Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Managed Nerds

REMOTE · MCP.MANAGEDNERDS.AI

Free email, domain and AI search checks, plus IT, security and SEO help for US small businesses.

62 Trust /100

Last scanned (2 hours ago)

Scores higher than 45% of remote servers

Reachable. Last reached 21 Nov 2026.

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security63
  • The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
  • No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation. See how to fix → View diagnostics → Partial
  • HTTPS enforcement could not be verified: the plaintext port answered with HTTP 405, which proves neither a plaintext path nor enforcement. View diagnostics → Unverified
  • HSTS check failed: the Strict-Transport-Security header is absent. See how to fix → View diagnostics → Fail
  • DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
Schema Quality & AI Usability63
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 2149 tokens (~134/item across 16 items; 16 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management0
  • Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage70
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 11% of tool parameters carry a description.Partial
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 16 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 17 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass

Unverified: 1 category

A category scored 0 because we could not verify it: authentication we do not have, an unreachable endpoint, or not enough scan history. We only credit what we can confirm.

What we tested

Checks we ran (11)

  • TLS certificate
  • Authorization
  • HSTS header
  • DNSSEC
  • Transport
  • Schema quality
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Checks we could not complete (2)

These are gaps on our side, not findings about this hosted endpoint. We only credit what we can confirm, so a category made up entirely of them scores 0.

  • HTTPS in Endpoint SecurityHTTPS enforcement could not be verified: the plaintext port answered with HTTP 405, which proves neither a plaintext path nor enforcement.
  • Stability in Stability & Change Management (scores 0 for this)Stability not yet verified: not enough scan history yet (needs a 30-day window).

Does not apply to this hosted endpoint (2)

  • Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
  • Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 21 Nov 26 62

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Nov 2026 · Probed https://mcp.managednerds.ai/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=managednerds.ai CN=WE1,O=Google Trust Services,C=US 20 Nov 2026 18 Feb 2027 ECDSA 256 ECDSA-SHA256 342020b68180346b0e0e27cdbf7e7f6a
SANs: managednerds.ai, mcp.managednerds.ai, *.mcp.managednerds.ai
CN=WE1,O=Google Trust Services,C=US (CA) CN=GTS Root R4,O=Google Trust Services LLC,C=US 13 Dec 2023 20 Feb 2029 ECDSA 256 ECDSA-SHA384 7ff31977972c224a76155d13b6d685e3
CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE 15 Nov 2023 28 Jan 2028 ECDSA 384 SHA256-RSA 7fe530bf331343bedd821610493d8a1b

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of mcp.managednerds.ai. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
ai. DS published 1814 8 Verified
managednerds.ai. No DS Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://mcp.managednerds.ai/mcp Verified 200
http (plaintext) http://mcp.managednerds.ai/mcp Inconclusive 405
MCP tools · 16 exposed · ~1,923 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
ask ~132

A question about Managed Nerds (services, who we work with, how things work, our how-to posts), answered only from our own pages, with the pages it used. Also "my X isn't working" questions (printer offline, Outlook rules, slow PC, locked out, fake virus pop-up, hacked WordPress, Microsoft 365 sign-in from another country...): when a step-by-step fix post matches, each source carries applies_to and last_checked, and still_stuck says how a person can help. Never gives prices. 100 answers a day across all agents.

NameTypeReqDescription
questionstringyes–

No output schema declared.

No examples provided.

check_ai_readiness ~214

Free AI search readiness check for a website (also accepts a domain or email address): whether ChatGPT, Claude, Perplexity, Google's AI Overviews, Bing and Copilot, Apple (Siri, Spotlight) and Meta AI can find and read it. Reads robots.txt by crawler job (search crawlers are graded; training crawlers are the owner's choice and only noted, since each company uses separate names), the home page (noindex, nosnippet, text without JavaScript, business structured data, title and description), the sitemap and llms.txt. Grades it (good, needs work, at risk) with exactly what to fix. Public data only, about four requests to the site; it never pretends to be a crawler, so firewall blocks can't be seen. No contact details; the domain and result are kept 90 days, nothing about who asked. 10 checks an hour per address.

NameTypeReqDescription
domainstringyesexample.com, https://example.com or you@example.com

No output schema declared.

No examples provided.

check_domain ~157

Free domain health check (also accepts an email or website address): when the domain expires and who it's registered with, whether it's locked against transfer, its name servers, whether the website loads over https and redirects http, www vs the bare domain, CAA, and DNSSEC as a note. Grades it (good, needs work, at risk) with exactly what to fix. Public data only (registration data, DNS, one request to the home page); auto-renew and certificate expiry can't be seen from outside. No contact details; the domain and result are kept 90 days, nothing about who asked. 10 checks an hour per address.

NameTypeReqDescription
domainstringyesexample.com, you@example.com or https://example.com

No output schema declared.

No examples provided.

check_email_security ~137

Free email security check for any domain (also accepts an email or website address): whether scammers can send email that looks like it came from it, and why its mail might land in spam. Checks SPF, DKIM, DMARC, the mail provider and MTA-STS from public DNS, grades it (good, needs work, at risk) and gives the exact records to add. Sends no email and needs no contact details; the domain and result are kept 90 days, nothing about who asked. 20 checks an hour per address.

NameTypeReqDescription
domainstringyesexample.com, you@example.com or https://example.com

No output schema declared.

No examples provided.

check_fit ~127

Would Managed Nerds take on this business? No contact details, nothing stored, no prices. All fields optional; more give a firmer answer. Returns fit (yes, partial, ask_a_person, no), reasons and the next step.

NameTypeReqDescription
citystring––
countrystring––
has_it_staffboolean––
has_own_rmmboolean––
platformsarray––
seatsinteger––
service_linestring––
statestring––
tenantstring––

No output schema declared.

No examples provided.

estimate_status ~47

Check an estimate you got earlier: still valid?, when it expires, whether a full quote was requested, revisions left. Send the token from its status_url.

NameTypeReqDescription
tokenstringyes–

No output schema declared.

No examples provided.

get_profile ~47

Managed Nerds' vendor profile for comparing providers: who they serve (US only; on-site around Augusta, Georgia), services, support hours, products supported and how to buy. No prices.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

list_guides ~41

Managed Nerds' downloadable guides: what each covers, who it's for, and how to get one, including by email to guides@managednerds.ai.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

list_projects ~84

Managed Nerds' fixed-scope projects (business email, domains, Wi-Fi, Google Business Profile, websites, security and more) and how to ask for each: who it's for and isn't, what's included, what the buyer provides, typical timeline, whether it's one-time or ongoing, and the questions a quote needs. Every project is quoted by a person; no prices.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

list_services ~57

Managed Nerds' managed IT and co-managed security services, what an estimate needs, and the rules (RMM, users, Linux, US only, IT support billed separately on managed IT). No prices. Read it before preliminary_estimate.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

preliminary_estimate ~274

Only when your user asked: a preliminary monthly estimate for managed IT (service_model managed; IT support time is billed separately, with an optional pre-paid block) or co-managed security (a range before volume discounts, not an offer) for a US business under 50 seats. Needs the buyer's name, business and email, and what they asked for. Body as in /agent/openapi.json (EstimateRequest).

NameTypeReqDescription
also_interested_inarray––
businessobjectyes–
computersobject––
contactobjectyes–
revisesstring–Revise an earlier estimate: its estimate_id (with status_token)
rmmobject––
service_modelstring––
servicesarray––
status_tokenstring–The token from the earlier estimate's status_url
supportobject–Managed IT only: a pre-paid block of support hours. Send hours_per_month, or non_technical_users for our suggestion (half an hour a month each).
tenantstring––
user_approvedbooleanyes–
user_requeststringyes–
usersinteger–All licensed Microsoft 365 or Google Workspace users in the tenant: ITDR is all or nothing

No output schema declared.

No examples provided.

request_callback ~147

Only when your user asked: a callback from a person at Managed Nerds (not a booking; they confirm a time by email within one business day). Needs the buyer's name, email and phone, and up to 3 windows on Monday to Friday, 8am to 6pm Eastern. Send estimate_id to attach it to an estimate.

NameTypeReqDescription
businessobject––
contactobjectyes–
estimate_idstring––
notesstring––
time_zonestring––
topicstring––
user_approvedbooleanyes–
user_requeststring––
windowsarray––

No output schema declared.

No examples provided.

request_full_quote ~88

Only after your user says yes to a full quote: send the estimate_id. A person at Managed Nerds replies by email within one business day.

NameTypeReqDescription
best_time_to_callstring––
contact_phonestring––
estimate_idstringyes–
notesstring––
timelinestring––
user_approvedbooleanyes–

No output schema declared.

No examples provided.

request_seo_check ~122

Only when your user asked: the free local SEO check. A person emails a two-page check within three business days (Google Business Profile, local basics, where they show for up to three services). US businesses, one per website, five a week. No ranking promises, no prices.

NameTypeReqDescription
businessobjectyes–
contactobjectyes–
google_business_profilestring––
notesstring––
servicesarrayyes–
user_approvedbooleanyes–
user_requeststringyes–

No output schema declared.

No examples provided.

request_service ~203

Only when your user asked: a quote from a person for SEO, secure WordPress or a project (no prices here; a reply by email within one business day). service_line seo needs website, service area, main services and whether Google Analytics and Search Console are set up; ad management comes only with SEO (seo.wants_ads, ad_platforms, ad_budget 500-1500, 1500-5000 or 5000+). secure_wp needs site URL, hosting provider, DNS provider, e-commerce and hacked-before. project needs project.slug and project.details (answer the project's quote_questions from list_projects).

NameTypeReqDescription
businessobjectyes–
contactobjectyes–
notesstring––
projectobject––
secure_wpobject––
seoobject––
service_linestringyes–
user_approvedbooleanyes–
user_requeststringyes–

No output schema declared.

No examples provided.

search_site ~46

Search Managed Nerds' website (blog posts and pages) and get titles, links and short excerpts. Read-only.

NameTypeReqDescription
limitinteger––
querystringyes–

No output schema declared.

No examples provided.

Install

How do I install the Managed Nerds MCP server?

Managed Nerds is a hosted endpoint at https://mcp.managednerds.ai/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · mcp.managednerds.ai

# add to Claude Code
claude mcp add --transport http tech-managednerds-managed-nerds 'https://mcp.managednerds.ai/mcp'
Common questions

What is the Managed Nerds MCP server?

Managed Nerds is an MCP server listed in the public MCP registry as tech.managednerds/managed-nerds. Free email, domain and AI search checks, plus IT, security and SEO help for US small businesses. This page covers its hosted endpoint (https://mcp.managednerds.ai/mcp).

Is the Managed Nerds MCP server safe to use?

Managed Nerds scores 62 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the Managed Nerds MCP server expose?

Managed Nerds exposes 16 tools: get_profile, list_guides, check_fit, list_services, list_projects, and 11 more. Their descriptions and schemas cost roughly 1,923 tokens of context every time the server is loaded.

Does the Managed Nerds MCP server require authentication?

No. We connected to Managed Nerds without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the Managed Nerds MCP server still maintained?

Managed Nerds is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What did VerifyMCP test on the Managed Nerds MCP server?

VerifyMCP ran 11 checks on Managed Nerds, covering TLS certificate, Authorization, HSTS header, DNSSEC and 7 more. 2 items could not be completed, a gap on our side rather than a finding about Managed Nerds: HTTPS and Stability. One category scores 0 for that reason, because we only credit what we can confirm. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.