# Managed Nerds (remote · mcp.managednerds.ai)

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

- Trust score: 62/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `mcp.managednerds.ai`: 62/100 (this document), [markdown](https://verifymcp.io/servers/tech-managednerds-managed-nerds/mcp.md), [page](https://verifymcp.io/servers/tech-managednerds-managed-nerds/mcp)

## Channel facts

- Endpoint: `https://mcp.managednerds.ai/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## Trust breakdown

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. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-21.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - 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.
  - HTTPS enforcement could not be verified: the plaintext port answered with HTTP 405, which proves neither a plaintext path nor enforcement.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 63/100
  - AI-judged instruction clarity (good).
  - 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.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 70/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 11% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 16 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 17 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

**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.

## 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.

### Claude

```bash
claude mcp add --transport http tech-managednerds-managed-nerds 'https://mcp.managednerds.ai/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "tech-managednerds-managed-nerds": {
      "url": "https://mcp.managednerds.ai/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "tech-managednerds-managed-nerds": {
      "type": "http",
      "url": "https://mcp.managednerds.ai/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.tech-managednerds-managed-nerds]
url = "https://mcp.managednerds.ai/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "tech-managednerds-managed-nerds": {
      "type": "remote",
      "url": "https://mcp.managednerds.ai/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add tech-managednerds-managed-nerds --url 'https://mcp.managednerds.ai/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  tech-managednerds-managed-nerds:
    url: "https://mcp.managednerds.ai/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "tech-managednerds-managed-nerds": {
      "Transport": "http",
      "Url": "https://mcp.managednerds.ai/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add tech-managednerds-managed-nerds -t streamable-http -u 'https://mcp.managednerds.ai/mcp'
```

### Other

```json
{
  "mcpServers": {
    "tech-managednerds-managed-nerds": {
      "type": "http",
      "url": "https://mcp.managednerds.ai/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-21 (score 62)

First indexed and scored.

## MCP tools (16)

### `get_profile` (~47 tokens)

Get vendor profile

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.

### `list_guides` (~41 tokens)

List guides

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

### `check_fit` (~127 tokens)

Check fit

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.

Input parameters:

- `city` (string)
- `country` (string)
- `has_it_staff` (boolean)
- `has_own_rmm` (boolean)
- `platforms` (array)
- `seats` (integer)
- `service_line` (string)
- `state` (string)
- `tenant` (string)

### `list_services` (~57 tokens)

List services

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.

### `list_projects` (~84 tokens)

List projects

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.

### `preliminary_estimate` (~274 tokens)

Get a preliminary estimate

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).

Input parameters:

- `also_interested_in` (array)
- `business` (object, required)
- `computers` (object)
- `contact` (object, required)
- `revises` (string): Revise an earlier estimate: its estimate_id (with status_token)
- `rmm` (object)
- `service_model` (string)
- `services` (array)
- `status_token` (string): The token from the earlier estimate's status_url
- `support` (object): 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).
- `tenant` (string)
- `user_approved` (boolean, required)
- `user_request` (string, required)
- `users` (integer): All licensed Microsoft 365 or Google Workspace users in the tenant: ITDR is all or nothing

### `request_callback` (~147 tokens)

Request a callback

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.

Input parameters:

- `business` (object)
- `contact` (object, required)
- `estimate_id` (string)
- `notes` (string)
- `time_zone` (string)
- `topic` (string)
- `user_approved` (boolean, required)
- `user_request` (string)
- `windows` (array)

### `ask` (~132 tokens)

Ask a question

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.

Input parameters:

- `question` (string, required)

### `check_email_security` (~137 tokens)

Check email security

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.

Input parameters:

- `domain` (string, required): example.com, you@example.com or https://example.com

### `check_domain` (~157 tokens)

Check domain health

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.

Input parameters:

- `domain` (string, required): example.com, you@example.com or https://example.com

### `check_ai_readiness` (~214 tokens)

Check AI search readiness

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.

Input parameters:

- `domain` (string, required): example.com, https://example.com or you@example.com

### `request_service` (~203 tokens)

Request a service quote

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).

Input parameters:

- `business` (object, required)
- `contact` (object, required)
- `notes` (string)
- `project` (object)
- `secure_wp` (object)
- `seo` (object)
- `service_line` (string, required)
- `user_approved` (boolean, required)
- `user_request` (string, required)

### `request_seo_check` (~122 tokens)

Request a local SEO check

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.

Input parameters:

- `business` (object, required)
- `contact` (object, required)
- `google_business_profile` (string)
- `notes` (string)
- `services` (array, required)
- `user_approved` (boolean, required)
- `user_request` (string, required)

### `estimate_status` (~47 tokens)

Check estimate status

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.

Input parameters:

- `token` (string, required)

### `request_full_quote` (~88 tokens)

Request a full quote

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.

Input parameters:

- `best_time_to_call` (string)
- `contact_phone` (string)
- `estimate_id` (string, required)
- `notes` (string)
- `timeline` (string)
- `user_approved` (boolean, required)

### `search_site` (~46 tokens)

Search the site

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

Input parameters:

- `limit` (integer)
- `query` (string, required)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/tech-managednerds-managed-nerds/mcp#diagnostics

## Score history

- 2026-11-21: 62

## 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.

## Links

- Remote endpoint: https://mcp.managednerds.ai/mcp
- Website: https://www.managednerds.tech/
- Changelog RSS feed: https://verifymcp.io/servers/tech-managednerds-managed-nerds/mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/tech-managednerds-managed-nerds/mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/tech-managednerds-managed-nerds/mcp.json
- HTML version of this page: https://verifymcp.io/servers/tech-managednerds-managed-nerds/mcp
