Scrupp MCP server
OfficialIt lets an agent pull and enrich B2B lead data from LinkedIn, Sales Navigator, and Apollo, plus look up companies, find decision makers, find/verify emails, and manage jobs and credits.
Export people from Sales Navigator, LinkedIn people search, or Apollo search URLs, with record caps, optional emails, account choice, and wait limits.
Enrich LinkedIn profile URLs with full profile data and optionally verified work emails.
Look up company data by domain, LinkedIn URL, or name.
Find decision makers at companies with names, titles, and where available work emails.
Find verified work emails from name plus company domain.
Verify up to 100 existing email addresses per call.
Check remaining credits and plan.
Poll a running extraction job by job ID and collect its records when finished.
Provides tools to find local businesses from Google Maps, returning details such as website, address, category, and rating.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Scrupp MCP server Find decision makers at Stripe and verify their work emails"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Scrupp MCP server
An MCP server over the Scrupp Jobs API, so an agent can pull leads without anyone
writing HTTP calls. Ships as scrupp-mcp-server on npm and as a listing in the MCP
registry; that registry is what a growing number of agent runtimes read when they pick
a tool, which is why this is the channel where the buyer is not a person.
In Claude (no install)
Add https://mcp.scrupp.com/sn as a custom connector in Claude and sign in to Scrupp.
Setup steps, what each tool needs and troubleshooting: https://scrupp.com/docs/api/claude
Related MCP server: MCP LinkedIn Sales Navigator
In Claude Code (plugin)
/plugin install scrupp --marketplace Wism-Corp/scrupp-mcp-serverOn Claude Code older than 2.1.275, in two steps:
/plugin marketplace add Wism-Corp/scrupp-mcp-server
/plugin install scrupp@scruppThe plugin connects Claude Code to the hosted connector at https://mcp.scrupp.com/sn,
the same full tool set as the private Claude connector, so nothing is installed
locally. The first time a tool runs, open /mcp, pick scrupp and sign in to Scrupp.
The plugin carries two things:
.mcp.json— the hosted connector above, signed in with OAuth.skills/scrupp-prospecting— how Claude should use the tools: check credits first, pick the tool from what the user has, export five records as a sample before the whole search, collect long jobs withscrupp_get_job, and what to say when a tool refuses.
Check it before a release with claude plugin validate ..
Using it
{
"mcpServers": {
"scrupp": {
"command": "npx",
"args": ["-y", "scrupp-mcp-server"],
"env": { "SCRUPP_API_KEY": "sk_live_..." }
}
}
}SCRUPP_WAIT_SECONDS (default 120) caps how long a tool blocks. A job that outruns it
comes back as { status: "running", job_id } with a note telling the agent to call
scrupp_get_job — better than holding a conversation open for twenty minutes on a
2,500-record export.
Tools
Tool | What it does |
| People out of a Sales Navigator search URL |
| People out of a LinkedIn people-search URL |
| People out of an Apollo search URL (needs a connected account) |
| Full profile data for profile URLs |
| Company data by domain, LinkedIn URL or name |
| Who to write to at a company |
| Verified work emails from name + domain |
| Deliverability check for addresses you already have (1 credit each) |
| Everyone who reacted to or commented on a LinkedIn post |
| Local businesses from Google Maps: website, address, category, rating |
| Watch people or companies for job changes, promotions, funding (0.5 credit per item per check) |
| What changed on a watchlist, newest first; your watchlists when no id is given |
| Status and records for a job that was still running |
| Remaining credits and plan |
Every tool carries a title and readOnlyHint / destructiveHint annotations — the
Claude connectors directory rejects a server without them.
Hosted connector (Streamable HTTP)
node src/http.js (or scrupp-mcp-http) serves the same server over Streamable HTTP
at POST /mcp, stateless, with GET /health for a load balancer. PORT defaults to
8787. Each request authenticates with the caller's own key as
Authorization: Bearer sk_live_...; the key is scoped to that request, so one process
serves many accounts without mixing them up.
The hosted connector exposes a narrower tool set than the local server: email finding, email verification, job status and credits. The tools that gather data from LinkedIn (Sales Navigator, LinkedIn search, profile enrichment) or answer from the shared lead base (company lookup, decision makers), and the Apollo export, stay local-only — they run through accounts that are not the caller's, which is not something to put in a public directory listing.
Try it in Claude Code against a deployed instance:
claude mcp add --transport http scrupp https://mcp.scrupp.com/mcp \
--header "Authorization: Bearer sk_live_..."Private connector with the full API (/sn)
POST /sn serves a second tool set for Scrupp customers who add it by URL
(Claude.ai: Settings → Connectors → Add custom connector →
https://mcp.scrupp.com/sn). It is not listed in the directory and works on
every Scrupp plan. On top of the core tools it has the rest of the API:
scrupp_build_sales_navigator_search (audience in words → a Sales Navigator
search URL with the size Sales Navigator reports, no credits),
scrupp_export_sales_navigator_search, scrupp_export_linkedin_search,
scrupp_run_apollo_search, scrupp_enrich_linkedin_profiles (optionally with
emails), scrupp_lookup_company and scrupp_find_decision_makers.
When the caller has a LinkedIn account with Sales Navigator connected with the Scrupp extension, all of them run only on that account. Without one, they run on Scrupp's shared account pool, which is open to paid plans. The Scrupp API decides this, not this server.
The OAuth resource is what tells the two apart: the protected-resource metadata
for /sn names https://mcp.scrupp.com/sn, and app.scrupp.com issues the
private connector's key (connector:claude-sn) only for that resource. A key
from the /mcp connector gets 403 on everything beyond email finding even if
it is sent to /sn.
Connecting with OAuth
Users of Claude.ai, Claude Desktop and Claude Code don't paste a key: they press
Connect, sign in to Scrupp and allow access. The server advertises its
authorization server at /.well-known/oauth-protected-resource (RFC 9728) and answers
an unauthenticated request with 401 and a WWW-Authenticate header pointing there.
The authorization server itself lives in the Scrupp app at app.scrupp.com
(/oauth/register, /oauth/authorize, /oauth/token); the access token it issues is
an ordinary Scrupp API key marked connector:claude, which the API restricts to the
four tools above. Access tokens last an hour, so the server checks the token before
each request (cached for a minute) and answers 401 invalid_token when it has expired,
which is what makes the client refresh it.
Variable | Default | Meaning |
|
| Listen port |
|
| Public URL of this server, used in the metadata |
|
| Where OAuth tokens are issued |
|
| Scrupp API the tools call |
Tool descriptions are written for a model, not a human: they say when to reach for the tool, not just what it does. That is the whole ranking signal in a registry — a listed server with vague descriptions gets picked and then misused.
Publishing
Move this directory to its own repo,
Wism-Corp/scrupp-mcp-server— the MCP registry validates ownership from the repository and themcpNameinpackage.json.npm publish --access publicwith provenance from GitHub Actions, the same workflow shape asn8n-nodes-scrupp.Publish the registry entry:
npx @modelcontextprotocol/publisher login github npx @modelcontextprotocol/publisher publishIt reads
server.json, checks the npm package carries the matchingmcpName, and lists the server.Then the downstream directories, which read from the registry or take a form: Smithery, Glama, mcp.so, PulseMCP, and Anthropic's connectors directory.
Testing before publishing
npm install
SCRUPP_API_KEY=... npx @modelcontextprotocol/inspector node src/index.jsRun scrupp_credits first (free), then scrupp_find_emails with two people — the
cheapest call that exercises create → poll → result.
Available Tools
10 toolsscrupp_creditsCredit balanceARead-only
Remaining Scrupp credits and the current plan. Worth checking before starting a large export — one credit is one record requested.
Inputs: no named parameters.
scrupp_enrich_linkedin_profilesEnrich LinkedIn profilesCIdempotent
Full profile data for LinkedIn profile URLs: current title, company, location, experience.
Inputs: profile_urls (required), with_emails, wait_seconds.
scrupp_export_linkedin_searchExport a LinkedIn searchAIdempotent
Extract the people from a regular LinkedIn people-search URL. Use this for linkedin.com/search/results/people URLs; use the Sales Navigator tool for linkedin.com/sales URLs.
Inputs: url (required), max, account, with_emails, +1 more.
scrupp_find_decision_makersFind decision makers at a companyAIdempotent
The people worth writing to at a company you only know the domain, LinkedIn URL or name of. Returns names, titles and (where found) work emails.
Inputs: find_by (required), companies (required), max, wait_seconds.
scrupp_find_emailsFind work emailsBIdempotent
Find and verify work email addresses from first name, last name and company domain. Addresses that cannot be verified come back marked rather than guessed.
Inputs: people (required), wait_seconds.
scrupp_get_jobCheck or collect a Scrupp jobARead-only
Status of a job, and its records once it has finished. Use this for a job that was still running when the tool that started it returned.
Inputs: job_id (required).
scrupp_lookup_companyLook up a companyBIdempotent
Company data — size, industry, location, website, LinkedIn — from a domain, a company LinkedIn URL, or a name.
Inputs: companies (required), lookup_by (required), wait_seconds.
scrupp_run_apollo_searchRun an Apollo searchBIdempotent
Extract the people from an Apollo search URL. Requires a connected Apollo account, passed as account.
Inputs: url (required), account (required), max, with_emails, +1 more.
scrupp_verify_emailsVerify email addressesA
Check whether email addresses are deliverable before sending to them. Costs one credit per address; use it on addresses you already have, not on ones scrupp_find_emails just returned (those are verified already).
Inputs: emails (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 10 tools
Most tools are clearly separated by input source and action: the export_* tools map to distinct URL types, and find_emails vs verify_emails have different intents. Some overlap remains among tools that return people/emails (find_emails, find_decision_makers, export_*), but the descriptions reduce confusion.
All names use the scrupp_ prefix with snake_case and generally follow an action_object pattern. The main deviation is scrupp_credits, which is a noun rather than a verb, and the verb set varies (find, verify, export, run, enrich, lookup, get), though still readably consistent.
10 tools is well-scoped for a contact/company data enrichment and export service. Each tool earns its place by covering a distinct source, action, or operational need (credits, async job status, find/verify, LinkedIn/Sales Navigator/Apollo exports, enrichment, company lookup, decision makers).
The surface covers the key workflows for the domain: finding and verifying emails, exporting people from LinkedIn, Sales Navigator, and Apollo searches, enriching LinkedIn profiles, looking up companies, finding decision makers, and checking credits and job status. No obvious retrieval or lifecycle gaps stand out for the stated purpose.
Maintenance
Related MCP Connectors
Search companies, enrich contacts, and reveal emails and phones from your AI agent.
Give AI agents the LinkedIn tools to find, qualify, engage, and follow up with prospects.
Run B2B outreach from your AI agent: 250+ tools for campaigns, leads, LinkedIn and email workflows.
Live LinkedIn data for AI agents: profiles, companies, jobs, posts, email finding. No account risk.
Related MCP Servers
AlicenseAqualityCmaintenanceEnables AI tools to search and enrich B2B leads, including finding professional emails, company profiles, and filtering people and companies by various criteria.5468 npmMIT- AlicenseAqualityBmaintenanceEnables AI assistants to search leads, view profiles, manage lists, send InMails, and export data from LinkedIn Sales Navigator through browser automation.87 npm15MIT
- AlicenseNot gradedqualityDmaintenanceGives AI assistants the power to find verified emails, phone numbers, and rich contact data from 575M+ professionals across 30M+ companies via GrowthToolkit's API.MIT
- AlicenseAqualityCmaintenanceEnables AI assistants to search leads, view profiles, manage lists, send InMails, and export data by automating LinkedIn Sales Navigator through a logged-in browser session.77 npmMIT