DatadogSAFE
MCP server interacts with the official Datadog API
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
A Model Context Protocol (MCP) server for interacting with the Datadog API.
Features
- Monitoring: Access monitor data and configurations
- Dashboards: Retrieve and view dashboard definitions
- Metrics: Query available metrics and their metadata
- Events: Search and retrieve events within timeframes
- Logs: Search logs with advanced filtering and sorting options
- Incidents: Access incident management data
- API Integration: Direct integration with Datadog's v1 and v2 APIs
- Comprehensive Error Handling: Clear error messages for API and authentication issues
- Service-Specific Endpoints: Support for different endpoints for logs and metrics
Prerequisites
- Node.js (version 16 or higher)
- Datadog account with:
- API key - Found in Organization Settings > API Keys
- Application key - Found in Organization Settings > Application Keys
Application Key Scopes
For improved security, you can scope your Application Key to grant only the minimum permissions required by this MCP server. By default, Application Keys inherit all permissions from the user who created them, but scoped Application Keys allow you to follow the principle of least privilege.
Required Scopes
The following scopes are required for the corresponding features:
e7416aea0e77OBSERVED · 2026-10-07Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add datadog-mcp-server --env DD_API_KEY=${DD_API_KEY} --env DD_APP_KEY=${DD_APP_KEY} -- npx -y [email protected]{
"mcpServers": {
"datadog-mcp-server": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"DD_API_KEY": "${DD_API_KEY}",
"DD_APP_KEY": "${DD_APP_KEY}"
}
}
}
}Exposed tools (10)
10 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
aggregate-logs | read | Perform analytical queries and aggregations on log data. Essential for calculating metrics (count, avg, sum, etc.), grouping data by fields, and creating statistical summaries from logs. Use this when you need to analyze patterns or extract metrics from log data. |
get-dashboard | read | Get the complete definition of a specific Datadog dashboard by its ID. Returns all widgets, layout, and configuration details. |
get-dashboards | read | Retrieve a list of all dashboards from Datadog. Useful for discovering available dashboards and their IDs for further exploration. |
get-events | read | Search for events in Datadog within a specified time range. Events include deployments, alerts, comments, and other activities. Useful for correlating system behaviors with specific events. |
get-incidents | read | List incidents from Datadog |
get-metric-metadata | read | Retrieve detailed metadata about a specific metric, including its type, description, unit, and other attributes. Use this to understand a metric |
get-metrics | read | List available metrics from Datadog. Optionally use the q parameter to search for specific metrics matching a pattern. Helpful for discovering metrics to use in monitors or dashboards. |
get-monitor | read | Get detailed information about a specific Datadog monitor by its ID. Use this to retrieve the complete configuration, status, and other details of a single monitor. |
get-monitors | read | Fetch monitors from Datadog with optional filtering. Use groupStates to filter by monitor status (e.g., |
search-logs | read | Search logs in Datadog with advanced filtering options. Use filter.query for search terms (e.g., |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (2 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (2)
@datadog/datadog-api-client, @modelcontextprotocol/sdk, dotenv, minimist, typescript, zod, @types/minimist
> **Note**: If you don't specify any scopes when creating an Application Key, it will have full access with all permissions of the creating user. For production use, we recommend always specifying exp
Gates applied: no_behavioural_pass.
e7416aea0e77full audit observations/trust-audit/mcp-server/geli2001__datadog-3.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-07 | e7416aea0e77 | SAFE | B | 89 | first audit |
Questions
What is the Datadog MCP server?
MCP server interacts with the official Datadog API
What tools does Datadog expose?
10 in total: 10 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Datadog safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Datadog need?
It reads DD_API_KEY and DD_APP_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Datadog run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as datadog-mcp-server at 1.0.8.
How current is this page?
The grade is for one exact copy of the source (e7416aea0e77), read on 2026-10-07. The repository is watched and re-audited when it changes.