How is this different from connecting Datadog 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 Datadog MCP API changes?

We track the Datadog 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 Datadog 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 Datadog?

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 Datadog MCP server myself?

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

Connect Datadog MCP to your AI agents, securely.

Q: Is Datadog MCP secure?

The server itself exposes 25 tools, and some of them can write to your Datadog 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 Datadog.

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

Get started for free

Get a demo

Try Datadog MCP now

What your agents can ask once Datadog MCP is connected.

Select the tools your AI agents can call

25 tools from the Datadog MCP schema.

Showing 25 tools

search_datadog_eventsreadSearches events like monitor alerts, deployment notifications, infrastructure changes, security findings, and service status changes.
get_datadog_incidentreadRetrieves detailed information about an incident.
search_datadog_dashboardsreadLists available Datadog dashboards and key details.
search_datadog_incidentsreadRetrieves a list of Datadog incidents, including their state, severity, and metadata.
get_datadog_dashboardreadGets the full details of a dashboard.
upsert_datadog_dashboardwriteCreates or updates a Datadog dashboard.
get_datadog_metricreadQueries and analyzes historical or real-time metric data, supporting custom queries and aggregations.
get_datadog_metric_contextreadRetrieves detailed information about a metric or derived metric, including metadata, available tags, and tag values for filtering and grouping.
search_datadog_monitorsreadRetrieves information about Datadog monitors, including their statuses, thresholds, and alert conditions.
search_datadog_metricsreadLists available metrics, with options for filtering and metadata.
get_datadog_tracereadFetches a complete trace from Datadog APM using a trace ID.
search_datadog_spansreadRetrieves spans from APM traces with filters such as service, time, resource, and so on.
aggregate_spansreadAggregates APM spans to compute counts, sums, averages, minimums, maximums, cardinality, and percentiles (p50 to p99).
get_datadog_notebookreadRetrieves detailed information about a specific notebook by ID, including name, status, and author.
search_datadog_notebooksreadLists and searches Datadog notebooks with filtering by author, tags, and content.
delete_datadog_notebookhigh riskSoft-deletes a notebook by its numeric ID; it can be restored within 30 days of deletion.
recover_datadog_notebookwriteRestores a soft-deleted notebook by its numeric ID. The notebook can be restored only within 30 days of deletion.
create_datadog_notebookwriteCreates a new Datadog notebook.
edit_datadog_notebookwriteEdits an existing Datadog notebook.
search_datadog_hostsreadLists and provides information about monitored hosts, supporting filtering and searching.
search_datadog_entitiesreadSearches Datadog’s Catalog for service identity, ownership and upstream and downstream dependencies.
analyze_datadog_logsreadAnalyzes Datadog logs using SQL queries for counting, aggregations, and numerical analysis.
search_datadog_logsreadSearches logs with filters (time, query, service, host, storage tier, and so on) and returns log details.
search_datadog_rum_eventsreadSearches Datadog RUM events using advanced query syntax.
aggregate_rum_eventsreadAggregates RUM events to compute counts, sums, averages, min, max, cardinality, and percentiles, with grouping support.

What Datadog MCP exposes

Datadog MCP groups its 25 tools into 8 categories, each with a suggested starting policy.

All 25 tools as JSON, ready to paste.

Category	Covers	Access	Suggested policy
Logs	Log search with query filters and SQL-based log analysis	Read	Limit access to intended indexes
APM	Span search and aggregation and full trace retrieval	Read	Limit access to intended services
Metrics & Monitors	Metric discovery, timeseries queries and monitor configurations	Read	Allow read-only reporting
Infrastructure	Host inventory and details, and Software Catalog services and dependencies	Read	Allow read-only reporting
Incidents & Dashboards	Ongoing incidents, incident detail, dashboard discovery and details, and dashboard creation and updates	Read / Write	Limit access to incident data
Events	Events such as monitor alerts, deployments, infrastructure changes and security findings	Read	Allow read-only access
Notebooks	Notebook search, details, creation, edits, soft deletion and recovery	Read / Write	Require approval before deleting notebooks
RUM	Real User Monitoring event search and aggregation	Read	Limit access to intended applications

Connect Datadog 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 Datadog
Find Datadog 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 Datadog MCP or block it. You allow the exact tools each agent can call, one by one.

Datadog MCP	25 TOOLS AVAILABLE
Code review agent	4 tools, read only
Issue triage bot	9 tools
Platform team assistant	all 25 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 Datadog 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.	Datadog MCP25 documented tools. 379 more tools in optional toolsets can be enabled with the toolsets parameter of the server URL.
Coding assistants	Connection & credentialsper user	Notebooks6 tools
Internal copilots	Tool access policiesdeny by default	Incidents & Dashboards5 tools
Workflow automations	Request & response inspectioninline	Metrics & Monitors4 tools
Compatible MCP clients	Activity monitoringalerts and logs	All other tools10 tools