# HirePulse B2B Company Research (remote · gethirepulse.xyz)

9 company tools: profiles, tech stack, hiring intent, open jobs, ads, contacts. 10 free calls a day.

- Trust score: 63/100 (medium)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `gethirepulse.xyz`: 63/100 (this document), [markdown](https://verifymcp.io/servers/edtool79-collab-hirepulse-b2b/gethirepulse.md), [page](https://verifymcp.io/servers/edtool79-collab-hirepulse-b2b/gethirepulse)

## Channel facts

- Endpoint: `https://gethirepulse.xyz/mcp?profile=b2b&ref=registry-b2b`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.2`

## 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 2026-11-05.

- **Endpoint Security**: 46/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 1 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS check failed: the endpoint is reachable over plaintext HTTP.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - 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**: 66/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1854 tokens (~185/item across 10 items; 10 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 33/100
  - Stability observed for 10 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.
  - Structured output schemas are declared (90% 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 10 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 11 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 HirePulse B2B Company Research MCP server?

HirePulse B2B Company Research is a hosted endpoint at https://gethirepulse.xyz/mcp?profile=b2b&ref=registry-b2b, 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 edtool79-collab-hirepulse-b2b 'https://gethirepulse.xyz/mcp?profile=b2b&ref=registry-b2b'
```

### Cursor

```json
{
  "mcpServers": {
    "edtool79-collab-hirepulse-b2b": {
      "url": "https://gethirepulse.xyz/mcp?profile=b2b&ref=registry-b2b"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "edtool79-collab-hirepulse-b2b": {
      "type": "http",
      "url": "https://gethirepulse.xyz/mcp?profile=b2b&ref=registry-b2b"
    }
  }
}
```

### Codex

```toml
[mcp_servers.edtool79-collab-hirepulse-b2b]
url = "https://gethirepulse.xyz/mcp?profile=b2b&ref=registry-b2b"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "edtool79-collab-hirepulse-b2b": {
      "type": "remote",
      "url": "https://gethirepulse.xyz/mcp?profile=b2b&ref=registry-b2b",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add edtool79-collab-hirepulse-b2b --url 'https://gethirepulse.xyz/mcp?profile=b2b&ref=registry-b2b' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  edtool79-collab-hirepulse-b2b:
    url: "https://gethirepulse.xyz/mcp?profile=b2b&ref=registry-b2b"
```

### Netclaw

```json
{
  "McpServers": {
    "edtool79-collab-hirepulse-b2b": {
      "Transport": "http",
      "Url": "https://gethirepulse.xyz/mcp?profile=b2b&ref=registry-b2b"
    }
  }
}
```

### Vellum

```bash
assistant mcp add edtool79-collab-hirepulse-b2b -t streamable-http -u 'https://gethirepulse.xyz/mcp?profile=b2b&ref=registry-b2b'
```

### Other

```json
{
  "mcpServers": {
    "edtool79-collab-hirepulse-b2b": {
      "type": "http",
      "url": "https://gethirepulse.xyz/mcp?profile=b2b&ref=registry-b2b"
    }
  }
}
```

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.

### 2026-11-05 (score 63, +1)

No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-03 (score 62, +1)

- [functional regression] Tool coverage: 100% → 90%
- [functional] Schema quality: good → excellent
- [functional] New tool “talk_to_hirepulse”

### 2026-11-02 (score 61, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “claim_free_trial” rewrote its description, which is the text the model reads
- [security] Tool “detect_website_tech_stack” rewrote its description, which is the text the model reads
- [security] Tool “extract_company_contacts” rewrote its description, which is the text the model reads
- [security] Tool “get_company_hiring_intent” rewrote its description, which is the text the model reads
- [security] Tool “get_company_open_jobs” rewrote its description, which is the text the model reads
- [security] Tool “get_google_ads_by_domain” rewrote its description, which is the text the model reads
- [security] Tool “watch_company_jobs” rewrote its description, which is the text the model reads

### 2026-11-01 (score 61, +1)

- [security regression] HTTPS: unverified → fail
- [security] Tool “detect_website_tech_stack” rewrote its description, which is the text the model reads
- [security] Tool “extract_company_contacts” rewrote its description, which is the text the model reads
- [security] Tool “get_company_hiring_intent” rewrote its description, which is the text the model reads
- [security] Tool “get_company_open_jobs” rewrote its description, which is the text the model reads
- [security] Tool “get_company_profile” rewrote its description, which is the text the model reads
- [security] Tool “get_google_ads_by_domain” rewrote its description, which is the text the model reads
- [security] Tool “watch_company_jobs” rewrote its description, which is the text the model reads

### 2026-10-31 (score 60, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “detect_website_tech_stack” rewrote its description, which is the text the model reads
- [security] Tool “get_company_profile” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 1501 → 1683
- [functional regression] Schema quality: 1501 → 1684
- [functional] New tool “watch_company_jobs”

### 2026-10-30 (score 60, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-28 (score 59, 0)

- [security] Tool “ask_hirepulse_advisor” rewrote its description, which is the text the model reads
- [security] Tool “claim_free_trial” rewrote its description, which is the text the model reads
- [security] Tool “get_company_hiring_intent” rewrote its description, which is the text the model reads
- [security] Tool “get_company_open_jobs” rewrote its description, which is the text the model reads
- [security] Tool “get_company_profile” rewrote its description, which is the text the model reads
- [security] Tool “get_google_ads_by_domain” rewrote its description, which is the text the model reads
- [functional improvement] Tool coverage: 88% → 100%
- [functional improvement] Tool “claim_free_trial” now declares an output schema
- [functional] Schema quality: excellent → good
- [cosmetic] “ask_hirepulse_advisor” added an optional parameter “query”
- [cosmetic] “ask_hirepulse_advisor” made “agent_goal” optional

### 2026-10-27 (score 59, +1)

- [functional improvement] Stability: unverified → 0.03

## MCP tools (10)

### `ask_hirepulse_advisor` (~205 tokens)

HirePulse Advisor (free)

Free advisor that maps B2B leads, hiring signals, buying intent, tech stack, Google Ads and due diligence goals to a tool, price, free-call balance and ready-to-run request preview. For unclear tool choice or cost; get_company_profile provides a full brief for a known domain. Includes four n8n recipes; never executes requests.

Input parameters:

- `agent_goal` (string): Describe the research goal so the advisor can recommend a tool and estimate its list price.
- `budget_usd` (number): Optional USD budget used for recommendations only; this does not authorize spending or payment.
- `domain_count` (integer): Number of companies you plan to research, used for batch sizing and cost estimates.
- `query` (string): Alias for agent_goal; provide one goal field, or identical values when both are present.
- `sample_domain` (string): Optional bare public company domain for a concrete request example and existing cached hints; no new lookup is run.

Output parameters:

- `alternatives`
- `cached_hint`: Today only, status metadata; no result data or new engine calls.
- `code`
- `cost_estimate_usd`: List-price range before free quota, actual data availability and optional follow-up calls; includes request splitting and scan limits.
- `efficiency_analysis`
- `free_quota`
- `guarantees`
- `recommended_execution_sequence`
- `recommended_pipelines`
- `recommended_tool`: Recommended data tool, or null when the goal is unclear.
- `status`
- `tools`
- `why`

### `detect_website_tech_stack` (~145 tokens)

Website Tech Stack

Website tech stack lookup from a domain (BuiltWith-style technographics): ad pixels (Meta, Google Ads, LinkedIn, TikTok), analytics, tag managers, CMS, e-commerce platform, hosting, payments, plus email provider, SPF and DMARC from DNS. Use when an agent needs technographic data for lead enrichment or competitor research. $0.005 per result; blocked or empty sites are free.

Input parameters:

- `context` (string): Optional. A few words on why you are calling this tool. Recorded without your identity to improve the tools; leave out personal data.
- `domain` (string, required): Public domain without a URL scheme, path or port.

Output parameters:

- `ad_pixels`
- `added`
- `age_seconds`: Seconds since checked_at, not the cache insertion time; null when the observation time is unknown.
- `analytics`
- `apify_alternative`
- `checked_at`
- `cms`
- `code`
- `dmarc_policy`
- `domain`
- `ecommerce`
- `email_provider`
- `final_url`
- `frameworks`
- `has_ga4`
- `has_google_ads_tag`
- `has_gtm`
- `has_linkedin_insight`
- `has_meta_pixel`
- `has_tiktok_pixel`
- `hosting_cdn`
- `is_first_run`
- `marketing_tools`
- `next_steps`: Suggested follow-up calls on the same domain, with the exact body. Optional to use.
- `note`
- `payments`
- `recommended_next_step`
- `removed`
- `sandbox`
- `served_from_cache`: True when the gateway reused a saved result; false does not guarantee the upstream fetched fresh data.
- `spf_senders`
- `status`: Only ok is charged. no_signals: the page loaded but no technology was detected.
- `technology_count`
- `title`
- `verified_services`

### `get_company_open_jobs` (~200 tokens)

Company Open Jobs

Company job postings lookup from a domain: open roles from public Greenhouse, Lever, Ashby, Workable, Recruitee and SmartRecruiters boards, with title, department, location, remote flag and published salary; up to 300 jobs, and new or closed jobs against known_job_ids. Use when an agent needs open roles or hiring signals for a company. $0.01; no board or no jobs is free.

Input parameters:

- `context` (string): Optional. A few words on why you are calling this tool. Recorded without your identity to improve the tools; leave out personal data.
- `diff_only` (boolean): Return only jobs that are not in known_job_ids. Needs known_job_ids.
- `domain` (string, required): Public domain without a URL scheme, path or port.
- `known_job_ids` (array): Job IDs you already have from an earlier call. The answer then lists new and closed job IDs.

Output parameters:

- `ats_type`
- `board_match`: name_match: the board name equals the first part of the domain, so check generic names.
- `board_slug`
- `checked_at`
- `code`
- `confidence`: high: the company website links to this board. unverified: only the board name matches the domain name.
- `diff`
- `domain`
- `jobs`
- `jobs_by_department`
- `jobs_returned`
- `jobs_truncated`
- `jobs_with_salary`
- `next_poll_after`: Job boards change slowly; calling again before this time is usually wasted.
- `next_steps`: Suggested follow-up calls on the same domain, with the exact body. Optional to use.
- `note`
- `remote_jobs`
- `sandbox`
- `status`: Only ok is charged.
- `top_locations`
- `top_technologies`
- `total_active_jobs`

### `get_company_hiring_intent` (~140 tokens)

Hiring Intent Score

Hiring intent score (0-100) for a company domain, from its public job board: hiring status, open roles, postings in the last 30 days, functions and technologies. A heuristic signal, not confirmed purchase intent. Use when an agent ranks accounts by hiring activity. $0.01; no board or no jobs is free. Job listings: get_company_open_jobs.

Input parameters:

- `context` (string): Optional. A few words on why you are calling this tool. Recorded without your identity to improve the tools; leave out personal data.
- `domain` (string, required): Public company domain without a URL scheme, path or port.

Output parameters:

- `ats_type`
- `buying_signals`
- `checked_at`
- `code`
- `confidence`: high: the company website links to the board. unverified: only the board name matches the domain.
- `department_breakdown`
- `domain`
- `function_breakdown`
- `hiring_status`
- `intent_score`
- `jobs_truncated`
- `next_steps`: Suggested follow-up calls on the same domain, with the exact body. Optional to use.
- `notable_open_roles`
- `note`
- `remote_roles`
- `roles_posted_last_30_days`
- `roles_with_known_post_date`
- `sandbox`
- `status`: Only ok is charged.
- `top_demanded_technologies`
- `top_locations`
- `total_open_roles`

### `get_google_ads_by_domain` (~144 tokens)

Google Ads by Domain

Google Ads lookup for a company domain from the public Ads Transparency Center: advertiser status, estimated ad count and up to 40 ads with format, dates and links; optional region filter. Use when an agent researches a company's or a competitor's advertising. No private account access. $0.01; no ads found is free.

Input parameters:

- `context` (string): Optional. A few words on why you are calling this tool. Recorded without your identity to improve the tools; leave out personal data.
- `domain` (string, required): Advertiser domain without a URL scheme, path or port.
- `region` (string): Optional country filter. Leave out for all regions.

Output parameters:

- `ads`
- `ads_returned`
- `ads_shown_last_30_days_in_sample`
- `advertisers`
- `checked_at`
- `code`
- `domain`
- `earliest_first_shown_in_sample`
- `formats_in_sample`
- `latest_last_shown_in_sample`
- `next_steps`: Suggested follow-up calls on the same domain, with the exact body. Optional to use.
- `note`
- `region`
- `sandbox`
- `status`: Only ok is charged.
- `total_ads_estimate`

### `get_company_profile` (~132 tokens)

Company Profile

Company profile and B2B lead enrichment: tech stack, hiring intent, Google Ads, published contacts and breakout_summary growth estimates. $0.03 only when2+ of4 sections have data; one of 10 free calls/day. Estimates are not forecasts. Use individual tools for one signal; bulk and footprint research require the full /mcp profile.

Input parameters:

- `context` (string): Optional. A few words on why you are calling this tool. Recorded without your identity to improve the tools; leave out personal data.
- `domain` (string, required): Public company domain without a URL scheme, path or port.

Output parameters:

- `age_seconds`: Seconds since checked_at, not the cache insertion time; null when the observation time is unknown.
- `breakout_summary`: get_company_profile only. Growth estimate from public signals (hiring, Google Ads, site maturity); not investment advice.
- `checked_at`
- `code`
- `contacts`: get_company_profile only. Same fields as extract_company_contacts.
- `domain`
- `footprint`: found, not_found or unknown for each public signal.
- `google_ads`: Same fields as get_google_ads_by_domain.
- `hiring_intent`: Same fields as get_company_hiring_intent.
- `note`
- `recommended_next_step`: null after a completed company-profile; no automatic repeat of the same lookup is recommended.
- `sandbox`
- `sections_status`
- `sections_with_data`
- `served_from_cache`: True when the gateway reused a saved result; false does not guarantee the upstream fetched fresh data.
- `signals`
- `status`: Only ok is charged: at least two sections have data (of four for get_company_profile, three for company_footprint_check).
- `tech_stack`: Same fields as detect_website_tech_stack.

### `watch_company_jobs` (~199 tokens)

Watch Company Jobs

Job-change monitoring for up to 50 company domains: with known_job_ids per domain from an earlier answer, returns only new and closed jobs. The scan is free and returns a quote_id; $0.01 is charged only per company whose jobs changed or that needs a first baseline, at most $0.50. Unchanged companies are free. Use when an agent tracks hiring at a list of accounts daily.

Input parameters:

- `context` (string): Optional. A few words on why you are calling this tool. Recorded without your identity to improve the tools; leave out personal data.
- `domains` (array): Public company domains without a URL scheme, path or port.
- `known_job_ids` (object): Map of domain to the job_id list from your previous answer. Domains without an entry get a full first baseline.
- `quote_id` (string): quote_id from step 1. Send it alone to pay and receive the results.

Output parameters:

- `billable_count`
- `code`
- `cold`: hot-buyers: domains below the threshold, free.
- `expires_at`
- `next`
- `price_micro_usd`
- `price_usd`
- `quote_id`
- `results`: Paid rows, after step 2.
- `sandbox`
- `status`: quote: pay with quote_id to get the results. nothing_billable: no charge. ok: paid results.
- `statuses`: Status of every domain, free.

### `extract_company_contacts` (~134 tokens)

Public Company Contacts

Company contact lookup from a domain: published emails and LinkedIn, X and GitHub links from the home, about, contact, team and careers pages, deduplicated, plus MX, SPF and DMARC records. Not mailbox verification. Use when an agent needs public company contact data for outreach research. $0.01; nothing found is free.

Input parameters:

- `context` (string): Optional. A few words on why you are calling this tool. Recorded without your identity to improve the tools; leave out personal data.
- `domain` (string, required): Bare public company domain whose published contact pages and DNS records should be inspected.

Output parameters:

- `code`
- `dmarc`
- `domain`
- `email_deliverable`
- `emails`
- `inferred_email_pattern`
- `mx`
- `sandbox`
- `social_links`
- `spf`
- `status`

### `talk_to_hirepulse` (~123 tokens)

Free optional conversation about your goal, arrival source and blocker. Messages are saved for the service owner. Omit secrets and personal data. Executes no work or payment. Save conversation_id and reuse message_id on retries.

Input parameters:

- `conversation_id` (string): Private continuation token returned by the previous response. Keep it secret.
- `message` (string, required): Your goal or answer to the last question. Saved for the owner. Omit secrets and personal data.
- `message_id` (string, required): Unique message identifier. Reuse it only when retrying the same message.

### `claim_free_trial` (~121 tokens)

Claim a free 25-call trial

One-time pass: 25 successful calls shared across supported single-domain tools, valid 30 days and independent of IP. Excludes private lookup, quote redemption and paid email inboxes. Takes one active Base wallet or a work email (no email is sent). The pass goes in the X-Trial-Token header or MCP metadata hirepulse/trial_token.

Input parameters:

- `email` (string): A work email address; free mailbox providers are not accepted.
- `wallet` (string): A Base address with at least one transaction or $0.10 USDC.

Output parameters:

- `calls`
- `demo_domains_always_free`
- `expires_at`
- `how_to_use`
- `status`
- `trial_token`: Secret bearer capability. Keep private; never publish or log.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/edtool79-collab-hirepulse-b2b/gethirepulse#diagnostics

## Score history

- 2026-11-05: 63
- 2026-11-04: 62
- 2026-11-03: 62
- 2026-11-02: 61
- 2026-11-01: 61
- 2026-10-31: 60
- 2026-10-30: 60
- 2026-10-29: 59
- 2026-10-28: 59
- 2026-10-27: 59
- 2026-10-26: 58

## Common questions

### What is the HirePulse B2B Company Research MCP server?

HirePulse B2B Company Research is an MCP server listed in the public MCP registry as io.github.edtool79-collab/hirepulse-b2b. 9 company tools: profiles, tech stack, hiring intent, open jobs, ads, contacts. 10 free calls a day. This page covers its hosted endpoint (https://gethirepulse.xyz/mcp?profile=b2b&ref=registry-b2b).

### Is the HirePulse B2B Company Research MCP server safe to use?

HirePulse B2B Company Research scores 63 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 HirePulse B2B Company Research MCP server expose?

HirePulse B2B Company Research exposes 10 tools: ask_hirepulse_advisor, detect_website_tech_stack, get_company_open_jobs, get_company_hiring_intent, get_google_ads_by_domain, and 5 more. Their descriptions and schemas cost roughly 1,543 tokens of context every time the server is loaded.

### Does the HirePulse B2B Company Research MCP server require authentication?

No. We connected to HirePulse B2B Company Research without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the HirePulse B2B Company Research MCP server still maintained?

HirePulse B2B Company Research is still listed as active in the MCP registry. We last reached this channel on 5 November 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://gethirepulse.xyz/mcp?profile=b2b&ref=registry-b2b
- Repository: https://github.com/edtool79-collab/hirepulse-mcp
- Changelog RSS feed: https://verifymcp.io/servers/edtool79-collab-hirepulse-b2b/gethirepulse.xml
- Changelog JSON feed: https://verifymcp.io/servers/edtool79-collab-hirepulse-b2b/gethirepulse.json
- HTML version of this page: https://verifymcp.io/servers/edtool79-collab-hirepulse-b2b/gethirepulse