Connect
Optimize
Secure
Datadog MCP Server
for AI Agents
Production-ready Datadog MCP server with 26 extensible actions — plus built-in authentication, security, and optimized execution.
Datadog MCP Server
Built by 
StackOne
StackOne 
Coverage
26 Agent Actions
Create, read, update, and delete across Datadog — and extend your agent's capabilities with custom actions.
Authentication
Agent Tool Authentication
Per-user OAuth in one call. Your Datadog MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →
Security
Agent Protection
Every Datadog tool response scanned for prompt injection in milliseconds — 88.7% accuracy, all running on CPU.
Prompt Injection Defense →
Performance
Max Agent Context. Min Cost.
Free up to 96% of your agent's context window to enhance reasoning and reduce cost, on every Datadog call.
Tools Discovery →What is the Datadog MCP Server?
A Datadog MCP server lets AI agents read and write Datadog data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Datadog MCP server ships with 26 pre-built actions, fully extensible via the Connector Builder — plus managed authentication, prompt injection defense, and optimized agent context. Connect it from MCP clients like Claude Desktop, Cursor, and VS Code, or from agent frameworks like OpenAI Agents SDK, LangChain, and Vercel AI SDK.
All Datadog MCP Tools and Actions
Every action from Datadog's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Logs
- Search Logs
Search and filter Datadog logs using log search syntax.
- List Logs
List recent log events from Datadog with optional filtering.
Monitors
- Create Monitor
Create a new monitor to alert on metrics, logs, or other data sources.
- List Monitors
Get all monitors with optional filtering by name, tags, or state.
- Get Monitor
Get details about a specific monitor by its ID.
- Update Monitor
Edit an existing monitor's configuration, thresholds, or notification settings.
Service Definitions
- Create Service Definition
CREATE a new service definition or UPDATE an existing service definition in the Datadog Service Catalog. Use for creating, adding, or registering services.
- List Service Definitions
List all service definitions in the service catalog with ownership and metadata.
- Get Service Definition
Retrieve the service definition for a specific service by name.
- Delete Service Definition
Delete a service definition from the service catalog.
Spans
- Search Spans
Search and filter APM spans/traces for debugging performance issues with latency and error analysis.
- List Spans
Get a list of spans matching a search query with optional time range filtering.
Other (14)
- Create Log Index
Create a new log index in Datadog.
- List Log Indexes
Get all log indexes in the organization.
- List Active Metrics
Get the list of actively reporting metrics from a given time until now.
- Query Metrics
Query timeseries points to get actual metric data values over time.
- Get Metric Metadata
Get metadata about a specific metric.
- Get Metric Tag Configuration
Get the tag configuration for a specific metric.
- List Tags By Metric
View indexed and ingested tags for a given metric name.
- List Service Dependencies
Get all APM service dependencies showing upstream and downstream service relationships.
- List Retention Filters
Get the list of APM retention filters for your organization.
- Aggregate Logs
Compute aggregations and statistics over log data for pattern analysis and error counting.
- Submit Metrics
Submit custom metric data points to Datadog for graphing on dashboards.
- Timeseries Query
Query timeseries data across multiple products (metrics, logs, spans, etc.) with formulas and functions.
- Scalar Query
Get a single aggregated scalar value (not timeseries) from Datadog metrics. Returns one number like average CPU, total count, or max memory for dashboard widgets, alerts, and summary statistics.
- Aggregate Spans
Aggregate spans into buckets and compute metrics and timeseries for latency analysis.
Set Up Your Datadog MCP Server in Minutes
One endpoint. Any framework. Your agent is talking to Datadog in under 10 lines of code.
MCP Clients
Agent Frameworks
JSON{
"mcpServers": {
"stackone": {
"command": "npx",
"args": [
"-y",
"mcp-remote@latest",
"https://api.stackone.com/mcp?x-account-id=<account_id>",
"--header",
"Authorization: Basic <YOUR_BASE64_TOKEN>"
]
}
}
}Datadog MCP Server Resources
MCP Code Mode: Keeping Tool Responses Out of Agent Context
Anthropic's code_execution processes data already in context. Custom MCP code mode keeps raw tool responses in a sandbox. 14K tokens vs 500.
11 min
Comparing BM25, TF-IDF, and Hybrid Search for MCP Tool Discovery
Benchmarking BM25, TF-IDF, and hybrid search for MCP tool discovery across 916 tools. The 80/20 TF-IDF/BM25 hybrid hits 21% Top-1 accuracy in under 1ms.
10 min
Indirect Prompt Injection Defense for MCP Tools: A Technical Guide
MCP tools that read emails, CRM records, and tickets are indirect prompt injection vectors. Here's how we built a two-tier defense that scans tool results in ~11ms.
12 min
Datadog MCP Server FAQ
Datadog MCP server vs direct API integration — what's the difference?
A Datadog MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Datadog. A Datadog MCP server is for AI agents — MCP clients like Claude and Cursor, plus framework agents built with OpenAI, LangChain, or Vercel AI — discovering and calling Datadog at runtime. StackOne provides both.
How does Datadog authentication work for AI agents?
Datadog authentication for AI agents works through a StackOne Connect Session. Create one via the dashboard or the SDK — you get an auth link and ready-to-paste config for Claude Desktop, Cursor, and other MCP clients. Your user authenticates their own Datadog account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via
origin_owner_id.Are Datadog MCP tools vulnerable to prompt injection?
Yes — Datadog MCP tools can be vulnerable to indirect prompt injection. Any tool that reads user-written content — documents, messages, tickets, records, or free-text fields — is a potential vector. StackOne Defender scans every tool response before it enters the agent's context — regex patterns in ~1ms, then a MiniLM classifier in ~4ms. 88.7% accuracy, CPU-only.
What is the context bloat of a Datadog agent and how do I avoid it?
Context bloat happens when Datadog tool schemas and API responses eat your Datadog agent's memory, preventing it from reasoning effectively. A single Datadog query can return a massive JSON response, and connecting multiple tools compounds the problem. Tools Discovery and Code Mode reduce context bloat — loading only relevant tools per query and keeping raw responses out of the agent's context.
Can I limit which actions my Datadog agent can access?
Yes — you can limit which actions your Datadog agent can access directly from the StackOne dashboard. Toggle actions on or off, or restrict them to specific accounts, with no code changes to your agent. Session tokens can be scoped to exact actions so if one leaks, exposure stays contained.
Can I create custom agent actions for my Datadog MCP server?
Yes — you can create custom agent actions for your Datadog MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Datadog's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Datadog MCP server?
Skip a Datadog MCP server if your integration is purely software-to-software — direct Datadog API integration is simpler when no AI agent is involved. For deterministic, compliance-critical operations (financial transactions, regulatory reporting), direct API gives you predictable behavior without agent-driven decision-making. MCP shines when AI agents need to dynamically discover and call Datadog actions at runtime.
What AI frameworks and AI clients does the StackOne Datadog MCP server support?
The StackOne Datadog MCP server supports both. MCP clients (paste-and-go apps): Claude Desktop, Claude Code, Cursor, VS Code, Goose. Agent frameworks (code SDKs you build with): OpenAI Agents SDK, Anthropic, Vercel AI, Google ADK, CrewAI, Pydantic AI, LangChain, LangGraph, Azure AI Foundry.
Put your AI agents to work
All the tools you need to build and scale AI agent integrations, with best-in-class connectivity, execution, and security.