About Sprouts Data Intelligence
From query to qualified lead in seconds.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
Endpoint
https://sprouts-mcp-server.kartikay-dhar.workers.devCopy install command
Claude CodeTerminal
claude mcp add --transport http sprouts https://sprouts-mcp-server.kartikay-dhar.workers.devCursor.cursor/mcp.json
{"mcpServers":{"sprouts":{"type":"http","url":"https://sprouts-mcp-server.kartikay-dhar.workers.dev"}}}Open in CursorVS Code.vscode/mcp.json
{"servers":{"sprouts":{"type":"http","url":"https://sprouts-mcp-server.kartikay-dhar.workers.dev"}}}Open in VS CodeClaude Desktopclaude_desktop_config.json
{"mcpServers":{"sprouts":{"type":"http","url":"https://sprouts-mcp-server.kartikay-dhar.workers.dev"}}}Windsurf~/.codeium/windsurf/mcp_config.json
{"mcpServers":{"sprouts":{"serverUrl":"https://sprouts-mcp-server.kartikay-dhar.workers.dev"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
20| Parameter | Type | Required | Description |
|---|---|---|---|
| page | number | No | Page of results to retrieve, 1-indexed (default: 1). Use this to reach records beyond the first pageSize of a large result set — e.g. pageSize 100 with page 2 returns results 101-200. Each page is a distinct slice; re-run the SAME query with an incremented page to continue. |
| query | string | Yes | Natural language search query - MUST preserve original grammatical structure. CRITICAL: Do NOT remove contextual connectors ("where the company has", "of over", "based in") or simplify working query structures. Examples: ✅"find Marketing Managers where the company has a marketing team of over 50 employees" ❌"find Marketing Managers at companies with marketing team over 50 employees". Always include action words like "find", "search for", but preserve the full grammatical context. |
| ranking | object | No | Optional ranking configuration to prioritize results |
| ranking.weights | object | No | Custom weights for ranking criteria (must sum to 1.0) |
| ranking.weights.companySize | number | No | |
| ranking.weights.industryMatch | number | No | |
| ranking.weights.dataCompleteness | number | No | |
| ranking.weights.jobTitleSeniority | number | No | |
| ranking.weights.locationProximity | number | No | |
| ranking.weights.personalizedBoost | number | No | |
| ranking.boostKeywords | array | No | Keywords to boost in ranking |
| ranking.targetIndustry | string | No | Target industry for matching |
| ranking.targetLocation | string | No | Target location for proximity scoring |
| ranking.penaltyKeywords | array | No | Keywords to penalize in ranking |
| ranking.targetSeniority | string | No | Target seniority level (entry, mid, senior, executive) |
| ranking.targetCompanySize | string | No | Target company size (startup, small, mid-size, large, enterprise) |
| pageSize | number | No | Number of results to retrieve (default: 25, max: 1000 — larger values are clamped). Values above 100 fan out to multiple upstream calls and take proportionally longer; prefer `page` to go deeper instead of huge pages. |
| companies | array | No | With perCompany: the companies to take contacts from (domains preferred, names or LinkedIn URLs work). Up to 25. |
| careerPath | object | No | Career path analysis settings |
| careerPath.enabled | boolean | No | Enable career path analysis |
| careerPath.includeReadiness | boolean | No | Include readiness scoring |
| careerPath.includeProgression | boolean | No | Include career progression data |
| clustering | object | No | Result clustering configuration |
| clustering.enabled | boolean | No | Enable result clustering |
| clustering.strategy | enum | No | Clustering strategyindustry_focused | geographic | seniority_levels |
| clustering.maxClusters | number | No | Maximum number of clusters |
| clustering.minClusterSize | number | No | Minimum cluster size |
| perCompany | number | No | Contacts to return at EACH company in `companies` (e.g. 2 for "2 contacts each"). pageSize and page are ignored when set. |
| recordType | enum | No | What the user wants back: "person" for people/contacts/leads/decision makers, "company" for companies/accounts. Omit only when the request is genuinely ambiguous.person | company |
| refinement | object | No | Optional query refinement configuration |
| refinement.enabled | boolean | No | Enable query refinement analysis |
| refinement.autoApply | boolean | No | Automatically apply refinement suggestions |
| refinement.categories | array | No | Specific categories to analyze for refinement |
| refinement.includeAnalysis | boolean | No | Include detailed analysis in response |
| webResearch | boolean | No | true when the answer depends on live web signals no database filter holds: buying intent or needs ("startups that need website design services", "companies looking for a CRM"), pain points, or recent events and news ("recently announced", "just launched", "opened a new office"). Leave false for firmographic searches (industry, size, location, founded year, funding, technology, titles). |
| booleanQuery | object | No | Boolean query parsing settings |
| booleanQuery.enabled | boolean | No | Enable boolean query parsing |
| booleanQuery.parseComplexQueries | boolean | No | Parse complex AND/OR/NOT queries |
| decisionMaker | object | No | Optional decision maker analysis configuration |
| decisionMaker.industry | string | No | Industry for industry-specific decision maker patterns |
| decisionMaker.saleType | enum | No | Sale type for decision maker analysisenterprise | mid-market | smb |
| decisionMaker.solution | enum | No | Solution type for decision maker contextsoftware | hardware | service | consulting |
| decisionMaker.companySize | string | No | Company size for decision maker multipliers (startup, small, mid-size, large, enterprise) |
| decisionMaker.customRules | object | No | Custom decision maker rules |
| decisionMaker.customRules.titlePatterns | array | No | Job title patterns to boost |
| decisionMaker.customRules.departmentBoost | object | No | Department-specific boosts |
| decisionMaker.customRules.seniorityMultiplier | object | No | Seniority-based multipliers |
| queryHandling | object | No | Query handling and expansion settings |
| queryHandling.preserveNumbers | boolean | No | Lock numerical thresholds to prevent reduction (e.g., keep "100+ employees" exactly as specified) |
| queryHandling.resultThreshold | number | No | Minimum results needed before triggering expansion (default: 0 - only expand when NO results found) |
| queryHandling.expansionStrategy | enum | No | Time-based query expansion aggressiveness levelconservative | moderate | aggressive |
| queryHandling.preserveTimeframe | boolean | No | Lock time periods to prevent expansion (e.g., keep "60 days" exactly as specified) |
| queryHandling.allowTimeExpansion | boolean | No | Allow intelligent timeframe expansion when few results found |
| queryHandling.preserveExactQuery | boolean | No | Preserve exact user query without any modifications |
| queryHandling.notifyModifications | boolean | No | Include notifications about query modifications in response |
| queryHandling.allowNumberExpansion | boolean | No | Allow intelligent number threshold reduction when few results found (e.g., 1000+ employees → 500+ employees) |
| queryHandling.maxExpansionAttempts | number | No | Maximum number of expansion attempts |
| queryHandling.numberExpansionStrategy | enum | No | Number threshold reduction aggressiveness levelconservative | moderate | aggressive |
| fieldSelection | object | No | Field selection for response optimization and token reduction |
| fieldSelection.fields | object | No | Custom field selection (GraphQL-style) |
| fieldSelection.fields.account | array | No | Account/company fields to include |
| fieldSelection.fields.contact | array | No | Contact/person fields to include |
| fieldSelection.fields.analysis | array | No | Enhanced analysis fields to include |
| fieldSelection.fieldSet | enum | No | Pre-defined field set for common use casescontact_essentials | lead_qualification | sales_outreach | decision_maker | company_research | recruiting | market_research | data_enrichment | event_targeting | content_marketing | full_dataset |
| fieldSelection.responseMode | enum | No | Response format modesummary | data | hybrid | current |
| fieldSelection.excludeHighVolume | boolean | No | Exclude high-volume fields that consume many tokens |
| fieldSelection.maxEstimatedTokens | number | No | Maximum estimated tokens for response (warning threshold) |
| applyIcpProfile | boolean | No | Apply ICP profile filters to search results. When enabled, automatically uses your saved ICP criteria (target industries, company sizes, locations, job titles, seniority) to rank and filter results. Prospects matching your ICP will be boosted. Requires an ICP profile to be set up first via icp_analysis tool. |
Details
The maintainer has not added details yet. Check the README in the repository.
Comments
Markdown supported
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.