search
Search for charts, dashboards, notebooks, experiments, events, properties, cohorts, and other Amplitude content.
65 tools over Amplitude — charts, cohorts, experiments, flags and taxonomy — free on every plan, with an EU endpoint.
The plugin Knowledge Work Plugins includes connection settings for this server.
LABSCO SUMMARY
Sixty-five tool definitions in every request is a real cost, and most vendors either ignore it or split into several servers. Amplitude offers a mode where the client starts small and asks for more — the correct fix, and rare. The other thing worth noting is that the taxonomy tools write: an agent here can rename events and change their official status, which is governance data other teams depend on. The admin-level org switch exists for exactly that reason.
Amplitude's endpoint, documented across 13 category tables. It has a progressive discovery mode that starts with a small tool list and lets the client find the rest, which matters when 65 definitions would otherwise ride in every request.
OAuth against your Amplitude account, scoped by the organisation's RBAC. Free for every customer including the Free plan. Org admins can allow or block MCP org-wide under Settings → Content Access → MCP, and users cannot override that.
Paste a URL, then authorize — add the endpoint to your client, then approve the OAuth consent screen
USE CASES
Resolve the Amplitude URL straight to its definition instead of asking what the chart measures.
Pull the experiment with its variants and decision details, plus the flags and deployments behind it.
Find the untidy events and properties, then update names, categories and official status.
Connect in progressive discovery mode so the client loads tools as it needs them.
Listed in project docs. Your client may show a different list.
searchSearch for charts, dashboards, notebooks, experiments, events, properties, cohorts, and other Amplitude content.
get_from_urlRetrieve the full object definition from any Amplitude URL, including charts, dashboards, and experiments.
get_amplitude_contextGet the current user, organization, and accessible projects. Call it with a project ID to get that project's settings instead, including time zone, currency, session definition, and AI context.
get_workspace_contextGet settings information about a Data project or portfolio.
get_chartsRetrieve full chart definitions by ID, including events, properties, and configuration.
get_dashboardRetrieve dashboards and all their charts, including chart IDs for individual queries.
get_cohortsRetrieve cohort definitions by ID, including audience criteria and metadata.
get_experimentsRetrieve experiments by ID with state, variant configuration, and decision details.
get_usersRetrieve user data from a project.
get_flagsRetrieve feature flag definitions by ID, including variants and configuration.
get_deploymentsRetrieve all deployments (API keys for flags and experiments) for a project.
get_agent_resultsRetrieve results from AI agents that analyzed your dashboards or session replays.
get_eventsRetrieve events from a project, with filtering by event type, a result limit, and cursor pagination.
get_propertiesRetrieve properties from a project's taxonomy. Use propertyType to select event, user, group, derived, or other property kinds.
update_propertiesUpdate a property's description, category, name, or official status. Use propertyType to select the kind of property to update.
get_custom_or_labeled_eventsRetrieve custom events, labeled (autotrack) events, or both, with optional filtering by ID or name, a result limit, and pagination.
update_custom_or_labeled_eventsUpdate the description, category, name, official status, or definition (source events and filters) of custom or labeled events.
update_eventUpdate an event's metadata, including its name, description, category, and official status.
get_transformationsRetrieve data transformations from a project. Transformations clean data by merging events, merging properties, or mapping property values.
get_group_typesList a project's group types, the categories of groups, such as Company, Team, or Account.
get_session_replaysSearch for session replays from the last 30 days, filtered by user properties or events.
list_session_replaysList session replays with simple time-range pagination.
get_session_replay_eventsRetrieve processed interaction timelines from a session replay recording.
query_chartQuery a single chart by ID and return its data.
query_chartsQuery up to three charts concurrently by ID and return their data.
query_amplitude_dataExecute ad-hoc analytics queries for event segmentation, funnels, retention, and more using a two-mode discover/execute workflow.
query_experimentQuery experiment analysis data, including variant performance and statistical significance.
render_chartRender a visual, interactive Amplitude chart from a query definition and return a chart edit URL.
save_chart_editsSave edits to existing charts or convert temporary chart edits into permanent saved charts.
create_dashboardCreate dashboards with charts, rich text, and custom layouts.
create_notebookCreate interactive notebooks with charts, rich text, and multi-column layouts.
create_experimentCreate A/B test experiments across one or more projects with custom variants and metrics.
create_cohortCreate cohorts based on user properties and behaviors.
create_flagsCreate multiple feature flags in batch.
create_metricCreate reusable metrics (KPIs) for use in experiments or dashboards.
create_eventsCreate new events or add ingested unexpected events to a project's tracking plan.
create_custom_eventCreate a custom event composed of one or more source events with optional filters.
create_propertiesCreate event, user, or group properties in a project's tracking plan.
get_cohort_sync_destinationsList cohort sync destinations configured for a project.
get_cohort_syncsList cohort syncs and their destination, cadence, and status.
get_cohort_sync_historyRetrieve sync history for a cohort sync, including added, removed, and skipped users.
sync_cohortTrigger a one-time cohort sync to a destination such as Braze, Iterable, S3, or a webhook. The tool previews the export and asks for confirmation before sending.
get_branchesList all branches in a project's tracking plan, including the main branch.
create_branchCreate a new branch in a project's tracking plan, forked from the main branch.
update_branchUpdate the description of a branch in a project's tracking plan.
refresh_branchPull the latest changes from main into a feature branch.
merge_branchMerge a branch into the main branch.
delete_branchPermanently delete a branch and all its uncommitted tracking plan changes.
edit_dashboardEdit an existing dashboard's metadata (title, description) and layout (add charts, remove charts, reorder sections) with optimistic concurrency protection to prevent conflicting edits.
edit_notebookEdit an existing notebook's metadata (title, description) and layout (add or remove charts, text blocks, and other content sections) with optimistic concurrency protection.
update_experimentSet or replace metrics on an experiment.
update_flagUpdate a feature flag or experiment's metadata, variants, testers, and deployments.
list_guides_surveysList guides and surveys in a project, with filters by type, platform, creator, date range, and archived status. Returns status, priority, and creator metadata for each item.
get_guide_or_surveyRetrieve full details for a single guide or survey by ID, including status, priority, variants, step content, page targeting rules, and trigger configuration.
use_amplitude_ai_feedbackQuery and analyze customer feedback from connected sources. Retrieves processed themes grouped by type (feature requests, bugs, complaints, praise, and pain points), raw comments with search and pagination, individual comments associated with a specific insight, connected feedback integrations and their source IDs, and saved customer feedback trends tracked over time.
query_agent_analytics_metricsAggregate quality, cost, performance, error, and trend metrics across AI agent sessions.
query_agent_analytics_sessionsList and filter AI agent sessions by quality, cost, sentiment, user, topic, or agent with optional groupBy aggregation.
query_agent_analytics_spansInspect individual operations (LLM calls, tool invocations) within AI agent traces for latency and error analysis.
get_agent_analytics_conversationRetrieve the full conversation transcript for an AI agent session.
search_agent_analytics_conversationsFull-text search across AI agent conversation content for specific keywords or topics.
get_agent_analytics_schemaDiscover available fields, rubric definitions, and filter values (agent names, tools, topics) for agent analytics queries.
get_data_ingestion_sourcesList ingestion sources for a project, including SDKs, warehouse imports, and third party integrations.
get_data_source_detailsGet configuration and metadata for one ingestion source.
get_data_warehouse_destinationsList export destinations for a project, including type, status, and last export timing.
get_data_warehouse_jobsGet batch job history for one import source or export destination: status, timing, records processed, errors, and failure reason.
BEFORE YOU INSTALL
65 tools named in the project's documentation.
INSTALLATION
Add the endpoint to your client, then approve the OAuth consent screen.
https://mcp.amplitude.com/mcpFor EU data residency, connect to https://mcp.eu.amplitude.com/mcp instead. For progressive discovery mode, append ?discovery=progressive to either URL (for example https://mcp.amplitude.com/mcp?discovery=progressive): the client starts with a small tool list plus list_tool_categories, get_category_tools and describe_tool, and loads the rest as it needs them.