Datadog
BetaObservability platform for logs, metrics, traces, monitors, incidents, security signals, and synthetic tests.
- Observability
- Monitoring
- Security
- Authentication
- OAuth 2.0
- Authorization
- Enterprise-managed
- Hosting
- Vendor-hosted endpoint
- Data actions
- Read and write
How it works
Every agent request passes through Ferentin policy before it reaches Datadog.
Datadog's Remote MCP Server (Preview) exposes 49+ tools across 8 toolsets — core, alerting, APM, networks, onboarding, security, synthetics, and workflows. Scope agents to specific toolsets via a URL query parameter. User mode uses OAuth 2.0 with PKCE; agent mode uses API Key + Application Key headers scoped to a service account with least privilege.
- AI agentAsks for something
- Ferentin policies
- OAuth 2.0 PKCE
- Scoped API keys
- Service accounts
- Regional endpoints
- Datadog MCP serverAuthorized connection
- Governed resultMasked, logged, returned
What agents can do
75 tools · you choose which ones agents may callEvery tool this server exposes. You choose which ones agents may call.
- aap_onboarding
- Aggregate Events
- Aggregate RUM Events
- Aggregate Spans
- analyze_cloud_network_monitoring
- Analyze Datadog Logs
- Analyze Security Findings
- Analyze Security Signals
- Analyze Security Findings
- browser_onboarding
- code_coverage_onboarding
- Workload Protection Agent Events Schema
- devices_onboarding
- Diff Network Device Configurations
- docker_onboarding
- ecs_onboarding
- generate_monitor_message
- Get Change Stories
- Get Dashboard
- Get Incident
- Get Metrics
- Get Metric Context
- Get Notebook
- List AAP Denylist Entries
- Get Datadog Security Detection Rule
- Get Datadog Security Detection Rules Schema
- Security Findings Schema
- Get Ticket Suggestions
- Get Security Signal
- Get Security Signals Schema
- Get Security Suppressions
- List AAP Allowlist Entries
- Get Trace
- Get Workflow
- Get Instance
- get_monitor_coverage
- get_monitor_templates
- Get Network Device
- Get Network Device Configuration
- Get Network Path Test Runs
- Get Synthetics Tests
- kubernetes_onboarding
- linux_onboarding
- List Datadog Security Detection Rules
- List Datadog Skills
- List Workflows
- llm_observability_onboarding
- Load Datadog Skill
- monitor_groups_search
- recommend_monitor_threshold
- Search Workload Protection Agent Events
- List Dashboards
- Get Events
- List Hosts
- List Incidents
- Search Logs
- List Metrics
- Get Monitors
- Search Notebooks
- Search RUM Events
- Search Security Findings
- Search Security Signals
- List Service Dependencies
- List Services
- search_datadog_slos
- List Spans
- Search Network Devices
- Search Network Interfaces
- Search Network Device Configurations
- serverless_onboarding
- source_map_uploads
- studio_onboarding
- test_optimization_onboarding
- validate_monitor_definition
- check_datadog_mcp_setup
Before you connect
- Toolset scoping: the bare endpoint returns ONLY the 'core' toolset (the default when 'toolsets' is omitted). Use '?toolsets=all' to enable all generally-available toolsets, or list a subset to keep the agent's tool surface focused.
- Toolset names are hyphenated (e.g. 'error-tracking', 'feature-flags', 'software-delivery') — use them exactly as published.
- Use '?omit_tools=' (comma-separated tool names) to drop specific tools from whatever the toolsets selection produced.
- Region is host-based, not a query parameter: point the instance endpoint at your Datadog site's MCP host (US1/US3/US5/EU/AP1/AP2/GovCloud).
About Datadog
Datadog is a cloud-scale observability and security platform used for infrastructure monitoring, APM, log management, incident response, and cloud security. It supports multi-region data sovereignty (US1, EU, US3/GovCloud, US5, AP1) and is HIPAA-eligible.
Frequently asked about Datadog
- What can AI agents do with Datadog through Ferentin?
- Through Ferentin, agents can use Datadog for log analysis, metric querying, distributed tracing, monitor management, slo tracking, security signals, network monitoring, synthetic tests and workflow execution. Every call is checked against your Ferentin policies first.
- How is Datadog access secured?
- Requests through the Datadog integration are covered by OAuth 2.0 PKCE, scoped API keys, service accounts, regional endpoints, hipaa eligible and audit logging. These controls are applied by Ferentin, not by Datadog, so they hold across every connected agent.
- How do I connect Datadog to Ferentin?
- Open the Ferentin admin console, add Datadog as a new connection and authenticate with OAuth 2.0. You then choose which permissions and which tools your agents may use, and the connection goes live for everyone covered by your policies.
- Is the Datadog integration generally available?
- The Datadog integration is currently beta on Ferentin.
Related integrations
3
AWS
Managed AWS MCP Server providing access to 15,000+ AWS APIs, documentation, and infrastructure workflows.
Supabase
Open source Firebase alternative with Postgres database, auth, edge functions, and real-time subscriptions.
GitHub
Development platform for version control, collaboration, and CI/CD workflows.