude Code:

```
claude mcp add --transport http cotlet \
  https://cotlet.dev/mcp/v1 \
  --header "Authorization: Bearer $COTLET_API_KEY"
```

   Cursor:

```
{
  "mcpServers": {
    "cotlet": {
      "url": "https://cotlet.dev/mcp/v1",
      "headers": {
        "Authorization": "Bearer ${COTLET_API_KEY}"
      }
    }
  }
}
```

   Codex:

```
# ~/.codex/config.toml
[mcp_servers.cotlet]
url = "https://cotlet.dev/mcp/v1"
bearer_token_env_var = "COTLET_API_KEY"
```

4. **Ask your agent** Ask in plain words. Your agent finds the SpyFu tools on the server and calls them for you; anything that reaches other people waits for your OK unless you switch that off for a tool.

```
Set up a monthly Domain Overview PDF report for each client domain in my list, email it to the contact I named for that client, and skip any client who already gets one.
```

### Call SpyFu from your scripts.

1. **Export your API key** Your scripts use the same API key as your agent. Keep it in an environment variable, never in your code.

```
export COTLET_API_KEY="cotlet_..."
```

2. **Call a tool** Every tool is an endpoint under /api/v1/spyfu with its own method and path, listed with the endpoints above. Path parameters go in the URL; the other parameters go in the query for GET and DELETE and in a JSON body otherwise.

```
curl -X POST https://cotlet.dev/api/v1/spyfu/scheduled-reports \
  -H "Authorization: Bearer $COTLET_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"page":"Domain Overview","subject":"trailkick.com","recipients":"maria@trailkick.com","schedule":"Monthly","title":"Trailkick monthly SEO recap"}'
```

3. **Read the result** You get plain JSON back, ready for your script. A failed call costs nothing.

```
{
  "report_id": "rep_3f9a1c",
  "page": "Domain Overview",
  "subject": "trailkick.com",
  "recipients": [
    "maria@trailkick.com"
  ],
  "schedule": "Monthly",
  "status": "scheduled"
}
```

## Why use Cotlet for SpyFu?

**Built for agents**

- One MCP server for every app you connect.
- The same tools as a REST API for scripts and cron jobs.
- Works with Claude Code, Codex and Cursor.

**Your login stays yours**

- You sign in to SpyFu yourself, in your own Cloud Browser. We never save your password; the profile is encrypted with AES-256-GCM, the cipher 1Password uses.
- A+ on Qualys SSL Labs, securityheaders.com and Mozilla Observatory.
- The model never sees a login.
- No stored passwords, no CAPTCHA solving, no MFA bypass.

**You stay in control**

- Scope each API key: its apps, its tools, read only or read and write.
- Anything that reaches other people waits for your OK, so a leaked key cannot post or message as you.
- Every background request listed in your Background activity. Disable for agents in one click.

**Kept working for you**

- We test every integration every 6 hours.
- When SpyFu changes, the tool pauses until we fix it.
- Failed calls cost nothing.

## Is it safe to connect SpyFu to Cotlet?

Yes. You sign in to SpyFu yourself, in your own Cloud Browser, and we never save your password. Your agents only get SpyFu once you enable it, and every background request is listed. The browser profile is stored encrypted with AES-256-GCM, the same cipher 1Password uses for its vaults and Apple for iCloud Keychain. Independent public scanners grade cotlet.dev A+ and find it clean; click a result to rerun it yourself.

- **A+ on Qualys SSL Labs**: Encryption in transit: TLS setup and certificates, on all four server addresses. [Live result](https://www.ssllabs.com/ssltest/analyze.html?d=cotlet.dev)
- **A+ on securityheaders.com**: Browser protections sent with every page, all six headers present. [Live result](https://securityheaders.com/?q=cotlet.dev&followRedirects=on)
- **A+ on Mozilla Observatory**: Mozilla's web security baseline: score 120 of 100, 12 of 12 tests passed. [Live result](https://developer.mozilla.org/en-US/observatory/analyze?host=cotlet.dev)
- **Clean on Sucuri SiteCheck**: No malware, spam or defacement, and not on any of 9 blocklists, Google Safe Browsing included. [Live result](https://sitecheck.sucuri.net/results/cotlet.dev)

[How Cotlet protects your access](https://cotlet.dev/security.md)

### Common concerns

**Who runs Cotlet?**

Cotlet is run by Take Group, a Polish software company working since 2019. Take Group runs about 3,200 websites on its own systems and has its own DevOps team for infrastructure security. We built and used integrations like this inside the company for years before opening them as Cotlet.

**Is this an official SpyFu integration?**

No, Cotlet is independent of SpyFu. SpyFu's own API is too limited for this work. Cotlet works through your own SpyFu account, the way you use SpyFu in the browser, so you need no partner approval and no developer setup.

**What about client data and GDPR?**

Cotlet is run from the EU and follows the GDPR. Cloud Browsers run in Finland, a Tier 1 country in the ITU Global Cybersecurity Index 2024. Data passes through a call and is not kept after it.

**Can I start with read only?**

Yes. Enable the app for agents as read only, or make the API key read only, and anything that reaches other people waits for your OK unless you switch that off per tool.

**Is it reliable?**

Every Cotlet service is checked every 3 minutes from Europe, North America, Asia and Australia. The live results and any outage are public at status.cotlet.dev.

**How do I stop?**

Press Disable for agents next to SpyFu in your console: your agents lose access at once and you stay signed in. Signing out of SpyFu in the browser works too, and Reset browser deletes the whole profile.

## Is there a SpyFu MCP server on GitHub?

Yes. Community SpyFu MCP servers exist on GitHub, usually maintained by one person. You install one on your own computer, sign it in, and keep it running yourself; when SpyFu changes, it stops working until you or the maintainer fix it. Cotlet hosts the same kind of server for you, works in your own SpyFu account, and our team keeps it working.

|  | GitHub MCP server | Cotlet |
|---|---|---|
| Setup | Clone the repo, install it, add your SpyFu login or key, add it to each MCP client | Sign up, sign in to SpyFu once, add one MCP server or API key |
| When SpyFu changes | It breaks until you or the maintainer fix it | Our team tests it daily and fixes it for you; failed calls are free |
| Your SpyFu session | In a file on your computer, readable by any program you run | In your own Cloud Browser in the EU, profile encrypted, only for the apps you enable, disabled for agents in one click |
| When the session expires | Tools fail until you sign in again by hand | Your Cloud Browser keeps you signed in; if SpyFu logs you out, your agent gets a link to sign in again |
| Upkeep | You update, monitor and debug it yourself | Nothing to host or update |
| Where it runs | Your computer, while it is on | Hosted: Claude Code, Codex, Cursor, n8n and scripts, also on a schedule |
| Price | Free, paid for with your time | Free 7-day trial, then pay-as-you-go credit packs, no subscription |

### Which one fits you

**Pick Cotlet if**

- you are not a developer, or you do not want to maintain a server
- you need it to keep working when SpyFu changes, without checking it yourself
- your agent or a script should run it on a schedule, also while your computer is off

**Pick an open-source server if**

- you are comfortable installing, updating and fixing it yourself
- you want your sign-in to stay on your own computer
- you only need it now and then, from one MCP client

## How much does the SpyFu API cost?

Free 7-day trial with 2,000 credits, no card needed. After that, the SpyFu API is pay as you go with no limit on apps: Credit packs from $29 for 5,000 credits, one-time, no subscription. A successful call uses 10 credits (about $0.04 to $0.06), your Cloud Browser uses 50 credits a day while it has an app enabled for agents, however many apps that is, and an agent driving the browser itself uses 5 credits a minute. Credit packs stay valid for 12 months and stack, so unused credits carry over.

| Credits | Price, one time | Calls at 10 credits | Per 1,000 credits |
|---|---|---|---|
| 5,000 | $29 | 500 | $5.80 |
| 15,000 | $79 | 1,500 | $5.27 |
| 32,000 | $149 | 3,200 | $4.66 |
| 60,000 | $249 | 6,000 | $4.15 |

Only successful calls use credits; failed calls and timeouts cost nothing. At a balance of 0 calls pause, never a surprise charge. Authenticate with the `Authorization: Bearer` header. [See full pricing](https://cotlet.dev/pricing.md)

## How Cotlet holds your access

Cotlet hosts MCP servers and REST APIs for apps with no usable API. Your agent works in your own SpyFu account.

- **Company details:** Cotlet is run by Take Group sp. z o.o., a company registered in Poland. Its full address and registration numbers are in the Terms of service. [Terms of service](https://cotlet.dev/terms)
- **Your sign-in:** You sign in to SpyFu yourself, in your own Cloud Browser: a Chrome we run for you in the EU, one per app. We never save your password (password saving is off), the profile is stored encrypted with AES-256-GCM, and your agents get SpyFu only after you enable it. When SpyFu signs you out, your agent gives you a link to sign in again. [Security](https://cotlet.dev/security.md)
- **Revoking access:** Press Disable for agents next to SpyFu, sign out of SpyFu in your Cloud Browser, or reset the browser. Every background request is listed in your Background activity. Actions that reach other people wait for your OK unless you switch that off per tool.
- **What we never do:** Store passwords, solve CAPTCHAs or bypass MFA.
- **SpyFu's terms:** You use your own SpyFu account and stay responsible for following SpyFu's terms. Cotlet is independent and not affiliated with SpyFu. [Terms](https://cotlet.dev/terms)
- **Contact:** Questions about the company, security or an app: [contact@cotlet.dev](mailto:contact@cotlet.dev)

## Frequently asked questions

**How do I get access?**

Sign up free, open SpyFu in the console and press Request access. Then you create your API key and connect SpyFu there.

**Do I need to be technical?**

No. You sign in to SpyFu once in your Cloud Browser, a normal Chrome you open from the console, and paste one command into your agent, or one URL into n8n. Your agent can walk you through it. There is no server to install, update or fix.

**Is it safe to connect SpyFu to Cotlet?**

Yes. You sign in to SpyFu yourself, in your own Cloud Browser in the EU, and we never save your password. Your agents only get SpyFu once you enable it, every background request is listed, and the browser profile is stored encrypted with AES-256-GCM, the cipher 1Password uses for its vaults. The AI model never sees a login, posts and messages wait for your OK, and Disable for agents cuts access in one click. Independent scanners grade cotlet.dev A+ on Qualys SSL Labs, securityheaders.com and Mozilla Observatory; live results are on https://cotlet.dev/security.

**Is a hosted server safer than a local one? My SpyFu sign-in would leave my computer.**

On Cotlet you sign in inside your own Cloud Browser, which only you open, and its profile is stored encrypted with AES-256-GCM in the EU. Agents get only the apps you enable, and every background request is listed. A local server keeps your SpyFu cookie in a plain file on your computer, readable by any program you run, and stops when your computer is off.

**Why does Cotlet send requests instead of clicking in my browser?**

To be fast, Cotlet doesn't click through SpyFu's pages. It sends the same requests your browser would, from your browser's IP with its cookies, without opening a window. SpyFu sees the same browser and IP you signed in with, and every request is listed in your Background activity.

**What if someone gets my Cotlet API key?**

The key holds no SpyFu login or cookies, it only asks Cotlet to run a tool. It can call only the apps and tools you gave it, and a read-only key changes nothing. Anything that reaches other people, like posts, comments or messages, waits for your OK in the dashboard by default, so a leaked key cannot post or message as you. When you switch approval off for a scheduled job, give that job its own key limited to that one tool. Every call is in your activity log, and deleting the key ends access at once.

**Why a signed-in browser and not OAuth, like other integration platforms?**

SpyFu offers no OAuth token you can simply grant for these tools: its official API leaves them out or needs a developer app, a plan or an approval first (see the official API section above). That is why Cotlet sets the limits itself: per key, per tool, with your approval before anything reaches other people. Cotlet is run by Take Group sp. z o.o., an EU company (VAT PL6342984273).

**Does Cotlet use my SpyFu API key or API credit?**

No. Cotlet works in your own SpyFu account through the web app, so nothing is billed per row. SpyFu bills its API per row returned, with a monthly API credit that depends on the plan, and it does not apply to anything outside the API (checked 23 Oct 2026).

**Which SpyFu plan do I need?**

The plan you already have decides what works. SpyFu limits how many sites My Sites tracks, caps leads exports each month and may limit white-label report titles to certain plans. A tool that your plan does not allow returns SpyFu's own refusal, not an empty result.

**Can my agent post or send messages in SpyFu without asking me?**

No. Every call to create_scheduled_report or remove_my_site waits for your OK by default. For scheduled automations you can switch confirmation off per tool in your dashboard, for example only for approvals. add_my_site runs without asking, because it sends nothing to anyone and one call undoes it.

**Can I use the SpyFu API in n8n?**

Yes. Add https://cotlet.dev/mcp/v1 with your API key in n8n's MCP Client node, or call its endpoints under https://cotlet.dev/api/v1/spyfu from the HTTP Request node.

---

Give your AI agents your signed-in browser.

**Product:** [Integrations](https://cotlet.dev/integrations.md) · [Use cases](https://cotlet.dev/use-cases.md) · [How it works](https://cotlet.dev/how-it-works.md) · [Pricing](https://cotlet.dev/pricing.md) · [Security](https://cotlet.dev/security.md)

**Resources:** [Blog](https://cotlet.dev/blog.md) · [API docs](https://cotlet.dev/docs.md) · [Help center](https://cotlet.dev/help.md) · [Changelog](https://cotlet.dev/changelog.md) · [GitHub](https://github.com/cotletdev/cotlet)

**Solutions:** [For developers](https://cotlet.dev/for-developers.md) · [For automation agencies](https://cotlet.dev/for-agencies.md)

**Company:** [About](https://cotlet.dev/about.md) · [AI info: company facts](https://cotlet.dev/ai-info.md) · [Contact](https://cotlet.dev/contact.md)

**Legal:** [Terms of service](https://cotlet.dev/terms) · [Privacy policy](https://cotlet.dev/privacy) · [Refund policy](https://cotlet.dev/refunds) · [Acceptable use](https://cotlet.dev/acceptable-use) · [Cookie policy](https://cotlet.dev/cookies) · [DPA](https://cotlet.dev/dpa) · [Subprocessors](https://cotlet.dev/subprocessors)

**Elsewhere:** [Status page](https://status.cotlet.dev) · [Cotlet on GitHub](https://github.com/cotletdev) · [Cotlet on X](https://x.com/cotletdev) · [Cotlet on LinkedIn](https://www.linkedin.com/company/cotletdev) · [Cotlet on Product Hunt](https://www.producthunt.com/products/cotlet) · [Cotlet on Crunchbase](https://www.crunchbase.com/organization/cotlet) · [Cotlet on SaaSHub](https://www.saashub.com/cotlet)

Cotlet.dev is built by Bart Krawczyk and Jake Slugocki, the founders of Take Group sp. z o.o., ul. Wincentego Janasa 4, 40-855 Katowice, Poland. KRS 0000871398, NIP 6342984273, VAT EU: PL6342984273. [About us](https://cotlet.dev/about.md)

Cotlet is an independent service. It is not affiliated with, endorsed by or sponsored by any of the products listed on this site. Product names are trademarks of their respective owners.