How is this different from connecting Amplitude MCP directly?

Connected directly, an agent sees every tool the server exposes and holds the credential itself. Through TrustGate you choose which tools each agent gets, and every call is logged against the agent that made it.

What if the Amplitude MCP API changes?

We track the Amplitude MCP schema, so the tool catalogue stays current. Tools you have already allowed keep working, and anything new stays denied until you enable it.

Can I give different agents different Amplitude tools?

Yes. Access is set per agent: one can get a handful of read tools, another the full set. You grant the whole MCP or single tools within it.

Where can I see what my agents did in Amplitude?

Every call is logged against the agent that made it, with the tool it used. Activity can be sent on to your own monitoring.

Do I need to run the Amplitude MCP server myself?

No. TrustGate connects to the Amplitude MCP server and sits in front of it. Your agent only talks to your TrustGate URL, never to Amplitude directly.

Connect Amplitude MCP to your AI agents, securely.

Q: Is Amplitude MCP secure?

The server itself exposes 45 tools, and some of them can write to your Amplitude account. Behind TrustGate an agent only sees the tools you allow, requests and responses are inspected, and every call is logged. Anything outside the allowlist is denied before it reaches Amplitude.

One secured endpoint for every Amplitude call your AI agents make, scoped per user, inspected, and logged.

Get started for free

Get a demo

Try Amplitude MCP now

What your agents can ask once Amplitude MCP is connected.

Select the tools your AI agents can call

45 tools from the Amplitude MCP schema.

Showing 45 tools

searchreadSearches for charts, dashboards, notebooks, experiments, events, properties, cohorts and other Amplitude content.
get_from_urlreadRetrieves the full object definition from any Amplitude URL, including charts, dashboards and experiments.
get_amplitude_contextreadGets the current user, organization and accessible projects, or the settings of a given project.
use_amp_dashboardswriteGets, creates and edits dashboards, including their metadata and the layout of charts and sections.
use_amp_notebookswriteGets, creates and edits interactive notebooks with charts, rich text and multi-column layouts.
use_amp_commentswriteReads and adds comments on Amplitude content.
share_amp_entitieshigh riskManages sharing and access roles for charts, dashboards, notebooks and other Amplitude entities.
query_experimentreadAnalyses experiment results and statistical significance.
get_experimentsreadLists the experiments and feature flags in a project.
create_experimentwriteCreates an experiment or feature flag.
use_amplitude_cohortswriteRetrieves, creates and syncs cohorts, checks cohort membership and exports cohort CSVs.
update_experimentwriteSets or replaces the metrics on an experiment.
create_metricwriteCreates reusable metrics (KPIs) for experiments or dashboards.
get_flagsreadRetrieves feature flag definitions by ID, including variants and configuration.
create_flagswriteCreates multiple feature flags in a batch.
update_flagwriteUpdates a feature flag or experiment's metadata, variants, testers and deployments.
get_deploymentsreadRetrieves the deployments (API keys for flags and experiments) of a project.
get_agent_resultsreadGets the results of an agent session by session ID.
get_amplitude_agent_analytics_inforeadQueries AI agent analytics: quality, cost, performance, error and trend metrics, sessions, spans and transcripts.
query_amplitude_datareadRuns ad-hoc analytics queries such as event segmentation, funnels and retention, and queries existing charts by ID.
get_amplitude_chartsreadRetrieves chart definitions and data by ID, including events, properties and configuration.
render_amplitude_chartreadRenders an interactive Amplitude chart from a query definition and returns a chart edit URL.
use_amplitude_chart_monitorswriteCreates, reads and manages chart alerts and monitors, including alert history.
get_amp_user_datareadRetrieves user profiles, properties and activity timelines for a project.
get_amp_taxonomyreadReads a project's tracking plan: events, properties, branch changes or change history.
manage_amp_eventshigh riskCreates, updates, deletes and restores events, custom events and labeled events in the tracking plan.
manage_amp_propertieshigh riskCreates event, user and group properties, and updates, deletes and restores event and user properties.
get_transformationsreadRetrieves a project's data transformations, such as merged events, merged properties and mapped values.
get_group_typesreadLists a project's group types, such as Company, Team or Account.
manage_amp_taxonomyhigh riskManages the tracking-plan branch workflow: creating, updating, deleting, merging, reviewing and refreshing branches.
get_session_replaysreadSearches session replays from the last 30 days, filtered by user properties or events.
list_session_replaysreadLists session replays with time-range pagination.
get_session_replay_eventsreadRetrieves the processed interaction timeline of a session replay recording.
list_guides_surveysreadLists the guides and surveys in a project, with filters by type, platform, creator, date and archived status.
get_guide_or_surveyreadRetrieves the full details of a guide or survey, including variants, step content, targeting and triggers.
use_amplitude_ai_feedbackreadQueries and analyses customer feedback from connected sources, grouped into themes such as feature requests and bugs.
query_wave_opportunitiesreadSearches and retrieves Wave opportunities and their details.
query_wave_product_areasreadSearches and retrieves Wave product areas.
manage_wave_opportunitieswriteCreates, updates and relates Wave opportunities.
manage_wave_product_areaswriteCreates and updates Wave product areas.
manage_wave_verification_artifactswriteAttaches and manages verification artifacts on Wave opportunities.
get_data_ingestion_sourcesreadLists a project's ingestion sources, including SDKs, warehouse imports and third-party integrations.
get_data_source_detailsreadGets the configuration and metadata of one ingestion source.
get_data_warehouse_destinationsreadLists a project's export destinations with type, status and last export time.
get_data_warehouse_jobsreadGets the batch job history of an import source or export destination, including status, records and errors.

What Amplitude MCP exposes

Amplitude MCP groups its 45 tools into 9 categories, each with a suggested starting policy.

All 45 tools as JSON, ready to paste.

Category	Covers	Access	Suggested policy
Search & Content	Searching charts, dashboards, notebooks, experiments, cohorts, events and properties, and resolving Amplitude URLs	Read / Write	Limit to the projects in scope
Query	Ad-hoc segmentation, funnels, retention, chart queries and metric queries	Read / Write	Watch query cost on large date ranges
Cohorts & Experiments	Cohort listing and creation, experiment results and feature flags	Read / Write	Approve cohort and experiment changes; they affect live targeting
Taxonomy	Tracking plan events and properties, read and write	Read / Write	Require approval for taxonomy changes; they affect reporting
Agent Analytics	AI agent session investigation and results	Read	Treat session content as potentially sensitive
Session Replay	Session replay search, listing and interaction timelines	Read	Allow; replays can contain user behaviour data
Guides, Surveys & Feedback	Guide and survey listing and details, and analysis of customer feedback themes	Read	Allow
Wave	Wave opportunities, product areas and verification artifacts	Read / Write	Allow queries; review writes to opportunities and product areas
Data Warehouse	Ingestion sources, warehouse export destinations and import or export job history	Read	Allow

Connect Amplitude MCP to your AI agent

Four steps, under ten minutes.

01
Sign in to NeuralTrust
Open the NeuralTrust platform, sign in and go to Getting started, then Connect your tools.
02
Choose your agent
When asked which agent you use, pick Claude Code, Codex, Cursor, Windsurf, Copilot or your own code.
03
Connect Amplitude
Find Amplitude in the tool list and connect it.
04
Connect your agent
Follow the steps on screen to add the config to your agent, then send the test prompt.

Permissions down to the single tool

You do not allow Amplitude MCP or block it. You allow the exact tools each agent can call, one by one.

Amplitude MCP	45 TOOLS AVAILABLE
Code review agent	4 tools, read only
Issue triage bot	9 tools
Platform team assistant	all 45 tools

Tool by toolConnecting the server is not the unit of access. Each tool is granted on its own.
Default denyA tool you have not enabled is never exposed to the agent.
Approval on writesTools that change or delete things can require a human to confirm.

Is Amplitude MCP secure?

One endpoint instead of raw credentials. Every call is checked against policy and logged.

AI agentsConnect through your MCP client configuration.	NeuralTrustApply controls based on your configuration.	Amplitude MCP45 documented tools.
Coding assistants	Connection & credentialsper user	Cohorts & Experiments10 tools
Internal copilots	Tool access policiesdeny by default	Search & Content7 tools
Workflow automations	Request & response inspectioninline	Taxonomy6 tools
Compatible MCP clients	Activity monitoringalerts and logs	All other tools22 tools