# Lyre Leads (remote · lyreleads.com)

Every business of a kind in a city, from Google Maps, read from its website, with verified emails.

- Trust score: 68/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-22

## Components

- remote · `lyreleads.com`: 68/100 (this document), [markdown](https://verifymcp.io/servers/com-lyreleads-lyre-leads/lyreleads.md), [page](https://verifymcp.io/servers/com-lyreleads-lyre-leads/lyreleads)

## Channel facts

- Endpoint: `https://lyreleads.com/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 2026-10-22.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (search_areas).
  - 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.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 63/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 4391 tokens (~292/item across 15 items; 15 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **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.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 15 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 16 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 Lyre Leads MCP server?

Lyre Leads is a hosted endpoint at https://lyreleads.com/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 com-lyreleads-lyre-leads 'https://lyreleads.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-lyreleads-lyre-leads": {
      "url": "https://lyreleads.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-lyreleads-lyre-leads": {
      "type": "http",
      "url": "https://lyreleads.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-lyreleads-lyre-leads]
url = "https://lyreleads.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-lyreleads-lyre-leads": {
      "type": "remote",
      "url": "https://lyreleads.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-lyreleads-lyre-leads --url 'https://lyreleads.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-lyreleads-lyre-leads:
    url: "https://lyreleads.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-lyreleads-lyre-leads": {
      "Transport": "http",
      "Url": "https://lyreleads.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-lyreleads-lyre-leads -t streamable-http -u 'https://lyreleads.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-lyreleads-lyre-leads": {
      "type": "http",
      "url": "https://lyreleads.com/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.

### 2026-10-21 (score 68, +1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “get_search_results” rewrote its description, which is the text the model reads
- [security] Tool “list_results” rewrote its description, which is the text the model reads
- [cosmetic] “get_search_results” reworded the description of “limit”

### 2026-10-19 (score 67, +1)

- [security] Tool “find_contacts” rewrote its description, which is the text the model reads
- [cosmetic] “estimate_list” reworded the description of “include_contacts”

### 2026-10-18 (score 66, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “enrich_leads” rewrote its description, which is the text the model reads
- [security] Tool “enroll_leads” rewrote its description, which is the text the model reads
- [security] Tool “estimate_area_search” rewrote its description, which is the text the model reads
- [security] Tool “estimate_list” rewrote its description, which is the text the model reads
- [security] Tool “find_contacts” rewrote its description, which is the text the model reads
- [security] Tool “get_balance” rewrote its description, which is the text the model reads
- [security] Tool “search_areas” rewrote its description, which is the text the model reads
- [security] Tool “search_leads” rewrote its description, which is the text the model reads
- [cosmetic] “count_saved_leads” reworded the description of “enrolled”
- [cosmetic] “estimate_list” reworded the description of “include_contacts”
- [cosmetic] Tool “get_balance” changed its title: Lead balance → Token balance

### 2026-10-17 (score 66, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “find_contacts” rewrote its description, which is the text the model reads
- [security] Tool “get_balance” rewrote its description, which is the text the model reads
- [security] Tool “get_search_results” rewrote its description, which is the text the model reads
- [security] Tool “list_results” rewrote its description, which is the text the model reads
- [security] Tool “preview_search” rewrote its description, which is the text the model reads
- [security] Tool “search_leads” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 235 → 280
- [cosmetic] “get_search_results” added an optional parameter “detail”
- [cosmetic] “list_results” added an optional parameter “detail”
- [cosmetic] “list_results” added an optional parameter “wait_seconds”
- [cosmetic] “list_results” reworded the description of “limit”
- [cosmetic] Tool “preview_search” changed its title: Preview a search (no account) → Free sample, nothing saved

### 2026-10-16 (score 66, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-15 (score 65, 0)

- [functional improvement] Stability: unverified → 0.03

### 2026-10-14 (score 65)

First indexed and scored.

## MCP tools (15)

### `preview_search` (~257 tokens)

Free sample, nothing saved

FREE sample, no account: the first page (up to 20) of ONE Google Maps search for a kind of business in a place, with phones partly hidden. Nothing is saved or enriched, and it returns no emails, contacts or software. Use it only when the user asks for a preview or a sample, or has no account connected and wants to see what comes back. When the user asks to search, find, pull or list businesses, use search_leads (one city, answered at once) or search_areas (whole cities) instead, even for a single page: they save the businesses to the user's account and enrich them, and calling one starts sign-in if the account isn't connected yet. Places look like "Houston, TX", "Copenhagen" or "Lyon, France"; a shared name picks the largest and lists the others.

Input parameters:

- `country` (string): Optional country name, if the place name alone is ambiguous across countries
- `place` (string, required): City or town, optionally with state and country, e.g. "Houston, TX" or "Aarhus, Denmark"
- `query` (string, required): Kind of business, e.g. "roofing contractor" or "hair salon"

### `find_areas` (~149 tokens)

Find search areas

FREE, no account needed. Look up the areas search_areas accepts in a country, most populous first, each with an id. Call without q to browse; call with no country to get the list of countries. When a place name is shared (the US list has four Houstons and thirteen Springfields), pass the id of the one the user means to search_areas.

Input parameters:

- `country` (string): Country name, e.g. "United States". Omit to list countries.
- `limit` (integer): Max areas (default 20, max 100)
- `q` (string): Part of a place name, case-insensitive, e.g. "hous"

### `estimate_area_search` (~168 tokens)

Size an area search

FREE, no account needed. Size a search_areas run before starting it: how many grid points, and, when the user's account is connected, how many areas it already covers for the query (those are skipped). It cannot give an exact cost, because billing is 1 token per NEW business found (one new lead costs one token) and nobody knows how many exist before looking.

Input parameters:

- `areas` (array, required): Area names like "Houston, Texas", or ids from find_areas
- `country` (string, required): Country name, as listed by find_areas
- `mode` (string): grid covers the whole area (default here); city pages from the centre and is cheaper for small towns
- `query` (string, required): Business keyword, e.g. "roofing contractor"

### `search_areas` (~272 tokens)

Search whole areas

The search to use for coverage. Sweeps each area with a grid of map points live against Google Maps, as a background job, the same search the Lyre Leads Search page runs. In Houston this found 1,061 roofing contractors where paging from one centre found 255. Costs 1 token per NEW business (one new lead costs one token); listings the account already holds cost nothing (a small per-page minimum applies). Every new business is enriched, relevance-checked, its address verified, and enrolled in the monthly re-check automatically. Returns job_id: poll get_job_status with kind "search" until finished is true, then read the leads with get_search_results. If an area name fits more than one place, the call returns the candidates with ids and starts nothing: ask the user which one they mean and resend with that id. At most two searches run at once per account.

Input parameters:

- `areas` (array, required): Area names like "Houston, Texas", or ids from find_areas
- `country` (string, required): Country name, as listed by find_areas
- `mode` (string): grid (default here) covers the whole area; city pages from the centre
- `query` (string, required): Business keyword, e.g. "roofing contractor" or "cosmetic dentist"

### `get_search_results` (~281 tokens)

Read a search's leads

FREE. Read the leads a search_areas job found, up to 100 per page. Accepts the same filters as the Lyre Leads database, passed as filters, e.g. {"relevanceYes": true, "hasVerifiedEmail": true, "noFBPixel": true}. Each lead comes back compact by default: contact details, business email and its verification state, named contact, relevance verdict with its evidence, software and signals, plus a summary and next steps; detail "full" returns every database field. The summary counts every lead in the search (or every lead the filters match), not only the page, so one read answers how many have emails, contacts or no contact yet; read further pages only when the user asks to see more leads. Enrichment keeps landing for a while after the search finishes, so re-read if leads are still enriching.

Input parameters:

- `detail` (string): compact (default) or full (every field, much longer)
- `filters` (object): Database filter parameters as key/value pairs, e.g. {"relevanceYes": true, "minReviews": 100}
- `job_id` (string, required): job_id returned by search_areas
- `limit` (integer): Leads per page (default 50, max 100)
- `page` (integer): Page number, from 1

### `search_leads` (~283 tokens)

Quick one-city search

Search ONE city on the user's account and get the businesses back in the same call: 1 to 5 result pages from the city centre, about 20 per page. Use it when the user asks for a quick search, a page of results or one town; for a whole city or several, use search_areas, which finds several times more. Costs 1 token per NEW business (one new lead costs one token); ones the account already holds are free. Every new business is then enriched from its own website in the background, about two minutes for 20: business email with its verification state, a named contact where the site names one, the software it runs, and a check that it really is the kind of business searched for. Returns the Maps listing and a search_id. Then call list_results with that search_id and wait_seconds 40, and show the user what enrichment found, not only the listing.

Input parameters:

- `city` (string, required): City name, e.g. "Austin"
- `country` (string, required): Country name, e.g. "United States"
- `pages` (integer): Result pages to pull, 1-5 (about 20 results per page). Default 1.
- `query` (string, required): Business keyword, e.g. "roofing contractor" or "cosmetic dentist" (max 200 chars)

### `list_results` (~233 tokens)

List saved leads

FREE. Read saved leads with what enrichment found: business email and its verification state, named contact (name, title, email and its state), the relevance verdict with the sentence from the business's own site, software (CMS, CRM, booking, chat, email marketing), technologies and signals. Pass the search_id from search_leads to read that search; wait_seconds (up to 45) first waits for enrichment still running on it. Returns a compact view with a summary and next steps; with a search_id the summary counts the whole search, not only the page. detail "full" returns every field.

Input parameters:

- `detail` (string): compact (default) or full (every field, much longer)
- `limit` (integer): Max rows to return (default 50, max 100)
- `offset` (integer): Pagination offset
- `search_id` (string): Batch id returned by search_leads (optional: omit for all results)
- `wait_seconds` (integer): With search_id: wait up to this many seconds for enrichment to finish before reading. 40 right after search_leads.

### `get_balance` (~148 tokens)

Token balance

Get the account's token balance and plan. Plans are sold in leads and every price is in tokens: one new lead (a business found by a search, with enrichment, relevance check, verified address and the monthly re-check included) costs one token. Businesses the account already holds: enrichment is one token per five, enrolling in the monthly re-check one token per two. A named contact found on the open web costs 2 tokens, charged only when a person is found. Email verification is included at no charge. Unused tokens roll over, up to three months' allowance. Plans are bought and changed on the Lyre Leads website, not through these tools; the result carries the link.

### `estimate_list` (~218 tokens)

Price a list

FREE, no account needed. Answers "what would it cost to find me N businesses, and what data comes with each one". Returns an exact cost in tokens broken down by stage (search, enrichment, contact discovery; one new lead costs one token), and when the user's account is connected its balance and the maximum businesses affordable right now, and the full list of data points each lead arrives with. THIS is the tool to use when a user asks what Lyre Leads can get them. Do NOT use count_saved_leads for that question: Lyre Leads generates leads on demand from a live Google Maps search and does not sell access to a stored pile of them, so a count of what an account already holds is not a measure of what is available.

Input parameters:

- `include_contacts` (boolean): Also find the named contacts at each business on the open web and verify their mailboxes. Default false. 2 tokens per person found, verification included.
- `lead_count` (integer, required): How many businesses the user wants found (1-100000)

### `count_saved_leads` (~667 tokens)

Count saved leads

FREE and exact. Counts leads THIS ACCOUNT has already searched and saved, matching any combination of filters, with a breakdown of how many are enriched, have an email, have a contact email, or have been relevance-checked. Use it to size a job over data the account already owns before spending: "how many of my saved roofers have no CRM and a verified email". CRITICAL: this is NOT an inventory of what Lyre Leads can find, and a small result here means the account has not searched much yet, nothing more. Never report this number to a user as the amount of data available, and never use it to answer "how many X do you have" — call estimate_list for that.

Input parameters:

- `ai_crawler_access` (string): One of: open, partial, blocked, unknown. "blocked" = the site is invisible to AI search engines.
- `city` (string): Substring match on city
- `country` (string): Substring match on country
- `email_verification_status` (string): One of: verified, catch_all, unknown, invalid
- `enrichment_status` (string): One of: enriched, pending, unverifiable, no_website, failed
- `enrolled` (boolean): true = enrolled in enrichment: re-checked about monthly at no charge. Every business a search found is enrolled. false = not enrolled (usually imported); enroll_leads enrolls it at one token per two…
- `has_cms` (boolean): true = a CMS was detected. false = enriched and none detected (custom/hand-built site).
- `has_contact_email` (boolean): true = a named contact address is on file.
- `has_crm` (boolean): true = a CRM was detected. false = enriched and none detected. This is the classic "they have no CRM, sell them one" filter.
- `has_email` (boolean): true = has a business email. false = enriched and confirmed to have none (excludes never-checked rows).
- `has_website` (boolean): true = has a website. false = enriched and confirmed to have none.
- `max_rating` (number): Maximum Google star rating. Use with min_reviews to find well-reviewed but poorly-rated businesses.
- `max_reviews` (integer): Maximum Google review count
- `min_rating` (number): Minimum Google star rating
- `min_reviews` (integer): Minimum Google review count
- `query` (string): Substring match on the search keyword that found the lead, e.g. "roofing"
- `relevance` (string): One of: yes, no, unclear. Did a model reading the business website judge it to be the kind of business this row's own search query asked for? Runs inside enrichment at no extra cost, and every verdic…
- `search_id` (string): Restrict to one batch from search_leads
- `type` (string): Substring match on the Google Maps business category, e.g. "Dentist"

### `enrich_leads` (~179 tokens)

Enrich leads

Fetch each lead's website and extract 50+ fields: business email, social profiles, CMS, CRM, email-marketing platform, chat widget, booking system, ad pixels, analytics, schema, SSL, page load, domain age, mail host, and AI-crawler policy. Costs one token per five businesses, on any business you hold, and does not enroll it. Every address it finds is verified at no extra charge. To keep businesses current, use enroll_leads instead. Runs in the background, returns a job id, poll it with get_job_status. Every field follows the three-state contract: a value, a confirmed absence, or unknown.

Input parameters:

- `force` (boolean): Re-enrich rows that already have data (use to refresh stale enrichment). Default false.
- `result_ids` (array, required): Lead ids from list_results

### `enroll_leads` (~129 tokens)

Keep leads current

Enroll leads in enrichment so they stay current: each lead is enriched now and re-checked about once a month for as long as the user keeps it, with change signals when something moves. Costs one token per two businesses, paid once. Businesses a search found are already enrolled for free; already-enrolled leads and leads without a website are skipped at no cost. Use it for the imported or chosen leads the user cares about most. Runs in the background and returns a job id: poll get_job_status with kind "enrich".

Input parameters:

- `result_ids` (array, required): Lead ids to enroll

### `find_contacts` (~232 tokens)

Find named contacts

For leads with a website but no named contact, search the open web for the people the business names (owner, founder, director), then resolve and verify their email in the same run. Costs 2 tokens per person found, verification included; the run reserves 2 tokens per business up front and settles on what it delivered, so the most a run can cost is 2 tokens per lead id sent. Separate from enrichment, which already lists the people a business's own site names, with a verified email where one exists, at no extra charge. This is what reaches local business owners who are not in any LinkedIn-derived contact database. Returns a job id, poll with get_job_status. Outcomes per lead: verified (SMTP-confirmed), published (the address is printed on the company's own site but the domain is catch-all so SMTP cannot confirm it), catch_all (person named, no address obtainable), or searched (no name found).

Input parameters:

- `result_ids` (array, required): Lead ids to search. Only leads with a website and no personal email yet are eligible; ineligible ids are skipped and not charged.

### `verify_emails` (~131 tokens)

Verify emails

SMTP-verify the business emails on saved leads through MillionVerifier. Included in every plan at no charge; a re-check within 90 days reuses the cached verdict. Runs in the background and returns a job id: poll get_job_status with kind "verify" until status is completed, then read the summary. Each address ends in one of four honest states: verified, catch_all (the domain accepts everything, so deliverability cannot be proven), unknown, or invalid. Never treat catch_all as verified.

Input parameters:

- `result_ids` (array, required): Lead ids to verify (max 2,000 per call)

### `get_job_status` (~125 tokens)

Check a background job

Poll a background job started by search_areas, enrich_leads, enroll_leads (kind "enrich"), find_contacts or verify_emails. Pass the job id and its kind. Long jobs are normal: a grid search works through many map points, and enrichment fetches every website in the batch.

Input parameters:

- `job_id` (string, required): Job id returned by the starting tool
- `kind` (string, required): Which tool started it: search (search_areas), enrich (enrich_leads, enroll_leads), contacts (find_contacts), verify (verify_emails)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-lyreleads-lyre-leads/lyreleads#diagnostics

## Score history

- 2026-10-22: 68
- 2026-10-21: 68
- 2026-10-20: 67
- 2026-10-19: 67
- 2026-10-18: 66
- 2026-10-17: 66
- 2026-10-16: 66
- 2026-10-15: 65
- 2026-10-14: 65

## Common questions

### What is the Lyre Leads MCP server?

Lyre Leads is an MCP server listed in the public MCP registry as com.lyreleads/lyre-leads. Every business of a kind in a city, from Google Maps, read from its website, with verified emails. This page covers its hosted endpoint (https://lyreleads.com/mcp).

### Is the Lyre Leads MCP server safe to use?

Lyre Leads scores 68 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 Lyre Leads MCP server expose?

Lyre Leads exposes 15 tools: preview_search, find_areas, estimate_area_search, search_areas, get_search_results, and 10 more. Their descriptions and schemas cost roughly 3,472 tokens of context every time the server is loaded.

### Does the Lyre Leads MCP server require authentication?

No. We connected to Lyre Leads without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Lyre Leads MCP server still maintained?

Lyre Leads is still listed as active in the MCP registry. We last reached this channel on 22 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://lyreleads.com/mcp
- Website: https://lyreleads.com/for-agents
- Changelog RSS feed: https://verifymcp.io/servers/com-lyreleads-lyre-leads/lyreleads.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-lyreleads-lyre-leads/lyreleads.json
- HTML version of this page: https://verifymcp.io/servers/com-lyreleads-lyre-leads/lyreleads