# Deeplead (remote · www.deeplead.io)

Find local businesses, companies and decision makers with verified emails for B2B outreach.

- Trust score: 79/100 (medium)
- Change this week: +40
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-03

## Components

- remote · `www.deeplead.io`: 79/100 (this document), [markdown](https://verifymcp.io/servers/io-deeplead-deeplead/api-mcp.md), [page](https://verifymcp.io/servers/io-deeplead-deeplead/api-mcp)

## Channel facts

- Endpoint: `https://www.deeplead.io/api/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.1.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-03.

- **Endpoint Security**: 97/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation is enforced on tool calls, advertised via RFC 9728 protected-resource metadata. Discovery is public, which costs nothing: no tool can be invoked without a token.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
  - The authorisation server supports Client ID Metadata Documents, the current MCP client-registration mechanism.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 68/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1996 tokens (~153/item across 13 items; 13 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability check failed: schema churn in the 8 days we've observed: 3 tool removals, 1 breaking changes, 0 auth/transport breaks, 7 additions.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 13 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 13 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the Deeplead MCP server?

Deeplead is a hosted endpoint at https://www.deeplead.io/api/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http io-deeplead-deeplead 'https://www.deeplead.io/api/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "io-deeplead-deeplead": {
      "url": "https://www.deeplead.io/api/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "io-deeplead-deeplead": {
      "type": "http",
      "url": "https://www.deeplead.io/api/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.io-deeplead-deeplead]
url = "https://www.deeplead.io/api/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "io-deeplead-deeplead": {
      "type": "remote",
      "url": "https://www.deeplead.io/api/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add io-deeplead-deeplead --url 'https://www.deeplead.io/api/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  io-deeplead-deeplead:
    url: "https://www.deeplead.io/api/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "io-deeplead-deeplead": {
      "Transport": "http",
      "Url": "https://www.deeplead.io/api/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add io-deeplead-deeplead -t streamable-http -u 'https://www.deeplead.io/api/mcp'
```

### Other

```json
{
  "mcpServers": {
    "io-deeplead-deeplead": {
      "type": "http",
      "url": "https://www.deeplead.io/api/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-03 (score 79, +1)

- [security] Tool “businesses_search” rewrote its description, which is the text the model reads
- [security] Tool “organizations_enrich” rewrote its description, which is the text the model reads
- [security] Tool “organizations_find_decision_maker” rewrote its description, which is the text the model reads
- [security] Tool “organizations_search” rewrote its description, which is the text the model reads
- [security] Tool “persons_find_email” rewrote its description, which is the text the model reads
- [security] Tool “persons_find_phone” rewrote its description, which is the text the model reads
- [security] Tool “persons_lookup” rewrote its description, which is the text the model reads
- [security] Tool “persons_search” rewrote its description, which is the text the model reads
- [functional improvement] Schema quality: 171 → 153
- [functional] New tool “deliverability_create_test”
- [functional] New tool “deliverability_get_test”
- [cosmetic] “persons_search” reworded the description of “organizationIds”

### 2026-09-28 (score 78, 0)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-09-27 (score 78, +39)

- [security regression] Stability: unverified → fail
- [security regression] Tool “organizations_findDecisionMaker” was removed
- [security regression] Tool “persons_save” was removed
- [security regression] Tool “search_parse” was removed
- [security improvement] Transport: unverified → pass
- [security improvement] Injection markers: unverified → pass
- [security] Authorization: Authorisation is enforced on tool calls, advertised via RFC 9728 protected-resource metadata. Discovery is public, which costs nothing: no tool can be invoked without a token.
- [security] Tool “businesses_search” rewrote its description, which is the text the model reads
- [security] Tool “organizations_search” rewrote its description, which is the text the model reads
- [security] Tool “persons_search” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 1551 → 1889
- [functional improvement] Endpoint reachability: behind authorisation → reachable
- [functional improvement] Tool coverage: 57% → 100%
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] Tool “businesses_search” now declares an output schema
- [functional improvement] Tool “contacts_create” now declares an output schema
- [functional improvement] Tool “contacts_list” now declares an output schema
- [functional improvement] Tool “credits_get” now declares an output schema
- [functional improvement] Tool “organizations_search” now declares an output schema
- [functional improvement] Tool “persons_search” now declares an output schema
- [functional] First check of Tool coverage: 100
- [functional] Server version: 1.0.0 → 1.1.1
- [functional] New tool “organizations_enrich”
- [functional] New tool “organizations_find_decision_maker”
- [functional] New tool “persons_find_email”
- [functional] New tool “persons_find_phone”
- [functional] New tool “persons_lookup”
- [cosmetic] “businesses_search” added an optional parameter “saveToContacts”
- [cosmetic] “organizations_search” added an optional parameter “hqCity”
- [cosmetic] “persons_search” added an optional parameter “onePerOrganization”
- [cosmetic] “persons_search” added an optional parameter “saveToContacts”
- [cosmetic] “businesses_search” reworded the description of “excludedNiches”
- [cosmetic] “businesses_search” reworded the description of “page”
- [cosmetic] “businesses_search” reworded the description of “rating”
- [cosmetic] “businesses_search” reworded the description of “reviews”
- [cosmetic] “contacts_create” reworded the description of “contacts”
- [cosmetic] “contacts_list” reworded the description of “limit”
- [cosmetic] “organizations_search” reworded the description of “foundedAfter”
- [cosmetic] “organizations_search” reworded the description of “foundedBefore”
- [cosmetic] “organizations_search” reworded the description of “includeWithoutWebsite”
- [cosmetic] “organizations_search” reworded the description of “limit”
- [cosmetic] “organizations_search” reworded the description of “offset”
- [cosmetic] “organizations_search” reworded the description of “revenueRange”
- [cosmetic] “organizations_search” reworded the description of “technologies”
- [cosmetic] “persons_search” reworded the description of “foundedAfter”
- [cosmetic] “persons_search” reworded the description of “foundedBefore”
- [cosmetic] “persons_search” reworded the description of “jobLevel”
- [cosmetic] “persons_search” reworded the description of “jobTitleExclude”
- [cosmetic] “persons_search” reworded the description of “limit”
- [cosmetic] “persons_search” reworded the description of “offset”
- [cosmetic] “persons_search” reworded the description of “personCity”
- [cosmetic] “persons_search” reworded the description of “personState”
- [cosmetic] “persons_search” reworded the description of “revenueRange”
- [cosmetic] “persons_search” reworded the description of “technologies”
- [cosmetic] Tool “persons_search” changed its title: Search persons → Search persons with their emails and phones

### 2026-09-26 (score 39, −31)

- [security regression] Endpoint reachability: reachable → behind authorisation
- [security regression] Tool safety: pass → unverified
- [security regression] Transport: pass → unverified
- [security improvement] Authorization: partial → pass
- [security] First check of Authorization: pass
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional improvement] Stability: unverified → 0.03
- [functional] First check of Schema quality: unverified

### 2026-09-25 (score 70)

First indexed and scored.

## MCP tools (13)

### `businesses_search` (~250 tokens)

Search local businesses from Google Business Profiles

Search local businesses from Google Business Profiles. 23M+ businesses with ratings, reviews, website contacts, socials and ad pixels. 30 per page. Charges 1 credit per business with an email or phone and 0.5 per business without. saveToContacts also stores them in your contacts.

Input parameters:

- `categories` (array, required): Google business categories, e.g. ["Dentist"]
- `excludedCategories` (array): Google business categories to exclude
- `keyword` (string): Matched against the business name and categories
- `location` (string, required): A city ("Austin, TX"), a US state ("Texas") or a country ("Germany")
- `page` (integer): Page number, starting at 1; up to 30 businesses per page
- `radiusMiles` (number): Around a city; default 30
- `rating` (string): Google rating band to match
- `require` (object): e.g. { "email": true, "metaAds": false }; false matches only businesses checked and found without it
- `reviews` (string): Google review-count band to match
- `saveToContacts` (boolean): Save returned businesses to your Deeplead contacts

Output parameters:

- `businesses` (array)
- `chargedCredits` (number)

### `organizations_search` (~382 tokens)

Search organizations, or look them up by domain

Search organizations, or look them up by domain. Charges 0.5 credits per returned organization. limit 0 returns only totalCount, free.

Input parameters:

- `domains` (array): Look companies up by domain, e.g. ["stripe.com"]
- `employeeBands` (array): Headcount bands
- `employeeGrowthMin` (integer): Minimum employee growth on LinkedIn in percent, e.g. 10; known for about 1 in 13 US companies
- `foundedAfter` (integer): Earliest founding year to include
- `foundedBefore` (integer): Latest founding year to include
- `fundedAfter` (integer): Year of the last funding round, at least; known for about 1 in 100 US companies
- `hqCity` (array): City names of the headquarters, e.g. ["Austin"]
- `hqCountry` (array): ISO alpha-2 country codes of the headquarters, e.g. ["US", "DE"]
- `hqState` (array): US state names or codes of the headquarters
- `includeWithoutWebsite` (boolean): Include companies without websites in search results
- `industryNaicsDirect` (array): NAICS codes
- `limit` (integer): Maximum companies to return; 0 returns only a free count
- `monthlyVisitsMin` (integer): Minimum monthly website visits; known for about 1 in 8 US companies, the rest are excluded
- `offset` (integer): Number of matching companies to skip for pagination
- `query` (string): Free text matched against company name, description and keywords
- `revenueRange` (array): Annual company revenue bands
- `semantic` (string): What the company is and sells, matched by meaning, e.g. "outsourced medical billing for clinics"
- `technologies` (array): Technologies used by the company

Output parameters:

- `chargedCredits` (number)
- `organizations` (array)
- `totalCount` (number)

### `organizations_enrich` (~60 tokens)

Enrich a company from its domain

Enrich a company from its domain. Returns the company's firmographics, socials and website data. Charges 0.5 credits only when the company is found.

Input parameters:

- `domain` (string, required): Company domain or website URL, e.g. "stripe.com"

Output parameters:

- `chargedCredits` (number)
- `found` (boolean)
- `organization`

### `organizations_find_decision_maker` (~58 tokens)

Find the decision maker of an organization with a verified email

Find the decision maker of an organization with a verified email. Charges 2 credits only when a decision maker is found. Can take a few minutes.

Input parameters:

- `organizationId` (string, required): Company ID returned by organization search or enrichment

Output parameters:

- `creditsCharged` (number)
- `decisionMaker`
- `found` (boolean)

### `persons_search` (~568 tokens)

Search persons with their emails and phones

Search persons with their emails and phones. Returns only people with an email or phone, with full contact data, and charges 1 credit per returned person. Page with nextOffset. limit 0 returns only totalCount, free. saveToContacts also stores them in your contacts, where people you already had are refunded.

Input parameters:

- `decisionMakersOnly` (boolean): C-level, VP or director seniority, or a founder, owner, CEO, managing director or president title
- `domains` (array): Look companies up by domain, e.g. ["stripe.com"]
- `employeeBands` (array): Headcount bands
- `employeeGrowthMin` (integer): Minimum employee growth on LinkedIn in percent, e.g. 10; known for about 1 in 13 US companies
- `foundedAfter` (integer): Earliest founding year to include
- `foundedBefore` (integer): Latest founding year to include
- `fundedAfter` (integer): Year of the last funding round, at least; known for about 1 in 100 US companies
- `hqCountry` (array): ISO alpha-2 country codes of the headquarters, e.g. ["US", "DE"]
- `hqState` (array): US state names or codes of the headquarters
- `inCountry` (array): ISO alpha-2 country codes where the person is based
- `industryNaicsDirect` (array): NAICS codes
- `jobLevel` (array): Allowed job seniority levels
- `jobTitle` (array): Matched as partial text, so "CEO" also finds "Assistant to the CEO"; combine with jobLevel to narrow
- `jobTitleExclude` (array): Job title phrases to exclude
- `limit` (integer): Maximum people to return; 0 returns only a free count
- `monthlyVisitsMin` (integer): Minimum monthly website visits; known for about 1 in 8 US companies, the rest are excluded
- `offset` (integer): Pagination offset; use nextOffset from the previous response
- `onePerOrganization` (boolean): Return at most one person per company
- `organizationIds` (array): Limit to organizations from organizations_search
- `personCity` (array): Cities where the person is based
- `personState` (array): States where the person is based
- `query` (string): Free text matched against company name, description and keywords
- `revenueRange` (array): Annual company revenue bands
- `saveToContacts` (boolean): Save returned people to your Deeplead contacts
- `semantic` (string): What the company is and sells, matched by meaning, e.g. "outsourced medical billing for clinics"
- `technologies` (array): Technologies used by the company

Output parameters:

- `chargedCredits` (number)
- `nextOffset` (number|null)
- `persons` (array)
- `totalCount` (number): With limit 0: all matching people, including those without an email or phone

### `persons_lookup` (~153 tokens)

Look up one person by LinkedIn URL, email, or name and company domain

Look up one person by LinkedIn URL, email, or name and company domain. Returns the person with their emails, phones, role and company. Charges 1 credit only when the person is found with an email or phone. saveToContacts also stores them in your contacts.

Input parameters:

- `domain` (string): Company domain, e.g. "acme.com"
- `email` (string): Known email address identifying the person
- `linkedin` (string): e.g. "https://www.linkedin.com/in/jane-doe"
- `name` (string): Full name, e.g. "Jane Doe"; needs domain
- `saveToContacts` (boolean): Save the returned person to your Deeplead contacts

Output parameters:

- `chargedCredits` (number)
- `found` (boolean)
- `person`

### `persons_find_email` (~94 tokens)

Find a person's work email by LinkedIn URL, or full name and company domain

Find a person's work email by LinkedIn URL, or full name and company domain. Charges 1 credit only when an email is found.

Input parameters:

- `domain` (string): Company domain, e.g. "acme.com"
- `linkedin` (string): e.g. "https://www.linkedin.com/in/jane-doe"
- `name` (string): Full name, e.g. "Jane Doe"; needs domain

Output parameters:

- `alternateEmails` (array)
- `chargedCredits` (number)
- `companyName` (string|null)
- `companyWebsite` (string|null)
- `email` (string|null)
- `found` (boolean)
- `jobTitle` (string|null)
- `linkedin` (string|null)
- `name` (string|null)

### `persons_find_phone` (~110 tokens)

Find a person's phone number by LinkedIn URL, email, or full name and company domain

Find a person's phone number by LinkedIn URL, email, or full name and company domain. Charges 2 credits only when a phone number is found.

Input parameters:

- `domain` (string): Company domain, e.g. "acme.com"
- `email` (string): Known email address identifying the person
- `linkedin` (string): e.g. "https://www.linkedin.com/in/jane-doe"
- `name` (string): Full name, e.g. "Jane Doe"; needs domain

Output parameters:

- `chargedCredits` (number)
- `companyName` (string|null)
- `companyWebsite` (string|null)
- `found` (boolean)
- `jobTitle` (string|null)
- `linkedin` (string|null)
- `name` (string|null)
- `phone` (string|null)
- `phones` (array)

### `contacts_create` (~51 tokens)

Save your own contacts or organizations

Save your own contacts or organizations. Free. Existing contacts are matched and kept, never duplicated.

Input parameters:

- `contacts` (array, required): Contacts to save; each needs an email, LinkedIn URL, website or organization ID

Output parameters:

- `saved` (number)

### `contacts_list` (~50 tokens)

List your contacts in a stable order; page with nextBefore

List your contacts in a stable order; page with nextBefore

Input parameters:

- `before` (string): The nextBefore of the previous page
- `limit` (integer): Maximum saved contacts to return on this page

Output parameters:

- `contacts` (array)
- `nextBefore` (string|null)

### `deliverability_create_test` (~104 tokens)

Start an inbox placement test for a mailbox you send from

Start an inbox placement test for a mailbox you send from. Send one email from the mailbox you want to test to every address in seedEmails, with the testId anywhere in the body, then poll deliverability_get_test about once a minute to see whether it landed in the inbox, spam or a tab at Gmail, Outlook and other providers. Most seeds report within 2-5 minutes; the test closes 60 minutes after it starts. Charges 25 credits.

Output parameters:

- `chargedCredits` (number)
- `closesAt` (string)
- `seedEmails` (array): Send the test email to every one of these addresses
- `testId` (string): Put this anywhere in the body of the test email

### `deliverability_get_test` (~104 tokens)

Where the test email landed at each seed mailbox

Where the test email landed at each seed mailbox. Poll about once a minute while status is waiting. placement is inbox, spam, promotions, social, updates or forums, or missing while the email has not arrived; score is the inbox share from 0 to 10 once the test is completed. rspamd is the content filter verdict with its matched rules, when a seed reports one.

Input parameters:

- `testId` (string, required): testId returned by deliverability_create_test

Output parameters:

- `closesAt` (string)
- `rspamd`
- `score` (number|null)
- `seeds` (array)
- `status` (string)
- `testId` (string)

### `credits_get` (~12 tokens)

Current credit balance

Current credit balance

Output parameters:

- `credits` (number)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/io-deeplead-deeplead/api-mcp#diagnostics

## Score history

- 2026-10-03: 79
- 2026-10-02: 78
- 2026-10-01: 78
- 2026-09-30: 78
- 2026-09-29: 78
- 2026-09-28: 78
- 2026-09-27: 78
- 2026-09-26: 39
- 2026-09-25: 70

## Common questions

### What is the Deeplead MCP server?

Deeplead is an MCP server listed in the public MCP registry as io.deeplead/deeplead. Find local businesses, companies and decision makers with verified emails for B2B outreach. This page covers its hosted endpoint (https://www.deeplead.io/api/mcp).

### Is the Deeplead MCP server safe to use?

Deeplead scores 79 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Deeplead MCP server expose?

Deeplead exposes 13 tools: businesses_search, organizations_search, organizations_enrich, organizations_find_decision_maker, persons_search, and 8 more. Their descriptions and schemas cost roughly 1,996 tokens of context every time the server is loaded.

### Does the Deeplead MCP server require authentication?

Yes. Deeplead asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

### Is the Deeplead MCP server still maintained?

Deeplead is still listed as active in the MCP registry. We last reached this channel on 3 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://www.deeplead.io/api/mcp
- Website: https://www.deeplead.io/
- Changelog RSS feed: https://verifymcp.io/servers/io-deeplead-deeplead/api-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/io-deeplead-deeplead/api-mcp.json
- HTML version of this page: https://verifymcp.io/servers/io-deeplead-deeplead/api-mcp