The NextDNS MCP server exposes 70+ NextDNS API operations as MCP tools, allowing AI assistants to fully manage NextDNS DNS filtering profiles and analyze DNS traffic.
Profile Management: Create, list, get, update, and delete NextDNS profiles. Set read-only or read/write access restrictions per profile.
DNS-over-HTTPS (DoH) Testing: Test how a profile resolves any domain, supporting all DNS record types (A, AAAA, CNAME, MX, TXT, NS, etc.).
Settings Configuration: Manage logs (retention, enable/disable), block page, performance options (EDNS Client Subnet, cache boost, CNAME flattening), and DNS rewrites.
Logs: Retrieve DNS query logs with filtering by date range, device, status, and domain; supports pagination. Clear all logs for a profile.
Analytics (11 endpoints): Query status, top domains, query types, block reasons, client IPs, DNSSEC validation, encryption usage, IP versions, protocol usage, destinations (by country or GAFAM), and per-device stats — many with time-series charting.
Denylist & Allowlist: Full CRUD operations on blocked/allowed domains, including bulk replace and enable/disable per entry.
Security: Configure threat intelligence feeds, DNSSEC, DNS rebinding protection, cryptojacking, typosquatting, NRD, DGA, CSAM, AI threat detection, Google Safe Browsing, and TLD blocking.
Privacy: Manage disguised trackers, affiliate link blocking, third-party privacy blocklists (e.g., EasyList), and native tracking protection (Alexa, Roku, Samsung, etc.).
Parental Controls: Configure safe search, YouTube restricted mode, block bypass prevention, blocked services (TikTok, Facebook, etc.), and blocked content categories (gambling, adult content, etc.).
Provides tools for managing NextDNS profiles, settings, logs, analytics, security, privacy, parental controls, and content lists via the NextDNS API.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@nextdns-mcp get my recent DNS query logs"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A Model Context Protocol (MCP) server for the NextDNS API, built with FastMCP and generated from OpenAPI specifications.
This project provides an MCP server that exposes NextDNS API operations as tools that can be used by AI assistants and other MCP clients. The server is automatically generated from a comprehensive OpenAPI specification using the FastMCP library.
Related MCP server: Cloudflare Control
Domain-grouped CRUD tools exposing the full NextDNS API surface through ~8 high-level tools
Profile Management: Full CRUD operations - create, read, update, and delete profiles
Profile Access Control: Fine-grained read/write restrictions per profile, with read-only mode support
DNS-over-HTTPS Testing: Perform DoH lookups to test DNS resolution through profiles
Settings Configuration: Comprehensive grouped settings management including logs, block page, and performance
Logs: Query log retrieval, download, and clearing
Analytics: Comprehensive DNS query analytics and statistics, including time-series and plotting
Content Lists: Manage denylist, allowlist, privacy blocklists, native tracking, security TLDs, and parental control
Security: Complete security settings and TLD blocking configuration
Privacy: Privacy settings, blocklists, and native tracking protection management
Parental Control: Settings management with safe search and YouTube restrictions
OpenAPI-backed: Tool behaviors are driven by nextdns-openapi.yaml
Docker MCP Gateway: Full integration with Docker's MCP Gateway for secure, isolated deployment
Docker Support: Containerized deployment with proper OCI labels
Safety Mechanisms: Write operation protections and validation
Complete documentation can be found in docs/index.md.
Python 3.12+
uv (for development)
Docker (for containerized deployment)
NextDNS API key (get one here)
Copy the .env.example file to .env:
cp .env.example .envEdit .env and set your NextDNS API key:
NEXTDNS_API_KEY=your_api_key_here
NEXTDNS_DEFAULT_PROFILE=your_profile_id # Optional
NEXTDNS_TEST_PROFILE=test_profile_id # For write operation tests
# Optional: Profile access control (see Profile Access Control section)
# NEXTDNS_READABLE_PROFILES=profile1,profile2
# NEXTDNS_WRITABLE_PROFILES=test_profile
# NEXTDNS_READ_ONLY=falseBuild the Docker image:
docker build -t nextdns-mcp:latest .Run the container with environment variables:
Option A: Direct environment variables (simple)
docker run -i --rm \
-e NEXTDNS_API_KEY=your_api_key_here \
-e NEXTDNS_DEFAULT_PROFILE=your_profile_id \
nextdns-mcp:latestOption B: Docker secrets (recommended for production)
# Create secret
echo "your_api_key_here" | docker secret create nextdns_api_key -
# Run with Docker Swarm
docker service create \
--name nextdns-mcp \
--secret nextdns_api_key \
-e NEXTDNS_API_KEY_FILE=/run/secrets/nextdns_api_key \
nextdns-mcp:latestOr for non-swarm (using mounted file):
# Create a secret file
echo "your_api_key_here" > /tmp/api_key.txt
chmod 600 /tmp/api_key.txt
# Run with mounted secret
docker run -i --rm \
-v /tmp/api_key.txt:/run/secrets/nextdns_api_key:ro \
-e NEXTDNS_API_KEY_FILE=/run/secrets/nextdns_api_key \
nextdns-mcp:latestOption C: Environment file (development)
docker run -i --rm \
--env-file .env \
nextdns-mcp:latestNote: MCP servers use stdio (standard input/output) for communication, not HTTP ports.
Alpine variant
An Alpine Linux image is also available. To build it locally, use Dockerfile.alpine:
docker build -f Dockerfile.alpine -t nextdns-mcp:alpine .The published Alpine tags use the -alpine suffix (e.g. nextdns-mcp:alpine, nextdns-mcp:2.0-alpine). The python:3.14-slim image remains the recommended default.
Install dependencies:
uv syncRun the server:
uv run python -m nextdns_mcp.serverThis server uses a modern, declarative approach:
OpenAPI Specification (nextdns-openapi.yaml): Complete NextDNS API documentation
FastMCP Foundation: Server initialized using FastMCP.from_openapi(), with atomic tools removed and replaced by grouped CRUD tools
HTTP Client: Authenticated httpx.AsyncClient with profile-level access control for NextDNS API calls
MCP Protocol: Tools, resources, and prompts exposed via Model Context Protocol
src/nextdns_mcp/nextdns-openapi.yaml: OpenAPI 3.0 specification for NextDNS API
src/nextdns_mcp/server.py: FastMCP server implementation
catalog.yaml: Docker MCP Gateway catalog entry with server metadata
Dockerfile: Container definition with OCI labels for MCP Gateway
AGENT.md: Development guidelines and safety rules
This project publishes official Docker images with a standardized tagging policy. The default image is based on python:3.14-slim; an Alpine Linux variant is also available and tagged with an -alpine suffix.
python:3.14-slim) tags:latest: Floating tag that tracks the most recent successful build from the main branch. This tag is rebuilt on changes to main and via scheduled rebuilds.
:<major>: Floating tag for the most recent build in a given major series (e.g., :2). This tag is updated whenever a new image for that major line is published and may include unreleased changes if the corresponding build comes from a branch head.
:<major>.<minor>: Floating tag for the most recent build in a given minor series (e.g., :2.0). Like :<major>, it is updated when new images are built for that series and may include unreleased changes.
:<major>.<minor>.<patch>: Tags for specific application releases (e.g., :2.0.3). These are intended to be immutable once published via the release workflow.
:alpine: Floating tag for the most recent Alpine build from main.
:<major>-alpine: Floating tag for the most recent Alpine build in a major series (e.g., :2-alpine).
:<major>.<minor>-alpine: Floating tag for the most recent Alpine build in a minor series (e.g., :2.0-alpine).
:<major>.<minor>.<patch>-alpine: Specific Alpine release tag (e.g., :2.0.3-alpine).
All floating tags (:latest, :<major>, :<major>.<minor> and their -alpine counterparts) are rebuilt regularly to include the latest OS security updates and any application changes present in the source commit used for that build. Consumers who require strict version pinning should use the full :<major>.<minor>.<patch> or :<major>.<minor>.<patch>-alpine tags.
This project is released under the MIT License.
See AGENT.md for guidelines and architecture
Note that NextDNS does not provide an OpenAPI specification. This is based on their documentation and may not reflect the current state of the API.
Perform a DNS-over-HTTPS lookup using a NextDNS profile.
| Name | Required | Description | Default |
|---|---|---|---|
| domain | Yes | The domain name to look up (e.g., "adwords.google.com") | |
| profile_id | No | NextDNS profile ID. If not provided, uses NEXTDNS_DEFAULT_PROFILE. | |
| record_type | No | DNS record type to query (default "A"). | A |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must carry the full burden of behavioral disclosure. It does indicate a dependency on a NextDNS profile and the DNS-over-HTTPS protocol, but does not explicitly state that this is a read-only operation or describe any side effects, error behavior, or rate limits. For a simple lookup tool, this is adequate but not thorough.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence with no fluff or repetition. It efficiently conveys the core action and resource, making it appropriately concise for a simple lookup tool.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has a simple parameter set and an output schema exists, so return values are documented elsewhere. However, the description omits usage guidance and some behavioral context, making it minimally complete but not richly helpful for an agent deciding when and how to invoke it.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with detailed descriptions for all three parameters. The description itself adds no parameter-specific meaning beyond what the schema already provides, so the baseline score of 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool performs a DNS-over-HTTPS lookup, with the specific resource (NextDNS profile) mentioned. This distinctively separates it from sibling tools that manage profiles, settings, lists, or analytics.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for DNS lookups but provides no explicit guidance on when to use this tool versus alternatives. It lacks any exclusions or alternative recommendations, though the sibling tool set makes the intended use reasonably clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Manage allow/deny/block lists for a NextDNS profile.
List types:
- allowlist / denylist: Always-allow or always-block specific domains.
- privacy_blocklists: Subscribed blocklists (e.g., nextdns-recommended).
- privacy_natives: Native tracking blockers (e.g., apple, facebook).
- security_tlds: Dangerous top-level domains to block (e.g., zip).
- parental_categories: Content categories (e.g., gambling, porn).
- parental_services: Specific apps/services (e.g., tiktok, youtube).
Operations:
- get: Return the current list.
- add: Append one entry (pass entry as {"id": "value"} or as a plain id string).
- remove: Delete one entry by entry_id.
- update: Toggle an existing entry by entry_id (pass entry={"active": True|False}).
Only supported for allowlist, denylist, parental_categories, and
parental_services.
- replace: Replace the entire list with entries (list of dicts).
Examples:
- get: manageLists(list_type="denylist", operation="get", profile_id="abc123")
- add: manageLists(list_type="denylist", operation="add", profile_id="abc123", entry={"id": "example.com"})
- remove: manageLists(list_type="denylist", operation="remove", profile_id="abc123", entry_id="example.com")
- replace: manageLists(list_type="privacy_blocklists", operation="replace", profile_id="abc123", entries=[{"id": "nextdns-recommended"}])
| Name | Required | Description | Default |
|---|---|---|---|
| entry | No | ||
| entries | No | ||
| entry_id | No | ||
| list_type | Yes | ||
| operation | Yes | ||
| profile_id | Yes |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, but description clearly explains the effect of each operation (get, add, remove, update, replace) and notes that update is only supported for specific list types. Could be improved by mentioning idempotency or error handling.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Well-structured with bullet points and examples. Front-loaded with purpose, then lists types, operations, and examples. Every sentence adds value without redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of 6 parameters and multiple operations/list types, the description is comprehensive. It covers all operations, provides concrete examples, and notes constraints. An output schema exists but isn't needed for completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With 0% schema coverage, the description fully compensates by explaining each parameter, including format for entry and entries, and providing concrete examples. It adds significant meaning beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states it manages allow/deny/block lists for NextDNS profiles, listing all list types and operations. It distinguishes well from sibling tools like manageProfiles and manageRewrites.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides detailed operations, supported list types for update, and examples for each operation. However, it doesn't explicitly state when to use this tool vs siblings or when not to use it for certain scenarios.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Manage query logs for a NextDNS profile.
Operations:
- get: Return recent query log entries (use limit to cap results).
Set raw=true to bypass deduplication/noise filtering.
- clear: Delete all stored logs for the profile.
- download: Download retained logs as CSV. from_time and to_time are
ignored by the NextDNS download endpoint.
Time values can be Unix timestamps or relative strings like -1d or -7d.
They are only used by get.
Examples:
- get recent: manageLogs(operation="get", profile_id="abc123", limit=10)
- get raw logs: manageLogs(operation="get", profile_id="abc123", raw=true)
- download: manageLogs(operation="download", profile_id="abc123", from_time="-1d")
- clear: manageLogs(operation="clear", profile_id="abc123")
| Name | Required | Description | Default |
|---|---|---|---|
| raw | No | ||
| user | No | ||
| limit | No | ||
| device | No | ||
| to_time | No | ||
| from_time | No | ||
| operation | Yes | ||
| profile_id | Yes |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description discloses key behaviors: clear is destructive, raw bypasses filtering, from_time/to_time ignored by download. It does not mention rate limits or authentication, but the output schema likely covers return format.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured with sections for operations, time values, and examples. It is front-loaded and efficient, though the examples repeat the tool name unnecessarily.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a multi-operation tool with an output schema, the description gives sufficient context for core behaviors and parameters. However, missing explanation for user/device and no mention of output format (though schema exists) keep it from a 5.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%, so description must explain parameters. It covers operation, profile_id, limit, raw, from_time/to_time well, but omits user and device. This partial coverage leaves some parameters undocumented.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool manages query logs for a NextDNS profile and lists three distinct operations (get, clear, download). It explicitly identifies the resource and actions, distinguishing it from siblings like dohLookup or manageLists.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides context for each operation (e.g., get with limit, raw; clear deletes all; download with ignored time parameters). However, it does not explicitly guide when to use this tool over alternatives like manageSettings, leaving some ambiguity.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Manage NextDNS profiles.
NextDNS profiles are named configurations that contain DNS settings, blocklists,
analytics, and logs. Most other tools require a profile_id from this tool.
Operations:
- list: Return all profiles the API key can access.
- create: Create a new profile (requires name).
- get: Retrieve a single profile (requires profile_id).
- update: Rename a profile (requires profile_id and name).
- delete: Remove a profile (requires profile_id).
Examples:
- list: manageProfiles(operation="list")
- create: manageProfiles(operation="create", name="Home Network")
- get: manageProfiles(operation="get", profile_id="abc123")
| Name | Required | Description | Default |
|---|---|---|---|
| name | No | ||
| operation | Yes | ||
| profile_id | No |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. Describes operations as CRUD but lacks details on side effects (e.g., that delete is irreversible) or permission requirements. Adequate but could be more explicit about destructive actions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Well-structured with overview, operations list, and examples. Every sentence adds value, front-loaded with purpose. No superfluous text.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (multiple operations, 3 params, 0% schema coverage, output schema exists), the description fully covers how to use each operation, links to other tools, and provides examples. Complete and self-contained.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so description compensates by explaining the role of each parameter (name for create/update, profile_id for get/update/delete) and the operation enum. Adds meaning beyond schema (e.g., 'rename a profile' for update). Good but could clarify that profile_id comes from list operation.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states it manages NextDNS profiles, enumerates five operations (list, create, get, update, delete), and explains that other tools require a profile_id from this tool. This distinguishes it from sibling tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides explicit context for each operation including required parameters (name for create/update, profile_id for get/update/delete). Indicates that other tools depend on this one for profile_id. Does not explicitly state when not to use this tool versus alternatives, but gives clear direction per sub-operation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Manage DNS rewrite entries for a NextDNS profile.
Rewrites let you return a custom answer for a hostname. Typical uses:
Point an internal hostname to a private IP.
Block a domain by rewriting it to 0.0.0.0.
Operations:
- list: Show existing rewrites.
- add: Create a rewrite (requires name and content).
- delete: Remove a rewrite (requires entry_id from list).
Examples:
- list: manageRewrites(operation="list", profile_id="abc123")
- add: manageRewrites(operation="add", profile_id="abc123", name="router.home", content="192.168.1.1")
- delete: manageRewrites(operation="delete", profile_id="abc123", entry_id="router.home")
| Name | Required | Description | Default |
|---|---|---|---|
| name | No | ||
| content | No | ||
| entry_id | No | ||
| operation | Yes | ||
| profile_id | Yes |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so description carries burden. It details that add creates, list shows existing, delete removes, and dependencies on entry_id from list. This is transparent for a CRUD operation, but lacks info on permissions or rate limits. Score 4.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Description is well-structured, concise, and front-loaded with purpose. Examples are efficient. Score 5.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With output schema present, description need not explain return values. It covers operations and parameter requirements. It is complete for managing rewrites, given sibling tools context. Score 4.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%, but description compensates by explaining the operation enum and required params for each operation with examples. It clarifies that name and content are needed for add, entry_id for delete. Score 4.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool manages DNS rewrite entries, distinguishes from sibling tools (manageProfiles, etc.) by focusing on rewrites. Provides specific verb and resource (manage rewrites) and explains typical use cases.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
While the description explains the operations and examples, it does not explicitly tell when to use this tool over siblings. Implicitly, it's for rewrites, but lacks 'when not to use' guidance. Score 3 because some guidance is provided through examples but not explicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Manage a settings category for a NextDNS profile.
Settings categories:
- general: Core profile settings (e.g., name, web3 blocking).
- privacy: Privacy features such as disguised-tracker blocking and affiliate links.
- security: Threat intelligence, Google Safe Browsing, typosquatting protection.
- parental: Parental control enablement (safe search, YouTube restricted mode).
- performance: ECS, cache boost, and other performance options.
- logs: Query-logging enablement and retention.
- blockpage: Whether to show a custom block page for blocked queries.
Operations:
- get: Retrieve current settings for the category.
- update: Apply new settings (requires settings payload).
The settings argument can be a Python dict or a JSON string. For update,
first call get to see the current schema, then send only the fields you want
to change.
Examples:
- get: manageSettings(operation="get", category="privacy", profile_id="abc123")
- update: manageSettings(operation="update", category="privacy", profile_id="abc123", settings={"disguisedTrackers": True})
| Name | Required | Description | Default |
|---|---|---|---|
| category | Yes | ||
| settings | No | ||
| operation | Yes | ||
| profile_id | Yes |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It discloses the two operations, the requirement for a settings payload on update, the ability to send only specific fields to change (implying partial updates), and the accepted formats for settings (dict or JSON string). It does not mention side effects, permissions, or rate limits, but for a settings tool, the key behaviors are covered.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured with clear sections for categories and operations, followed by practical examples. It is appropriately sized for the complexity of the tool, with every sentence providing valuable information and no redundant content.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity and the presence of an output schema, the description is complete. It covers all categories, operations, and usage nuances (e.g., partial updates), and provides examples that demonstrate correct invocation. It fully prepares an agent to use the tool effectively without needing to consult external resources.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds substantial meaning beyond the schema: it explains each category enums with examples (e.g., privacy includes disguised-tracker blocking), clarifies the operation enums, and details the settings argument as a Python dict or JSON string with instructions to use get first for update. The examples also illustrate how to pass profile_id and settings. This richly compensates for the 0% schema coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool manages a settings category for a NextDNS profile, then enumerates the specific categories and operations (get/update). This distinguishes it from sibling tools by focusing on settings categories rather than profiles, lists, or rewrites.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives explicit guidance on when to use get vs update, instructing users to call get first to see the current schema before updating. It provides concrete examples for both operations. However, it does not explicitly mention when not to use this tool or contrast it with alternatives like manageProfiles or manageLists, though the domain is clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Generate a PNG line chart for a NextDNS analytics time-series metric.
Use this to visualize query trends over time. The profile should have recent query history; otherwise the tool returns an error explaining that no data is available.
Supported metrics: status, devices, protocols, queryTypes,
ipVersions, dnssec, encryption, reasons, ips.
Time values can be Unix timestamps or relative strings like -1d.
Examples:
- plotAnalytics(metric="status", profile_id="abc123", from_time="-1d")
- plotAnalytics(metric="devices", profile_id="abc123", from_time="-7d", interval=86400)
Returns: An MCP ImageContent PNG chart, or an error dict if data is unavailable.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| metric | Yes | ||
| to_time | No | now | |
| interval | No | ||
| partials | No | none | |
| timezone | No | GMT | |
| alignment | No | end | |
| from_time | No | -1d | |
| profile_id | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It discloses return type (PNG ImageContent or error), and mentions error condition. Lacks details on auth, rate limits, or performance but is adequate for basic transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Description is well-structured with clear sections for purpose, supported metrics, time formats, examples, and return type. It is moderately concise; examples add length but improve clarity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given high parameter count (9), no annotations, and no output schema, the description is incomplete. It covers key aspects but ignores many parameters and doesn't describe chart content or relationship to sibling `queryAnalytics`.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, requiring description to explain parameters. It covers `metric` and `time` formats (from_time), and provides examples. However, it does not explain 7 other parameters (limit, interval, etc.), leaving significant gaps.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states it generates a PNG line chart for NextDNS analytics time-series, specifying action and resource. It does not explicitly differentiate from sibling `queryAnalytics` but implicitly distinguishes by mentioning chart output vs raw data.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Describes when to use (visualize query trends), notes prerequisite (recent query history), and lists supported metrics. Does not explicitly state when not to use or compare to alternatives, but provides examples for clarity.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Query NextDNS analytics metrics.
Metrics:
- status: Query resolution status (default, blocked, allowed, relayed).
- devices: Queries per device.
- protocols: DNS transport protocol (DoH, DoT, Do53 UDP/TCP, DoQ).
- queryTypes: DNS record types requested (A, AAAA, CNAME, etc.).
- ipVersions: IPv4 vs IPv6 queries.
- dnssec: DNSSEC validation results.
- encryption: Encrypted vs unencrypted queries.
- reasons: Why queries were blocked or allowed.
- ips: Top source IPs.
- destinations: Top destinations; requires destination_type such as
countries or gafam.
Set series=true to fetch time-series data instead of aggregate totals.
Time values can be Unix timestamps or relative strings like -1d.
Note: series=true is not supported when metric="domains".
Optional filters:
- cursor: Pagination cursor from a previous response.
- device: Filter analytics to a single device id.
- status: For the domains metric, filter by resolution status.
- root: For the domains metric, group results by root domain (boolean).
Examples:
- totals: queryAnalytics(metric="status", profile_id="abc123", from_time="-1d")
- time series: queryAnalytics(metric="status", profile_id="abc123", from_time="-1d", series=true)
- destinations: queryAnalytics(metric="destinations", profile_id="abc123", from_time="-1d", destination_type="countries")
| Name | Required | Description | Default |
|---|---|---|---|
| root | No | ||
| limit | No | ||
| cursor | No | ||
| device | No | ||
| metric | Yes | ||
| series | No | ||
| status | No | ||
| to_time | No | ||
| interval | No | ||
| partials | No | ||
| timezone | No | ||
| alignment | No | ||
| from_time | No | ||
| profile_id | Yes | ||
| destination_type | No |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description discloses important behavioral traits like time format flexibility and the series restriction, but could mention read-only nature and lack of destructive side effects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Well-structured with bullet points and examples, front-loaded with purpose. Slightly lengthy but each part adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (15 params, output schema exists), the description provides sufficient context for typical use cases, though some parameters are left unexplained.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%, but the description covers many key parameters (metrics, series, time, filters) adding meaning beyond schema. Some parameters like limit, interval remain undocumented.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Query NextDNS analytics metrics' and lists numerous specific metrics, making the tool's purpose explicit and distinct from siblings like plotAnalytics, dohLookup, etc.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides clear context through examples and notes like 'series=true is not supported when metric="domains"', but lacks explicit when-not-to-use or alternative tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Each tool targets a distinct resource or operation: profiles, lists, rewrites, logs, analytics query, and analytics plotting. No two tools have overlapping purposes; the domain boundaries are clear.
All tool names follow a consistent verb_noun pattern in camelCase: manageProfiles, manageLists, manageRewrites, manageLogs, queryAnalytics, plotAnalytics. No mixing of styles or vague verbs.
6 tools is well-scoped for a DNS management service. Each tool covers a core functional area without being too few or too many, and the operations within each tool are comprehensive.
The set covers profile CRUD, list management, rewrites, logs, and analytics. A minor gap is the inability to modify profile settings beyond renaming, but core workflows are supported.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Query your team's drift, vulnerability, and upgrade data from any AI assistant. OAuth 2.1, 51 tools.
Zero-setup MCP gateway securely connecting AI to your tools with authentication and workflows
Manage hosts, redirects, SSL, and traffic analytics from Claude and other AI assistants.
Run your website's AI support agent from Claude, Cursor or any MCP client. Manage the knowledge base, edit agent instructions, read conversations and leads, reply live to visitors, and check plan usage. 54 tools, OAuth sign-in, no API key. Free with every Asyntai account: https://asyntai.com/documentation/mcp/
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/dmeiser/nextdns-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
