# DataMerge MCP MCP server

B2B data enrichment for 375M+ companies: legal entities, corporate hierarchies, and contacts.

## Links
- Registry page: https://www.getdrio.com/mcp/ai-datamerge-mcp

## Install
- Endpoint: https://mcp.datamerge.ai
- Auth: Auth required by registry metadata

## Setup notes
- Remote header: Authorization (required; secret)
- The upstream registry signals required auth or secrets.
- Remote endpoint: https://mcp.datamerge.ai
- Header: Authorization

## Tools
- configure_datamerge (Configure DataMerge Authentication) - Configure DataMerge API authentication (required before using other tools if DATAMERGE_API_KEY is not set). Endpoint: https://mcp.datamerge.ai
- start_company_enrichment (Start Company Enrichment) - POST /v1/company/enrich. Enrich one or more companies by domain. Returns a job_id (async). Single: domain. Batch: domains, country_code, global_ultimate, list, skip_if_exists. Endpoint: https://mcp.datamerge.ai
- get_company_enrichment_result (Get Company Enrichment Result) - GET /v1/company/enrich/{job_id}/status. Poll until status is "completed" or "failed". Response includes record_ids. Status values: queued · processing · completed · failed. Endpoint: https://mcp.datamerge.ai
- start_company_enrichment_and_wait (Start Company Enrichment and Wait) - POST /v1/company/enrich then poll GET /v1/company/enrich/{job_id}/status until status is "completed" or "failed" or timeout. Same params as start_company_enrichment plus poll_interval_seconds and timeout_seconds. Endpoint: https://mcp.datamerge.ai
- run_company_enrichment (Run Company Enrichment) - Agent-friendly company enrichment. On the first call provide enrichment params (domain, domains, company_name, country_code, etc.); the server starts the job and polls internally for up to ~25s. If the job is still running, the response will be {status:"pending", continuation_token, attempt, elapsed_seconds}. When you see status "pending" you MUST immediately call run_company_enrichment again with only continuation_token set — do not ask the user, do not call any other tool first. Typical jobs finish within 5 attempts (~125s). On completion the response contains record_ids and full company records. Endpoint: https://mcp.datamerge.ai
- run_contact_enrich (Run Contact Enrich) - Agent-friendly contact enrichment. On the first call provide contacts and enrich_fields; the server starts the job and polls internally for up to ~25s. If still running, returns {status:"pending", continuation_token, attempt, elapsed_seconds} — you MUST immediately call run_contact_enrich again with only continuation_token set. Do not ask the user. Typical jobs finish within 5 attempts. On completion the response contains record_ids and full contact records. Endpoint: https://mcp.datamerge.ai
- run_contact_search (Run Contact Search) - Agent-friendly contact search. On the first call provide domains and enrich_fields; the server starts the job and polls internally for up to ~25s. If still running, returns {status:"pending", continuation_token, attempt, elapsed_seconds} — you MUST immediately call run_contact_search again with only continuation_token set. Do not ask the user. On completion the response contains record_ids, full contact records, and credits_consumed_total. Endpoint: https://mcp.datamerge.ai
- get_company (Get Company) - Get a single company record. GET /v1/company/get?datamerge_id={id} or ?record_id={uuid}. Provide either datamerge_id (charges 1 credit) or record_id (free). Not both. Optional: add_to_list — list slug to add the company to (only with datamerge_id). Endpoint: https://mcp.datamerge.ai
- get_company_hierarchy (Get Company Hierarchy) - Get all entities in the same global ultimate hierarchy. GET /v1/company/hierarchy?datamerge_id={id}. Parameters: include_names (bool, charges 1 credit), include_branches (bool), only_subsidiaries (bool), max_level (int), country_code (array), page (int). Endpoint: https://mcp.datamerge.ai
- start_lookalike (Start Lookalike) - POST /v1/company/lookalike. Find similar companies using seed domains. Returns a job_id (async, 202). Poll GET /v1/company/lookalike/{job_id}/status until completed or failed. Endpoint: https://mcp.datamerge.ai
- get_lookalike_status (Get Lookalike Status) - GET /v1/company/lookalike/{job_id}/status. Poll until status is "completed" or "failed". Response includes record_ids. Endpoint: https://mcp.datamerge.ai
- contact_search (Contact Search) - POST /v1/contact/search. Search for contacts at specified companies. Returns a job_id (async, 202). enrich_fields required (at least one of contact.emails or contact.phones). Use company_list (slug) instead of domains to search a saved list. Endpoint: https://mcp.datamerge.ai
- get_contact_search_status (Get Contact Search Status) - GET /v1/contact/search/{job_id}/status. Poll until status is "completed" or "failed". Response includes record_ids. Endpoint: https://mcp.datamerge.ai
- contact_enrich (Contact Enrich) - POST /v1/contact/enrich. Enrich specific contacts by LinkedIn URL or name+domain. Returns a job_id (async, 202). Endpoint: https://mcp.datamerge.ai
- get_contact_enrich_status (Get Contact Enrich Status) - GET /v1/contact/enrich/{job_id}/status. Poll until status is "completed" or "failed". Response includes record_ids. Endpoint: https://mcp.datamerge.ai
- get_contact (Get Contact) - GET /v1/contact/get?record_id={uuid}. Retrieve a specific contact by record UUID. Never charges credits. Endpoint: https://mcp.datamerge.ai
- list_lists (List Lists) - GET /v1/lists. Optional: object_type=company or object_type=contact. Endpoint: https://mcp.datamerge.ai
- create_list (Create List) - POST /v1/lists. Body: name, object_type (company or contact). Endpoint: https://mcp.datamerge.ai
- get_list_items (Get List Items) - GET /v1/lists/{object_type}/{list_slug}. object_type: company or contact. list_slug: e.g. target-accounts. Parameters: page, page_size (max 100), sort_by, sort_order (asc/desc). Endpoint: https://mcp.datamerge.ai
- remove_list_item (Remove List Item) - DELETE /v1/lists/{object_type}/{list_slug}/{item_id}. Endpoint: https://mcp.datamerge.ai
- delete_list (Delete List) - DELETE /v1/lists/{object_type}/{list_slug}. System lists cannot be deleted. Endpoint: https://mcp.datamerge.ai
- get_credits_balance (Get Credits Balance) - GET /v1/credits/balance. Returns credits_balance and balances (one_off, recurring, rollover, total). Endpoint: https://mcp.datamerge.ai
- health_check (Health Check) - Check if the DataMerge API client is configured and can connect. Uses /auth/info. Endpoint: https://mcp.datamerge.ai
- company_lookalike_fast (Company Lookalike (Fast, Beta)) - POST /v1/company/lookalike/fast. Synchronous lookalike returning raw Ocean candidates without per-candidate enrichment. Lower-latency, lower-cost variant for agent use cases. BETA: requires the `lookalike_fast` flag on the account. Endpoint: https://mcp.datamerge.ai
- contact_search_unenriched (Contact Search (Unenriched, Beta)) - POST /v1/contact/search/unenriched. Find contacts without running email/phone enrichment. Returns a job_id; contacts are created in `unconfirmed` status with stable ids. BETA: requires the `contact_search_unenriched` flag on the account. Endpoint: https://mcp.datamerge.ai
- run_contact_search_unenriched (Run Contact Search (Unenriched, Sync, Beta)) - POST /v1/contact/search/unenriched/sync. Synchronous unenriched contact search — returns contacts inline (no polling). Requires the `contact_search_unenriched` beta flag. Limits: 10 domains and max_results_per_company ≤ 10. Response includes credits_consumed_total computed as 0.5 × len(contacts). Endpoint: https://mcp.datamerge.ai

## Resources
Not captured

## Prompts
- enrich_company_workflow - Enrich Company Workflow Step-by-step prompt for enriching companies by domain using DataMerge. Arguments: domain
- datamerge_quickstart - DataMerge Quick Start Quick reference for connecting and using the DataMerge MCP server.

## Metadata
- Owner: ai.datamerge
- Version: 1.0.0
- Runtime: Streamable Http
- Transports: HTTP
- License: Not captured
- Language: Not captured
- Stars: Not captured
- Updated: Feb 27, 2026
- Source: https://registry.modelcontextprotocol.io