configure_datamerge
Configure DataMerge API authentication (required before using other tools if DATAMERGE_API_KEY is not set).
LABSCO SUMMARY
Publishing both the raw async pair and a continuation-token version is the most agent-aware design here.
Polling loops are where agents waste turns — call, wait, call again, lose track. The run_* tools fold that into a single conversation with a continuation token, while the raw tools stay available for anything that needs control. get_contact is worth noting separately: the description says it never charges, which is exactly the kind of thing a credit-metered API should tell a model before it calls in a loop. Corporate hierarchy is the differentiator against cheaper enrichment: knowing a domain's global ultimate parent is what makes account mapping possible.
What it is
DataMerge's endpoint, which lists 23 tools. Nearly every operation exists twice: a raw pair that returns a job id you poll, and a run_* variant that manages the waiting for you.
What you get
- run_company_enrichment, run_contact_enrich, run_contact_search — agent-friendly: first call sends the parameters, then a continuation token carries the rest
- start_company_enrichment and get_company_enrichment_result — the raw async pair, plus a start_and_wait variant
- get_company and get_company_hierarchy — a record, or every entity under the same global ultimate parent
- contact_search and contact_enrich with their status pollers, and get_contact by record id
- Lists: list_lists, create_list, get_list_items, remove_list_item
- configure_datamerge — set the API key at runtime if it is not in the environment
Requirements
An API key as Authorization: Token. Credit-based and pay-per-lookup: one credit for a company record or a validated email, four for a mobile number, nothing upfront.
Setup effort
Paste a URL with a key — add the endpoint to your client
USE CASES
01
Enriching a list of domains
Use the agent-friendly tool so the polling is handled and the conversation is not a loop.
02
Mapping an account's real footprint
Pull every entity under the same global ultimate parent rather than treating one domain as the company.
03
Finding people at target accounts
Search contacts by domain and job title, then enrich the ones that matter.
04
Keeping the credit spend down
Re-reading a record by id is documented as free; a mobile number costs four credits.
23 tools
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
contact_enrich
POST /v1/contact/enrich. Enrich specific contacts by LinkedIn URL or name+domain. Returns a job_id (async, 202).
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.
contact_search_unenriched
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.
create_list
POST /v1/lists. Body: name, object_type (company or contact).
delete_list
DELETE /v1/lists/{object_type}/{list_slug}. System lists cannot be deleted.
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).
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.
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).
get_contact
GET /v1/contact/get?record_id={uuid}. Retrieve a specific contact by record UUID. Never charges credits.
get_contact_enrich_status
GET /v1/contact/enrich/{job_id}/status. Poll until status is "completed" or "failed". Response includes record_ids.
get_contact_search_status
GET /v1/contact/search/{job_id}/status. Poll until status is "completed" or "failed". Response includes record_ids.
get_credits_balance
GET /v1/credits/balance. Returns credits_balance and balances (one_off, recurring, rollover, total).
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).
health_check
Check if the DataMerge API client is configured and can connect. Uses /auth/info.
list_lists
GET /v1/lists. Optional: object_type=company or object_type=contact.
remove_list_item
DELETE /v1/lists/{object_type}/{list_slug}/{item_id}.
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.
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.
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.
run_contact_search_unenriched
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 computed as 0.5 × len(contacts).
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.
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.
BEFORE YOU INSTALL
What to know first
Tools you get
23 tools when we connected.
Requires
- an MCP client that can reach a remote endpoint
- API key(header Authorization: Token <api-key>)
CONTEXT COST
Light Standing cost
Rated by the size of the 23 tool definitions that ride along on every turn, not by how many there are
INSTALLATION
Connect your client
Add the endpoint to your client.
Server setup
ENDPOINT URL
https://mcp.datamerge.aiRequirements
- API key(header Authorization: Token <YOUR_API_KEY>)
