Skip to main content
Glama
DNSFilter MCP Server

DNSFilter MCP Server

by WYRE-AI

DNSFilter MCP Server

MCP server for DNSFilter's DNS security/filtering API - organizations, networks (sites), filtering policies, content/application categories, custom block pages, and the full traffic/threat reporting surface, for AI assistants and the WYRE Conduit gateway.

Scope

This is a deliberately narrow, read-only v1 surface, hard-scoped to organizations, networks, policies, categories, block pages, and reporting. DNSFilter's REST API (api.dnsfilter.com) has 217 documented paths across a much broader surface - MSP/distributor management, billing, users, roaming-client agents, enterprise SSO connections, API key management, scheduled reports, and more. None of that is implemented here, by design, not by oversight. Every tool in this connector maps 1:1 to a real, documented GET operation in DNSFilter's own published OpenAPI spec (https://api.dnsfilter.com/docs.json) - there is no write, update, or delete tool anywhere in this codebase.

Hard-excluded (every write/mutation operation on every in-scope resource) - never implemented:

  • POST/PATCH/DELETE /v1/organizations* (create, bulk_update, promote_to_msp, update, cancel, destroy) - organization mutations.

  • POST/PATCH/DELETE /v1/networks* (create, bulk_create/update/destroy, update, destroy, secret_key rotate/revoke/generate) - network mutations, including LAN IP and subnet writes.

  • POST/PATCH/DELETE /v1/policies* (create, update, destroy, application_update, add/remove_allowed_application, add/remove_blacklist_category, add/remove_blacklist_domain, add/remove_blocked_application, add/remove_whitelist_domain, permissive_mode update) and all of /v1/policies/bulk/* (bulk allow/block-list add/remove) and /v1/policy_ips writes - every policy-content mutation.

  • POST/DELETE /v1/block_pages* (create, destroy) and PATCH /v1/block_pages/{id} (update) - block-page mutations.

  • Every write endpoint on resources this connector doesn't otherwise touch at all: API keys (create/destroy/revoke), users and organization users (create/update/destroy/resend_invite), billing/invoices, distributors (MSP/sub-org provisioning, SKUs, cancellation), enterprise SSO connections, scheduled policies/reports, roaming-client user-agents (bulk delete/update/cleanup, dequeue-uninstall), domain notes, IP/MAC address management, and trials.

They can be added as a follow-up if there's demand, after a deliberate scope decision - not by default.

Deferred (read-only, not implemented in this v1 - not a security exclusion): a handful of GET-only sub-resources and dashboard-adjacent endpoints exist under the same resource groups this connector covers, but aren't wired up yet: network subnets (GET /v1/networks/{id}/subnets*), network LAN IPs (GET /v1/networks/{id}/lan_ips*), policy IPs (GET /v1/policy_ips*), the unpaginated */all variants of every list endpoint (redundant with the paginated list tool), and administrative */counts endpoints. These can be added later without any scope-policy change, since they're already read-only.

Related MCP server: mailfact-mcp

Authentication

DNSFilter authenticates with a static API key, generated in the DNSFilter dashboard under Account Settings -> Security -> API Keys (an account supports up to 5 active keys at a time; see DNSFilter's own API Keys article). Unlike most sibling WYRE Conduit connectors, the key is sent as the raw header value - Authorization: <key>, with no Bearer prefix - per DNSFilter's own API docs: "Authentication is done by setting the Authorization request header. The header value is the API key itself. For example: Authorization: eyJ...".

Credential scope: two separate claims, at deliberately different confidence levels

  • Structurally verified (checked directly, stated with full confidence): this connector's own code makes zero mutating calls - every function in client.ts is a GET, and no POST/PUT/PATCH/DELETE call exists anywhere in src/ (enforced by tool-scope.test.ts's forbidden-token check). Also structurally verified, directly against DNSFilter's own published OpenAPI spec (api.dnsfilter.com/docs.json, fetched directly): an API key is generated per user account (the ApiKey resource schema carries a user_id field) and its own creation request (ApiKeyCreateSpec) accepts only name and expiry - there is no scope/role/permission field chosen at key-creation time. A key's effective capability is therefore inherited from whatever role the DNSFilter user account it was generated under holds, not selected independently when the key itself is created. That same spec's Membership/OrganizationUser role enums explicitly include a "read_only" value alongside "administrator" (and, on the MSP/distributor membership shape, alongside "network_administrator"/"network_support"/"support") - so a genuinely restricted DNSFilter user role is a first-class, documented concept in the API itself, not just dashboard-UI copy.

  • Vendor-documented, not independently verified (hedged deliberately): DNSFilter's own help center separately describes a dashboard-level Read Only user role ("Users with more restrictive roles like Read Only... have hidden dashboard tabs and panels"). Combined with the structural finding above, generating an API key under a dedicated Read-Only-role user account should yield a key whose calls DNSFilter's API server rejects for any write endpoint - but whether the API actually enforces that role server-side against write calls (versus the restriction being dashboard-UI-only) has not been tested by WYRE. Nobody sent a live write call against a Read-Only-role key to confirm, correctly: that would be a mutating test against a real account, not something to run without consent. Do not read this README as having established that a Read-Only-role API key cannot perform writes against DNSFilter's API - only that (a) DNSFilter's spec models a read_only role as a real, first-class concept, and (b) this connector's own code never attempts a write regardless of which key it's given.

In gateway mode the key arrives per-request via the X-DNSFilter-Api-Key header; in local/stdio mode it's read once from DNSFILTER_API_KEY. The stdio transport does not use CONDUIT_S2S_SECRET.

HTTP authentication

MCP_TRANSPORT=http refuses to start when CONDUIT_S2S_SECRET is empty or a known placeholder (changeme, change-me, placeholder, secret, example, replace-me, replace-with-a-real-secret, your-s2s-secret, your-secret, s2s-secret). The process logs an error and exits non-zero. It never prints the secret. A placeholder is refused even if MCP_ALLOW_INSECURE_DEV=1 is set.

MCP_ALLOW_INSECURE_DEV=1 is local development only. It starts HTTP without a secret, logs a warning, does not check X-Gateway-S2S, and listens on 127.0.0.1 only. A non-loopback MCP_HTTP_HOST (including 0.0.0.0) is ignored in that mode and the override is logged.

When a real secret is set, MCP_HTTP_HOST is honored. Unset, the bind address is 127.0.0.1. The container image sets MCP_HTTP_HOST=0.0.0.0 and AUTH_MODE=gateway.

Every /mcp request must then include X-Gateway-S2S:

t=<unix seconds>,v1=<hex hmac-sha256>

v1 is HMAC-SHA256 of the ASCII string t=<unix seconds>, keyed with CONDUIT_S2S_SECRET, hex-encoded. The timestamp must be within 300 seconds of the server clock. A missing or invalid header returns 401.

In AUTH_MODE=gateway, /mcp also requires X-DNSFilter-Api-Key. A request missing that header returns 401 and does not fall back to DNSFILTER_API_KEY. /health stays unauthenticated and does not read credentials.

Request limits

  • HTTP request bodies are capped at 256 KiB (262144 bytes). After the X-Gateway-S2S check (and, in gateway mode, the X-DNSFilter-Api-Key presence check) passes, a Content-Length above the cap returns 413 with a JSON-RPC error; bodies without Content-Length are capped by the MCP SDK transport. Unauthenticated requests still get 401 first.

  • tools/call arguments are capped at 10,000 elements (every array item and object key at any depth). Larger inputs return an isError tool result with a fixed message (no caller input echoed) and are never dispatched.

These limits address CVE-2026-111768 / GHSA-46jr-4wx8-v453 (memory exhaustion during validation) and GHSA-f897-62hf-6gxq (no request body / batch cap).

Configuration

Copy .env.example and set the variables below.

Env var

Description

DNSFILTER_API_KEY

DNSFilter API key, generated in the DNSFilter dashboard. Required for stdio and for AUTH_MODE=env. Not set on the gateway Compose service.

MCP_TRANSPORT

stdio (default) or http.

AUTH_MODE

env (default, reads the var above) or gateway (credential arrives per-request via the X-DNSFilter-Api-Key header, injected by the Conduit gateway). The image and Compose default to gateway. Gateway mode never falls back to DNSFILTER_API_KEY.

CONDUIT_S2S_SECRET

Required for HTTP. Service-to-service secret used to verify X-Gateway-S2S. The process exits when this is empty or a known placeholder. Compose will not start without it. Never commit a real value.

MCP_ALLOW_INSECURE_DEV

Set to exactly 1 only for local HTTP without CONDUIT_S2S_SECRET. Logs a warning, skips X-Gateway-S2S, and binds 127.0.0.1 only.

MCP_HTTP_HOST

Bind address when a real CONDUIT_S2S_SECRET is set. Defaults to 127.0.0.1. The container image sets 0.0.0.0. Ignored (forced to 127.0.0.1) when there is no secret.

MCP_HTTP_PORT

HTTP port. Defaults to 8080.

LOG_LEVEL

debug | info (default) | warn | error.

Tools

57 read-only tools, one per documented DNSFilter GET operation across six resource groups.

Organizations

  • dnsfilter_list_organizations - list organizations visible to this API key.

  • dnsfilter_get_organization - get one organization's basic information.

  • dnsfilter_get_organization_settings - get organization-level settings.

Networks

  • dnsfilter_list_networks - list networks (sites/locations).

  • dnsfilter_get_network - get one network's basic information.

  • dnsfilter_lookup_network_by_ip - find the network associated with a source IP address.

  • dnsfilter_get_networks_geo - get every network's geo/location metadata only.

Policies

  • dnsfilter_list_policies - list filtering policies.

  • dnsfilter_get_policy - get one policy's full configuration (allow/block lists, categories, applications).

  • dnsfilter_get_application_policies - get which policies allow/block a specific application.

  • dnsfilter_get_policy_permissive_mode - get whether a policy has permissive (monitor-only) mode enabled.

Categories

  • dnsfilter_list_categories - list content-filtering categories.

  • dnsfilter_get_category - get one content category's details and hierarchy.

  • dnsfilter_list_application_categories - list application categories.

  • dnsfilter_get_application_category - get one application category's details.

Block Pages

  • dnsfilter_list_block_pages - list custom block pages.

  • dnsfilter_get_block_page - get one custom block page's configuration.

Metrics

  • dnsfilter_get_organization_usage - get organization usage (plan, users, total requests) over a date range.

  • dnsfilter_get_organization_usage_detailed - get the detailed per-metric breakdown of organization usage.

Traffic Reports

DNSFilter's entire reporting surface is GET-only, so all 38 documented report operations are implemented with no curation:

  • dnsfilter_get_qps, dnsfilter_get_qps_active_agents, dnsfilter_get_qps_active_organizations - queries-per-second time series.

  • dnsfilter_get_query_logs - raw DNS query log entries (domain, requester, category, allow/block result). The most granular, PII-bearing report this connector exposes.

  • dnsfilter_get_top_agents, dnsfilter_get_top_application_categories, dnsfilter_get_top_categories, dnsfilter_get_top_collections, dnsfilter_get_top_domains, dnsfilter_get_top_networks, dnsfilter_get_top_organizations_requests, dnsfilter_get_top_users - "top N" breakdowns by traffic volume.

  • dnsfilter_get_total_applications_agents_stats, dnsfilter_get_total_applications_collections_stats, dnsfilter_get_total_applications_networks_stats, dnsfilter_get_total_applications_stats, dnsfilter_get_total_applications_users_stats - application request-count totals, broken out by dimension.

  • dnsfilter_get_total_categories, dnsfilter_get_total_categories_organizations, dnsfilter_get_total_category_stats - content-category request totals.

  • dnsfilter_get_total_client_stats, dnsfilter_get_total_deployments, dnsfilter_get_total_roaming_clients - client/deployment counts.

  • dnsfilter_get_total_domain_stats, dnsfilter_get_total_domains, dnsfilter_get_total_domains_organizations, dnsfilter_get_total_domains_users - domain request totals.

  • dnsfilter_get_total_organizations_requests, dnsfilter_get_total_organizations_stats - organization-level request totals.

  • dnsfilter_get_total_requests, dnsfilter_get_total_requests_agents, dnsfilter_get_total_requests_collections, dnsfilter_get_total_requests_geo, dnsfilter_get_total_requests_organizations, dnsfilter_get_total_requests_users - total request-count totals, broken out by dimension.

  • dnsfilter_get_total_threats, dnsfilter_get_total_threats_organizations, dnsfilter_get_total_threats_users - blocked-threat totals.

The qps_active_agents and qps_active_organizations filter names match DNSFilter OpenAPI (neither path accepts MAC address, NAT IP, or private IP filters); shared enum/string schemas may still accept values those paths reject (for example source: "networks"). Empty or whitespace-only query values are omitted to preserve upstream defaults. Upstream 4xx/5xx response bodies (except the separately handled 401/429 responses) are redacted and truncated before being logged and surfaced to callers. Query logs allow up to 25 seconds, within the gateway's 30-second limit; other requests retain the 15-second timeout.

Sensitivity

Every tool in this connector is classified isAdmin: true in the Conduit gateway (see result-cache.ts's VENDOR_TOOL_CONFIG entry for this vendor), a whole-connector decision rather than a per-tool one. DNSFilter's surface here is a DNS security product: policy configuration, block-page branding, and - especially - the traffic-report family carry per-device/per-user DNS query history and threat-detection data (dnsfilter_get_query_logs returns individual domains queried by individual requesters; several total_*/top_* reports break results out by local user or client/agent). That's PII- and security-posture-adjacent data even as a plain read, the same posture this WYRE Conduit wave has taken for other security-category connectors (Cork, CyberQP, Cisco Duo).

Development

npm install
npm run build
npm test
npm run lint   # tsc --noEmit

Docker

The image listens on 0.0.0.0 inside the container (MCP_HTTP_HOST) and defaults to AUTH_MODE=gateway. Publish the port on loopback and pass the S2S secret. In gateway mode the DNSFilter API key arrives on each request as X-DNSFilter-Api-Key; it is not read from the environment. Sign X-Gateway-S2S as t=<unix seconds>,v1=<hex hmac-sha256 of that t= string> with CONDUIT_S2S_SECRET.

docker build -t dnsfilter-mcp .
docker run \
  -e CONDUIT_S2S_SECRET="$CONDUIT_S2S_SECRET" \
  -p 127.0.0.1:8080:8080 \
  dnsfilter-mcp

Compose refuses to start when CONDUIT_S2S_SECRET is unset, sets AUTH_MODE=gateway, does not inject DNSFILTER_API_KEY, and publishes 127.0.0.1:8080:8080:

CONDUIT_S2S_SECRET="$CONDUIT_S2S_SECRET" docker compose up

Single-tenant HTTP (AUTH_MODE=env) still requires the S2S secret, then uses DNSFILTER_API_KEY:

docker run \
  -e CONDUIT_S2S_SECRET="$CONDUIT_S2S_SECRET" \
  -e AUTH_MODE=env \
  -e DNSFILTER_API_KEY=your-api-key \
  -p 127.0.0.1:8080:8080 \
  dnsfilter-mcp

Local HTTP without a secret is development-only. It binds 127.0.0.1 even if MCP_HTTP_HOST is 0.0.0.0, and logs a warning:

MCP_TRANSPORT=http MCP_ALLOW_INSECURE_DEV=1 npm run start:http

License

Apache-2.0

Available Tools

57 tools
dnsfilter_get_application_categoryB

Get one application category's details. Requires an application category ID from dnsfilter_list_application_categories.

Inputs: id (required).

dnsfilter_get_application_policiesA

Get which policies in an organization allow or block a specific application. Requires an application ID and organization ID.

Inputs: application_id (required), organization_id (required), name, policy_ids.

dnsfilter_get_block_pageA

Get one custom block page's configuration: branding (org name, logo), contact email, and appearance settings. Requires a block page ID from dnsfilter_list_block_pages.

Inputs: id (required), include_relationships.

dnsfilter_get_categoryA

Get one content category's details and hierarchy (parent/child categories). Requires a category ID from dnsfilter_list_categories.

Inputs: id (required).

dnsfilter_get_networkA

Get one network's basic information. Requires a network ID from dnsfilter_list_networks.

Inputs: id (required), count_network_ips.

dnsfilter_get_networks_geoA

Get every visible network's geo/location metadata only (name, lat/long, physical address) - a lighter-weight variant of dnsfilter_list_networks for mapping.

Inputs: no named parameters.

dnsfilter_get_organizationA

Get one organization's basic information. Requires an organization ID from dnsfilter_list_organizations.

Inputs: id (required), include_current_mrr.

dnsfilter_get_organization_settingsB

Get organization-level settings, optionally scoped to a specific organization or MSP.

Inputs: name, msp_id, organization_id, organization_ids.

dnsfilter_get_organization_usageA

Get usage information (plan, term, user/wifi counts, total requests, estimated users) for an organization over a date range. Maximum range is 365 days. Requires an organization ID from dnsfilter_list_organizations.

Inputs: id (required), to (required), from (required).

dnsfilter_get_organization_usage_detailedA

Get the detailed (per-metric) breakdown of an organization's usage over a date range. Maximum range is 365 days. Requires an organization ID from dnsfilter_list_organizations.

Inputs: id (required), to (required), from (required).

dnsfilter_get_policyA

Get one policy's full configuration: allow/block domain lists, allow/block category rules, allowed/blocked applications, and which networks it's assigned to. Requires a policy ID from dnsfilter_list_policies.

Inputs: id (required), include_relationships.

dnsfilter_get_policy_permissive_modeA

Get whether a policy currently has permissive (monitor-only, non-blocking) mode enabled. Requires a policy ID from dnsfilter_list_policies.

Inputs: id (required).

dnsfilter_get_qpsB

Queries-per-second time series - the closest thing to a live traffic pulse.

Inputs: to, from, type, msp_id, +16 more.

dnsfilter_get_qps_active_agentsC

Queries-per-second broken out by active client/agent.

Inputs: to, from, type, source, +8 more.

dnsfilter_get_qps_active_organizationsC

Queries-per-second broken out by active organization.

Inputs: to, from, type, msp_id, +9 more.

dnsfilter_get_query_logsB

Raw DNS query log entries - domain queried, requester, category, and allow/block result. The most granular, PII-bearing report this connector exposes.

Inputs: to, fqdn, from, page, +24 more.

dnsfilter_get_top_agentsC

Clients/agents generating the most traffic.

Inputs: to, from, name, page, +16 more.

dnsfilter_get_top_application_categoriesC

Application categories generating the most traffic.

Inputs: to, from, name, page, +15 more.

dnsfilter_get_top_categoriesC

Content categories generating the most traffic.

Inputs: to, from, name, page, +15 more.

dnsfilter_get_top_collectionsC

Collections (roaming-client groupings) generating the most traffic.

Inputs: to, from, name, page, +16 more.

dnsfilter_get_top_domainsC

Domains queried most often.

Inputs: to, fqdn, from, page, +17 more.

dnsfilter_get_top_networksC

Networks generating the most traffic.

Inputs: to, from, name, page, +15 more.

dnsfilter_get_top_organizations_requestsC

Organizations generating the most request volume.

Inputs: to, from, page, msp_id, +2 more.

dnsfilter_get_top_usersC

Local users generating the most traffic.

Inputs: to, from, name, page, +16 more.

dnsfilter_get_total_applications_agents_statsC

Application request counts broken out by client/agent.

Inputs: to, from, name, type, +15 more.

dnsfilter_get_total_applications_collections_statsC

Application request counts broken out by collection.

Inputs: to, from, name, type, +15 more.

dnsfilter_get_total_applications_networks_statsB

Application request counts broken out by network.

Inputs: to, from, name, type, +15 more.

dnsfilter_get_total_applications_statsC

Total application request counts.

Inputs: to, from, name, type, +16 more.

dnsfilter_get_total_applications_users_statsC

Application request counts broken out by local user.

Inputs: to, from, name, type, +15 more.

dnsfilter_get_total_categoriesC

Total content-category request counts over time.

Inputs: to, from, type, msp_id, +15 more.

dnsfilter_get_total_categories_organizationsC

Total content-category request counts broken out by organization.

Inputs: to, from, type, source, +14 more.

dnsfilter_get_total_category_statsC

Content-category request-count summary.

Inputs: to, from, msp_id, network_ids, +2 more.

dnsfilter_get_total_client_statsC

Client/agent count summary.

Inputs: to, from, msp_id, network_ids, +1 more.

dnsfilter_get_total_deploymentsC

Deployed client/network counts.

Inputs: msp_id, network_ids, organization_id.

dnsfilter_get_total_domainsD

Total domain request counts over time.

Inputs: to, from, type, domain, +16 more.

dnsfilter_get_total_domains_organizationsD

Total domain request counts broken out by organization.

Inputs: to, from, type, domain, +16 more.

dnsfilter_get_total_domain_statsA

Single-domain request-count summary - use with the domain/fqdn filter.

Inputs: to, fqdn, from, domain, +3 more.

dnsfilter_get_total_domains_usersC

Total domain request counts broken out by local user.

Inputs: to, from, type, domain, +16 more.

dnsfilter_get_total_organizations_requestsC

Total request counts broken out by organization.

Inputs: to, fqdn, from, name, +14 more.

dnsfilter_get_total_organizations_statsC

Organization-level request-count summary.

Inputs: to, from, name, type, +9 more.

dnsfilter_get_total_requestsC

Total DNS request counts over time.

Inputs: to, from, type, msp_id, +16 more.

dnsfilter_get_total_requests_agentsC

Total request counts broken out by client/agent.

Inputs: to, from, type, msp_id, +16 more.

dnsfilter_get_total_requests_collectionsC

Total request counts broken out by collection.

Inputs: to, from, type, source, +15 more.

dnsfilter_get_total_requests_geoC

Total request counts broken out by geography.

Inputs: limit (required), to, from, msp_id, +1 more.

dnsfilter_get_total_requests_organizationsB

Total request counts broken out by organization.

Inputs: to, from, type, msp_id, +16 more.

dnsfilter_get_total_requests_usersB

Total request counts broken out by local user.

Inputs: to, from, type, msp_id, +16 more.

dnsfilter_get_total_roaming_clientsB

Count of roaming (off-network) clients.

Inputs: msp_id, organization_id.

dnsfilter_get_total_threatsC

Total blocked-threat counts over time.

Inputs: to, from, type, source, +13 more.

dnsfilter_get_total_threats_organizationsC

Total blocked-threat counts broken out by organization.

Inputs: to, from, type, source, +13 more.

dnsfilter_get_total_threats_usersC

Total blocked-threat counts broken out by local user.

Inputs: to, from, type, source, +13 more.

dnsfilter_list_application_categoriesA

List application categories, used for the application allow/block surface of a policy (distinct from content categories). IDs from this response are required by dnsfilter_get_application_category and can filter traffic-report tools via application_category_ids.

Inputs: page.

dnsfilter_list_block_pagesA

List the custom block pages configured for the current user/organization (shown to end users when a request is filtered). Block page IDs from this response are required by dnsfilter_get_block_page.

Inputs: page, organization_id.

dnsfilter_list_categoriesA

List DNSFilter's content-filtering categories (e.g. Malware, Gambling, Social Networking) used to build allow/block rules in a policy. Category IDs from this response are required by dnsfilter_get_category and can filter traffic-report tools via category_ids.

Inputs: page.

dnsfilter_list_networksA

List the networks (sites/locations) visible to this API key, with basic info and whether a filtering policy is assigned. Network IDs from this response are required by dnsfilter_get_network and can scope most traffic-report tools via network_ids.

Inputs: page, search, protected, basic_info, +3 more.

dnsfilter_list_organizationsA

List the organizations visible to this API key, with basic info (name, type, MSP relationships). Organization IDs from this response are required by dnsfilter_get_organization, dnsfilter_list_networks/policies/block_pages (via organization_id), and every traffic-report tool.

Inputs: name, page, type, basic_info, +4 more.

dnsfilter_list_policiesA

List filtering policies visible to this API key. Policy IDs from this response are required by dnsfilter_get_policy and dnsfilter_get_policy_permissive_mode.

Inputs: page, organization_id, include_global_policies.

dnsfilter_lookup_network_by_ipA

Find the network associated with a given source IP address, along with that network's block-page branding.

Inputs: requesting_ip_address (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    C2.6/5.0

    Scored across 57 tools

    Disambiguation2/5

    The read tools (list_*/get_*) are reasonably distinct, but the ~40 traffic-report tools are heavily confusable: dnsfilter_get_total_organizations_requests and dnsfilter_get_total_requests_organizations have essentially identical descriptions, as do the domains/organizations/requests variants. An agent must reason carefully about whether it wants a 'top' vs 'total' vs 'stats' vs 'broken out by' metric, with only subtle wording distinguishing many.

    Naming Consistency3/5

    All tools share a consistent dnsfilter_ prefix and snake_case verb_noun shape (list_/get_/lookup_), which is good. However, the noun composition is chaotic: get_total_requests_users vs get_total_domains_users vs get_total_applications_users_stats vs get_total_organizations_stats, and the suffix (_stats, _requests, _top_) is applied inconsistently, making names hard to predict.

    Tool Count2/5

    57 tools is far too many for this scope, dominated by dozens of near-duplicate reporting variants (three QPS tools, five 'total_requests_*' tools, several 'top_*' variants). A single parameterized reports tool with dimension/breakout arguments would cover most of this surface.

    Completeness3/5

    Reporting coverage is genuinely thorough and read access to organizations, networks, policies, categories, and block pages is complete. However there are notable gaps: no create/update/delete for any resource (purely read-only), and no list_applications tool even though dnsfilter_get_application_policies requires an application ID, creating a dead end.

    Maintenance

    ActivityMaintained
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      D
      maintenance
      Read-only MCP server for the Action1 RMM REST API, enabling access to endpoints, missing updates, vulnerabilities, installed software, policies, automations, and reports.
      21
      Apache 2.0
    • A
      license
      A
      quality
      C
      maintenance
      Provides read-only access to a Mailfact tenant, letting users list domains, sending sources, and aggregate reports, and query DMARC alignment, reporter coverage, and record-level data through MCP tools. It returns counts and rows only, without recommending policies or scoring domains.
      9
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables AI agents to read protected computers and their check-ins, computer groups, approval requests, the unified audit log, and child organizations through a zero-trust endpoint security portal API. Every operation is read-only, with credentials supplied per request as headers and never stored.
      Apache 2.0
    • A
      license
      B
      quality
      B
      maintenance
      Provides 40 governed read tools for querying tenant and connector health, applications, access policies, shared objects, collections, DNS, identities, cloud integrations, and audit logs.
      40
      MIT