Lusha
by Lusha
Search B2B contacts and companies, reveal verified emails and phone numbers, and pull buying signals from your AI assistant. 24 tools, OAuth sign-in, reveals consume Lusha credits.
Verified connector
Listed by Anthropic as a partner connector in its Connectors Directory.
Connection checked by Agentman on .
Anthropic states this reflects the level of review a connector received, not a security audit.
Connect Lusha via MCP
https://mcp.lusha.com/mcp/claudeWorks in any MCP-compatible client. In Agentman Studio it is one click — no config file to edit.
Lusha Tools & Capabilities (24)
Tool names from Anthropic's directory listing. This server requires sign-in, so we could not read tool descriptions or parameter schemas.
Limits
- The output is other people's personal data, and your obligations start when it arrives. Lusha states it relies on legitimate interest and does not collect opt-in consent from individuals for third-party outreach, and places responsibility for a valid legal basis and for honouring opt-outs on the customer. Its API terms require you to delete personal information if the individual asks.
- Opt-out suppression does not reach a transcript. Lusha suppresses opted-out contacts from future output, but details already pulled into a conversation, a document or a CRM are yours to remove. Opt-out reports go to an account Admin monthly, or to a webhook — not to the agent.
- An agent enriching in a loop can spend an allowance fast. At 5 credits per phone number, a hundred-contact list revealed with phones is 500 credits before emails. Requests returning no results still cost the 1-credit minimum. Per-user credit caps exist only on Premium and Scale plans, and legacy Premium plans are excluded from that feature.
- There is no read-only grant. The server advertises a single
mcpscope, and the authorization server's extraapi_accessscope is a platform scope rather than a narrower alternative. Per-call approval in your client is the granular control. - A paid plan and an elevated role are both required. Lusha lists a paid plan with API credits plus an Admin or Manager role, so there is no reduced-privilege way to connect.
- Coverage is uneven and Lusha says so. Lusha states no B2B data provider has 100% coverage or accuracy, that quality varies by region, industry and seniority, that its coverage is stronger for English-speaking markets and technology industries, and that phone coverage varies significantly by country. Emails carry a high/medium/low confidence score.
- You cannot correct a record through the connector. Lusha does not support manual updates to contact information; corrections run through automated algorithms, a thumbs-down in the platform, or a CSV submission.
- Do Not Call filtering is Scale-only and covers two countries. UK (TPS and CTPS) and USA, with an Admin enabling it. Lusha warns that calling a registered number may result in significant fines.
- The published tool lists disagree with each other. The directory names 24 and Lusha's MCP table lists 22, with renames in one direction and three directory-only tools in the other. Two further names appear only in Lusha's narrative docs. Lusha's own note says available tools may vary by client.
- Tool parameters and safety annotations were not readable. All three live endpoints returned HTTP 401 to an anonymous
initializeon 2026-08-18, so names came from the directory snapshot and meanings from Lusha's documentation. No tool was called and no person was looked up.
Frequently asked questions
Does the Lusha MCP server cost credits to use?
Yes, but only when you reveal contact data. Lusha charges 1 credit per email revealed and 5 credits per phone number, with search, filtering and company browsing at 0 credits. Its documentation states MCP calls consume API credits, and that API requests carry a 1-credit minimum even when no results come back.
What plan do you need for the Lusha MCP server?
A paid Lusha plan with available API credits. Lusha's setup article lists a paid plan and an Admin or Manager role as requirements, because generating an API key needs that role. Lusha sells Free, Starter, Pro, Premium and Scale tiers, and its Do Not Call filtering feature is restricted to Scale plans only.
How do you connect Lusha to a client other than Claude?
Use the bare host with an API key header. Lusha's documentation gives OAuth for Claude, ChatGPT and Codex only, and tells every other client — Cursor, VS Code, n8n, Gemini CLI — to point at https://mcp.lusha.com and pass an x-api-key header. Lusha notes the header name must be lowercase or authentication fails.
Whose personal data does the Lusha connector return?
Third parties who never gave Lusha their data directly. Lusha aggregates business contact details from public professional profiles, company websites, business directories and contributed sources. It states it relies on legitimate interest as its legal basis and does not collect opt-in consent from individuals for third-party outreach.
How can someone remove their details from Lusha?
Through Lusha's removal form or its privacy team. Lusha documents an automated removal form and a privacy address, and states submitted details are permanently deleted. Opted-out contacts are suppressed from search, enrichment and any Lusha output. Bulk removal through the form is not available, so multiple records need the privacy team directly.
Will an agent tell you when a contact has opted out?
No — opt-out reporting runs outside the connector. Lusha sends CSV opt-out reports to a designated account Admin, typically monthly, covering only contacts who opted out since the previous report. Lusha also offers an opt-out webhook for real-time notification. Building a full suppression list means aggregating every report you have received.
Can the Lusha MCP server spend money without you noticing?
It can spend credits, and Anthropic's snapshot names a purchase_options tool. Reveals deduct credits automatically, and Lusha documents an in-conversation top-up flow on its Claude cards. Lusha lets Admins cap credits per user or group on Premium and Scale plans, which is the control that limits an agent's spend.
What are the Lusha API rate limits?
Twenty-five requests per second on general endpoints. Lusha's API documentation adds 5 requests per minute for the Account Usage API and 100 per minute for the Webhooks API, and returns remaining quota in response headers such as x-rate-limit-minute. Exceeding a limit or a daily quota returns HTTP 429.
Sources
- Lusha MCP Server documentation, for the tool table, connection methods, per-client setup, troubleshooting and security guidance (retrieved 2026-08-18 via the Markdown variant at the same path with
.mdappended).docs.lusha.com/robots.txtis a blanketAllow: /with noContent-Signalline, and the host publishes both anllms.txtindex and asitemap.xml. · retrieved 2026-08-18 - Lusha user guide, "Lusha Model Context Protocol (MCP) Server", for the paid-plan and Admin/Manager-role requirements and the capability summary (retrieved 2026-08-18). Absent from
llms.txt; found via the sitemap. · retrieved 2026-08-18 - Lusha user guide, "Using Lusha Inside LLMs", for the interactive Claude cards, the one-click signal pull and the in-conversation top-up flow (retrieved 2026-08-18) · retrieved 2026-08-18
- Lusha user guide, "How to Use the Lusha Plugin for Claude", for the plugin-versus-connector distinction, the four pre-built skills and their example prompts (retrieved 2026-08-18) · retrieved 2026-08-18
- Lusha user guide, "How Credits Are Counted", for the complete per-feature credit table, the API-specific rules and the MCP/API Buying Group pricing note (retrieved 2026-08-18) · retrieved 2026-08-18
- Lusha user guide, "How Credits Work in Lusha", for the reveal costs, plan names, rollover cap and reset behaviour (retrieved 2026-08-18) · retrieved 2026-08-18
- Lusha user guide, "How can I ensure compliance with privacy laws when using Lusha's data for B2B outreach?", for the legitimate-interest legal basis, the absence of opt-in consent for third-party outreach, the customer-responsibility statements and Lusha's no-legal-advice disclaimer (retrieved 2026-08-18) · retrieved 2026-08-18
- Lusha user guide, "What are my rights as a data subject?", for the access, rectification, erasure, restriction, portability and objection rights and the privacy-team route (retrieved 2026-08-18) · retrieved 2026-08-18
- Lusha user guide, "How to remove your details from Lusha", for the automated removal form, permanent deletion and the absence of bulk removal (retrieved 2026-08-18) · retrieved 2026-08-18
- Lusha user guide, "Opt-Out Contacts", for suppression from search, enrichment and output, the monthly CSV report to an account Admin and the opt-out webhook (retrieved 2026-08-18) · retrieved 2026-08-18
- Lusha user guide, "Do Not Call (DNC) tables", for the Scale-plan gate, the UK and USA coverage and the fines warning (retrieved 2026-08-18) · retrieved 2026-08-18
- Lusha user guide, "Understanding Data Quality and Coverage", for the data sources, the no-data-brokers statement, coverage caveats, confidence scores and the no-manual-updates policy (retrieved 2026-08-18) · retrieved 2026-08-18
- Lusha API Q&A, for rate limits, the HTTP 451 GDPR status, the search-then-enrich pattern and the per-action billing rules (retrieved 2026-08-18) · retrieved 2026-08-18
- Lusha, "Responsible Use of Lusha API", for the customer obligations on privacy rights, prohibited uses, security measures and deletion on request (retrieved 2026-08-18) · retrieved 2026-08-18
- Lusha user guide, "Buying Group: Find the Right Contacts Fast", for the Decision Maker, Champion and End User reveal costs and the MCP/API-first pricing note (retrieved 2026-08-18) · retrieved 2026-08-18
- Lusha user guide, "Website Visitors API", for the 2-credits-per-company MCP rate (retrieved 2026-08-18) · retrieved 2026-08-18
- Lusha user guide, "Credits and Unified Recommendations List", for the blurred-by-default identifiers and the reveal-versus-show credit split (retrieved 2026-08-18) · retrieved 2026-08-18
- Live auth-posture check against
https://mcp.lusha.com/mcp/claude—initializereturned - RFC 9728 protected-resource descriptors — , the
/mcpform and the host root (all HTTP 200, 2026-08-18). Each namesscopes_supported: ["mcp"],authorization_servers: ["https://auth.lusha.com"]and itself as theresource. · retrieved 2026-08-18 - RFC 8414 authorization server metadata (HTTP 200, 2026-08-18), naming
scopes_supported: ["mcp", "api_access"], PKCES256and aregistration_endpoint. The copy served frommcp.lusha.comlists only themcpscope. · retrieved 2026-08-18 - Anthropic Connectors Directory entry, for tool names, tier, endpoint, the "Read and write"
permissionsvalue andhas_mcp_app(snapshot dated 2026-08-16) · retrieved 2026-08-16 - Not used as a source:
www.lusha.com. Itsrobots.txtcarriesContent-Signal: search=yes, ai-train=no, use=referenceand disallows ClaudeBot by name, and the host returns HTTP 403 to a command-line client. Lusha's privacy notice, data page, trust centre and removal form live there; this page links to them and synthesises nothing from them. Everything above comes fromdocs.lusha.com, which sets no such signal.
Use in Agentman
Connect once and your agents call these tools on their own — on a schedule, in a workflow, with nobody at the keyboard.
Open in Agentman StudioServer Info
- Category
- Productivity
- Developer
- Lusha
- Tools
- 24
- Domain
- mcp.lusha.com
Using Claude Desktop or another MCP client? Setup docs — the connection URL above works anywhere.