Zeotap MCP server
Yes. Zeotap publishes an official MCP server at https://mcp.zeotap.com/mcp. It's hosted. It offers 131 tools. We last checked it on 22 Nov 2026.
Official: answers MCP requests at mcp.zeotap.com, on Zeotap's own domain zeotap.com. Checked 22 Nov 2026. Maintained by Stuart Brameld.
Key facts
As of 22 Nov 2026, Zeotap's official MCP server scores 65/100 (provisional) on MartechDB's Agent Readiness Index (v1.1). It answered 55 of our 55 checks in the last 90 days and has 131 tools named in its documentation.
How the Agent Readiness Index works · Wrong? Suggest a correction
Zeotap MCP server review
65/100
Zeotap's MCP server scores 65/100 on MartechDB's Agent Readiness Index: easy to connect an AI agent to, with a few gaps.
The good
Hosted by Zeotap: connect by URL, with nothing to install
Documented, with 131 tools known
Answered 100% of our checks in the last 90 days
The bad
Nothing we've found.
Not checked yet: how you sign in; what agent access costs. Anything not checked scores nothing.
Official MCP server
Zeotap MCP server
- Address
- https://mcp.zeotap.com/mcp
- Runs
- Hosted
- Sign-in
- Vendor docs
- Official MCP Registry
- Not listed
- How we know it's official
-
- Answers MCP requests at mcp.zeotap.com, on Zeotap's own domain zeotap.com.
- Documentation
- composable-docs.zeotap.com/agent-smith/mcp-server
- Tools
- 131 tools · from Zeotap's documentation
- First seen
- 1 Oct 2026
- Last checked
-
Reachable ·
16 Nov 2026: reachable17 Nov 2026: reachable18 Nov 2026: reachable19 Nov 2026: reachable20 Nov 2026: reachable21 Nov 2026: reachable22 Nov 2026: reachable
- Uptime
- 100% · 55 of 55 checks reachable since 1 Oct 2026
Zeotap MCP server tools (131)
The server needs sign-in before it lists its tools, so these are as Zeotap's documentation names them (read 10 Nov 2026). They may be out of date.
-
list_modelsList the data models in the workspace — name, entity type, source table, keys, status and column count.
-
get_modelGet detailed information about a specific model — columns, types, primary key, entity type, SQL, and column_config.
-
list_relationshipsList all entity relationships (joins) connecting parent, related, and event models in the workspace.
-
list_traitsList all computed attributes (aggregated values) defined on parent or related models in the workspace.
-
list_audiencesList the audiences in the workspace, with name, parent model, estimated size, status, folder and tags.
-
get_audienceGet an audience's full filter tree, parent model, estimated size, and sync status.
-
estimate_audience_sizeEstimate the row count matching a filter tree against a parent model without creating an audience.
-
validate_filter_nodeValidate a FilterNode JSON structure for correctness without executing it.
-
compile_filterCompile a FilterNode tree into SQL and return the estimated size; useful before saving an audience.
-
create_audienceCreate a new audience from a FilterNode tree.
-
update_audienceUpdate an existing audience's name, description, filter tree, or status.
-
list_audience_canvasesList all audience canvases in the workspace, with parent model, audience count, and when each was last published.
-
get_audience_canvasGet a canvas's draft nodes and edges, its published version, and its parent model.
-
validate_canvas_changesetValidate proposed nodes and edges before saving or publishing — cycles, unwired tiles, missing audience names.
-
create_audience_canvasCreate a new, empty canvas on a parent model, optionally routed through an identity graph.
-
update_canvas_draftReplace a canvas's draft nodes and edges.
-
publish_audience_canvasPublish the current draft, compiling every Create Audience tile and materialising the audiences it owns.
-
create_traitCreate a new computed attribute on a parent entity model.
-
update_traitUpdate a computed attribute's name, description, configuration, result type, or status.
-
trigger_trait_evaluationTrigger an optional manual refresh of computed attributes for a parent model and return a run ID for tracking.
-
create_modelCreate a model from a warehouse table or custom SQL.
-
update_modelUpdate an existing model's name, description, columns, SQL, entity type, or status.
-
update_column_configSet per-column sensitivity levels, PII types, display aliases, and enabled state.
-
update_column_descriptionsDescribe what a model's columns mean (partial update).
-
create_relationshipCreate a relationship (join) between two models, enabling event and relation conditions in audience filters.
-
list_sourcesList the configured data sources (input warehouses) in the workspace, with type and status.
-
introspect_sourceList all database schemas available in a source connection.
-
list_tablesList all tables in a specific schema of a source connection.
-
list_columnsList all columns in a specific table, including name, data type, and nullability.
-
get_warehouse_contextGet the full data model context — models, columns, relationships, computed attributes, event schema, and system tables.
-
query_warehouseExecute a read-only SQL query against a data warehouse; one SELECT statement only, capped at 500 rows, results masked.
-
write_warehouseExecute a write SQL statement (INSERT, UPDATE, CREATE TABLE); DELETE, DROP, ALTER, TRUNCATE are blocked.
-
list_destinationsList the configured destinations (output targets), with type and status.
-
create_destinationCreate a new destination (Snowflake, BigQuery, Databricks, webhook, etc.) for syncing audience or model data.
-
list_syncsList the Reverse ETL syncs in the workspace — model, destination, mode, schedule, and status.
-
list_audience_syncsList the audience syncs — audience, destination, mode, schedule and status.
-
create_audience_syncCreate a new audience sync linking an audience to a destination, with field mapping, sync mode, and schedule.
-
trigger_syncTrigger a Reverse ETL sync to execute immediately. Returns the sync run ID.
-
trigger_audience_syncTrigger an audience sync to execute immediately.
-
pause_syncPause a Reverse ETL sync.
-
resume_syncResume a Reverse ETL sync and reset its failure count.
-
pause_audience_syncPause an audience sync.
-
resume_audience_syncResume an audience sync, whether a person or repeated failures paused it.
-
list_sync_runsList recent runs for a model sync or an audience sync (newest first) — status, timing, row counts, batch counts, and errors.
-
get_sync_runGet the status and metrics of a single sync run.
-
list_loadersList all loaders (inbound ELT connectors) — type, source, target schema, streams, schedule, status, and last-run summary.
-
list_loader_runsList recent load runs for a loader (newest first) — status, timing, rows loaded, per-stream counts, and errors.
-
get_loader_runGet the status and metrics of a single load run.
-
list_storesList all stores in the workspace, with primary index and status.
-
get_storeGet a single store by ID.
-
list_store_feedsList the feeds attached to a store — model, deletion behaviour, schedule, and last refresh.
-
list_store_feed_runsList a feed's recent refresh runs, with rows added, updated and deleted, status, and any error.
-
create_storeCreate a store. The primary index is the row key and cannot be changed afterwards.
-
archive_storeArchive a store. Its feeds stop running.
-
create_store_feedAttach a feed that mirrors one parent-entity model into the store.
-
update_store_feedRename, reschedule, or remap a feed, or change its deletion behaviour.
-
delete_store_feedDelete a feed. Data already written to the store is not removed.
-
trigger_store_feedRefresh a feed immediately. Returns the run ID.
-
resume_store_feedResume a feed that auto-paused after repeated failed refreshes.
-
list_identity_graphsList all ID graphs in the workspace.
-
get_identity_graphGet the full configuration of an ID graph — metadata plus models, identifiers, merge rules, limits, and probabilistic rules.
-
create_identity_graphCreate a new ID graph with full configuration in one call.
-
update_identity_graphUpdate an ID graph's metadata.
-
configure_identity_graph_rulesConfigure models, identifiers, merge rules, limit rules, and probabilistic rules for an ID graph (partial update).
-
delete_identity_graphDelete an ID graph permanently — definition, models, identifiers, rules, run history, and golden-record configs.
-
list_identity_graph_runsList recent resolution runs for an ID graph (newest first) with status, timing, and metrics.
-
get_identity_graph_runGet details for a specific ID graph resolution run.
-
trigger_identity_graph_runTrigger or cancel an ID graph resolution run.
-
explore_identity_graphLook up a resolved profile by an identifier value — returns the unified profile (ss_id) and all source rows.
-
configure_golden_recordCreate or update the golden-record configuration (survivorship rules) for an ID graph.
-
get_golden_recordRead a unified profile's golden record by ss_id or by identifier, with the attribute definitions and source ranking behind each value.
-
get_profile_membersReturn the source rows of one model that belong to a resolved profile (ss_id), with their column values.
-
get_profile_relatedFollow one registered relationship out from a profile and return the related model's rows.
-
get_profile_lineageExplain why a profile's records merged: the identity edges inside the cluster, which rows were linked, on which identifier, at what confidence.
-
get_golden_record_lineageExplain, attribute by attribute, where a profile's golden-record values came from.
-
get_model_recordRead one row of a model by its primary key, with its visible column values.
-
get_model_record_relatedFollow one registered relationship out from a single model record and return the related rows, without an identity graph.
-
list_realtime_eventsList all realtime events in the workspace — stream-sourced related events declared on a parent model.
-
list_model_realtime_eventsList the realtime events declared on one parent model.
-
get_realtime_eventGet one realtime event, including its event source, event type, parent relationship, and its filterable property catalog.
-
create_realtime_eventDeclare a realtime event on a parent model, bound to the existing event-ingest spine.
-
update_realtime_eventUpdate a realtime event's editable fields.
-
delete_realtime_eventDelete a realtime event; refused while any audience filter still references it.
-
list_journeysList all orchestrations in the workspace.
-
get_journeyGet full details of an orchestration — tiles, edges, entry/exit criteria, schedule, status, and last run info.
-
create_journeyCreate a new orchestration (starts in draft status).
-
update_journeyUpdate an orchestration's name, description, tiles, edges, or schedule.
-
delete_journeyDelete an orchestration permanently.
-
validate_journeyValidate the DAG structure — cycles, dangling edges, missing tiles, schedule correctness.
-
activate_journeyActivate an orchestration (draft/paused -> active), provisioning warehouse tables and scheduling.
-
pause_journeyPause an active orchestration. Existing member state is preserved.
-
resume_journeyResume a paused orchestration.
-
trigger_journeyManually trigger an evaluation run for an active orchestration.
-
list_journey_runsList recent evaluation runs for an orchestration with status, timing, and per-tile metrics.
-
get_journey_runGet details for a specific orchestration run, including evaluation metrics.
-
cancel_journey_runCancel a pending or running orchestration evaluation.
-
list_event_keysList all event source write keys in the workspace, with name, value, status, topic, and last-used timestamp.
-
get_event_volumeGet hourly event volume metrics for the workspace over the last 7 days, grouped by event type and name.
-
list_event_contractsList all event contracts — schemas, enforcement modes, and undeclared-field handling.
-
list_event_contract_violationsList event contract violations — type, field path, expected vs received values, sample event ID, count.
-
list_event_forwarding_rulesList event forwarding rules — destination, event filter, transformation, field mapping, consent, rate limit.
-
list_event_transformationsList event transformations — JavaScript functions that modify event payloads before forwarding.
-
get_event_warehouse_configGet the event warehouse configuration — source ID, schema, staging bucket, and enabled status.
-
list_predictive_modelsList the workspace's predictive models with each model's current version: headline metrics, whether they could be measured, and any suspected leakage.
-
get_predictive_modelGet one model: its training configuration, versions with metrics and top feature importance, recent training runs, and where its scores are served.
-
get_predictive_training_runGet one training run's status, estimated and measured cost, and the version it produced.
-
check_predictive_readinessCheck whether a warehouse has the grants, schemas and features predictive models need, with a remediation for each failing check.
-
estimate_predictive_training_costEstimate one training run's cost as a range without starting it, and whether it would exceed the model's cost budget.
-
create_predictive_modelCreate a trained model over a parent model; a cost budget above zero is required.
-
trigger_predictive_trainingStart training now; above the approval threshold the call returns pending_approval.
-
promote_predictive_versionPropose promoting a version; always returns pending_approval.
-
list_predictive_scoring_runsList a model's most recent scoring runs: when it last scored everyone, with which version, how many rows, and how far the score distribution moved.
-
get_predictive_scoreGet one entity's served score and percentile, for an id the client already has.
-
get_predictive_score_distributionSummarise a model's served scores without listing anyone: row count, range, mean, and each decile's score range.
-
list_featuresList the feature library, optionally for one parent model, so a client can name feature_ids when creating a model.
-
list_predictive_retention_batchesList the superseded versions proposed for clean-up.
-
ingest_byo_predictionsRegister scores the customer already computes in their warehouse as a predictive model, so audiences can filter on them.
-
retry_byo_viewRetry creating the scores view of a bring-your-own model whose view failed.
-
update_predictive_modelChange a trained model's training configuration, algorithm or number of kept versions, for its next training run.
-
pause_predictive_modelPause a model: its schedules, automatic retrain on drift and stale-score checks stop, while its current scores stay in place.
-
resume_predictive_modelResume a paused model.
-
rescore_predictive_modelPropose rescoring a trained model with its promoted version; always returns pending_approval.
-
reject_predictive_training_runReject a training run the model's cost budget parked, so it never runs.
-
delete_predictive_modelDelete a model and its versions and runs; refused if an audience, canvas, journey, rule, subset or template filters on it.
-
list_anomaliesList anomalies found by the background monitor, newest first — metric, resource, observed vs usual, severity, open or resolved, and the root-cause analysis once written.
-
get_anomalyGet one anomaly with the evidence its analysis was written from.
-
dismiss_anomalyDismiss an open anomaly that will never recover because the change was intended, recording why.
-
ack_incidentAcknowledge one of the workspace's alert incidents: record that somebody is on it.
-
mute_incidentMute one of the workspace's alert incidents until a time or indefinitely, recording why.
-
check_approval_statusCheck the status of a pending guardrail approval.
-
get_workspace_memoryRetrieve durable facts learned about this workspace — naming conventions, quirks of the data model, pitfalls hit before, team preferences.
Connect your AI to Zeotap
Add the official Zeotap MCP server to Claude, ChatGPT or your editor.
Connect Zeotap MCP to Claude
Claude.ai and Claude Desktop
Open Customize, then Connectors.
Click +, then Add custom connector.
Name it Zeotap, paste the address below and click Add.
Connect Zeotap MCP to ChatGPT
Open Settings, then Apps, then Advanced settings.
Turn on Developer mode, then click Create.
Name it Zeotap and paste the address below.
ChatGPT usually only connects to servers with self-serve sign-in or none.
Connect Zeotap MCP to Cursor
Opens Cursor if it's installed. If nothing happens, use the JSON below.
Connect Zeotap MCP to VS Code
Opens VS Code if it's installed. Otherwise add the JSON settings from the Cursor tab to your .vscode/mcp.json.
Zeotap MCP server questions
Does Zeotap have an official MCP server?
Yes. Zeotap publishes its MCP server itself. Its address is on Zeotap's own domain (mcp.zeotap.com). MartechDB only lists servers a vendor publishes, never community copies.
What is the Zeotap MCP server URL?
The address is https://mcp.zeotap.com/mcp.
How do I connect Zeotap MCP to Claude, ChatGPT or Cursor?
In Claude, add https://mcp.zeotap.com/mcp as a custom connector (Customize, Connectors, Add custom connector). In Cursor, use the Add to Cursor link on MartechDB's page, or paste the JSON settings into your mcp.json. In Claude Code, run: claude mcp add --transport http zeotap https://mcp.zeotap.com/mcp
What can the Zeotap MCP server do?
It offers 131 tools, including list_models, get_model, list_relationships, list_traits and list_audiences (as its documentation names them, read on 10 Nov 2026).
Is the Zeotap MCP server in the official MCP Registry?
No. Zeotap hasn't published it to the official MCP Registry.
Is the Zeotap MCP server working?
Yes. It answered our most recent check. We last checked it on 22 Nov 2026.
What are the alternatives to Zeotap's MCP server?
In Customer data, the most agent-friendly alternatives with an official MCP server are ChatGPT in Google Sheets (100/100), Octoparse (94/100), MrScraper (91/100), Sparktoro (88/100) and Attensira (88/100). Zeotap scores 65/100 on the same index.
Alternatives to Zeotap's MCP server
Vendors in Customer data with an official MCP server, the most agent-friendly first. Zeotap scores 65/100.
ChatGPT in Google Sheets
twominutereports.com
Octoparse
octoparse.com
MrScraper
mrscraper.com
Sparktoro
sparktoro.com
Attensira
attensira.com
Use with AI
Connect your AI to MartechDB
Then ask it about Zeotap, or any of the 1,850 marketing tools with an official MCP server. Free, no sign-in.
Claude.ai and Claude Desktop
Open Customize, then Connectors.
Click +, then Add custom connector.
Name it MartechDB, paste the address below and click Add. There's no sign-in.
The free plan allows one custom connector. On Team and Enterprise plans, an owner adds the connector first.
Claude Code
Run this in your terminal:
ChatGPT
Open Settings, then Apps, then Advanced settings.
Turn on Developer mode, then click Create.
Name it MartechDB, paste the address below and choose No authentication.
Developer mode is on Plus and Pro plans, and on Business, Enterprise and Edu if an admin allows it.
API
The same data as JSON, with no sign-in. See the OpenAPI description for every endpoint and field.
CLI
Search the directory and print the command to connect a vendor's server, from your terminal. Needs Node 18 or later. View on npm
Show that your MCP server is verified
If you work at Zeotap, add this badge to your MCP docs or README. It's free, it's the same for every vendor, and it updates from our daily checks: it shows uptime while the server responds, and says so if it stops.
Something wrong or out of date? Suggest a correction or email us, and we'll check it against the evidence. Every correction we make is listed on Corrections.