# Agentosaurus (remote · agentosaurus.com)

Claude Code policy gateway, prices, AI-agent reviews and Amsterdam sustainability data as MCP tools.

- Trust score: 74/100 (medium)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `agentosaurus.com`: 74/100 (this document), [markdown](https://verifymcp.io/servers/com-agentosaurus-agentosaurus/agentosaurus.md), [page](https://verifymcp.io/servers/com-agentosaurus-agentosaurus/agentosaurus)

## Channel facts

- Endpoint: `https://agentosaurus.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.1`

## 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**: 80/100
  - 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 is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - 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**: 64/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 2016 tokens (~72/item across 28 items; 28 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 23/100
  - Stability observed for 7 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 89/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 67% 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 28 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 29 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the Agentosaurus MCP server?

Agentosaurus is a hosted endpoint at https://agentosaurus.com/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 com-agentosaurus-agentosaurus 'https://agentosaurus.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-agentosaurus-agentosaurus": {
      "url": "https://agentosaurus.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-agentosaurus-agentosaurus": {
      "type": "http",
      "url": "https://agentosaurus.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-agentosaurus-agentosaurus]
url = "https://agentosaurus.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-agentosaurus-agentosaurus": {
      "type": "remote",
      "url": "https://agentosaurus.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-agentosaurus-agentosaurus --url 'https://agentosaurus.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-agentosaurus-agentosaurus:
    url: "https://agentosaurus.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-agentosaurus-agentosaurus": {
      "Transport": "http",
      "Url": "https://agentosaurus.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-agentosaurus-agentosaurus -t streamable-http -u 'https://agentosaurus.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-agentosaurus-agentosaurus": {
      "type": "http",
      "url": "https://agentosaurus.com/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 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-19 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-18 (score 72, 0)

- [security] Tool “request_data_removal” rewrote its description, which is the text the model reads
- [security] Tool “request_scoping_call” rewrote its description, which is the text the model reads
- [security] Tool “signup” rewrote its description, which is the text the model reads
- [cosmetic] “request_scoping_call” reworded the description of “privacy_consent”
- [cosmetic] “signup” reworded the description of “note”
- [cosmetic] “request_data_removal” made “submitted_by_agent” optional
- [cosmetic] “request_scoping_call” made “privacy_consent” optional

### 2026-11-17 (score 72, +1)

- [security] Tool “request_data_removal” rewrote its description, which is the text the model reads
- [functional] Server version: 1.0.0 → 1.0.1

### 2026-11-16 (score 71, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “about_wingie” rewrote its description, which is the text the model reads
- [security] Tool “request_scoping_call” rewrote its description, which is the text the model reads

### 2026-11-15 (score 71, +1)

- [functional improvement] Stability: unverified → 0.03
- [functional] New tool “get_policy_gateway_offer”

### 2026-11-14 (score 70)

First indexed and scored.

## MCP tools (28)

### `get_pricing` (~41 tokens)

Training-run price list

Published prices for each stage of a sovereign training run at each model size, for both architectures, with their assumptions. Same data as /agents/pricing.json.

### `get_quote` (~145 tokens)

Quote one model size

An itemised quote for one model size, with dataset-only, dataset-plus-compute and selection totals. Same data as /agents/quote.json.

Input parameters:

- `arch` (string)
- `dataset` (boolean): Include the dataset.
- `expert_hours` (integer)
- `expert_rate` (number): USD per expert hour. Send this or novelty, not both.
- `hours_per_day` (integer)
- `licensing` (string)
- `novel` (boolean): A novel architecture.
- `novelty` (string): A published novelty band id.
- `size` (string, required): Model size, case-insensitive.
- `supervision` (boolean): Include a supervised run.

### `get_review_scope` (~44 tokens)

The Review: scope and plan

The change-control Review (the Audit): its scope, the plan by week, what you receive and how the price is set. Same text as /agents/audit.txt.

### `get_policy_gateway_offer` (~76 tokens)

The policy gateway for Claude Code

The policy gateway offer: policy research, enforcement on every Claude Code tool call through hooks, a human approvals queue, a tamper-evident decision log and a weekly report per team; how a team switches it on through managed settings; the four tiers; and what is collected. Same text as /policy-gateway.txt.

### `list_nodes` (~46 tokens)

Sovereign GPU node builds

GPU node builds a buyer owns and Agentosaurus racks in Amsterdam, with build totals, the minimum order, monthly colocation and energy factors. Same data as /agents/nodes.json.

### `estimate_pretraining_cost` (~107 tokens)

Pretraining cost for a model shape

What pretraining a model of a given shape costs at the published rates: token budget, GPU hours, run schedule and the total. The same arithmetic as the /cost/ calculator and /agents/model.json.

Input parameters:

- `active_params` (integer): Parameters active per token. Defaults to total_params (dense).
- `architecture` (string)
- `tier` (string): Trajectory tier.
- `tokens_per_param` (integer)
- `total_params` (integer, required): Total parameters.

### `list_blog_posts` (~45 tokens)

List published posts

Published blog posts, newest first, with excerpts and tags.

Input parameters:

- `limit` (integer): How many results to return.
- `tag` (string): Only posts carrying this tag.

### `get_blog_post` (~30 tokens)

Read one published post

The full Markdown of one published post.

Input parameters:

- `slug` (string, required): The slug from a search result.

### `about_wingie` (~43 tokens)

About wingie

Who wingie, the AI agent at Agentosaurus, is, what it may do and how to reach the team. Same text as /wingie.txt.

### `how_to_contact` (~24 tokens)

How to contact Agentosaurus

The contact address and the ways to reach a person at Agentosaurus.

### `search_organizations` (~93 tokens)

Search sustainability organisations

Search the public directory of analysed organisations (the /planet-agent/ directory) by name, city and SDG goal. Returns public profile fields only.

Input parameters:

- `city` (string): City name, for example Amsterdam.
- `limit` (integer): How many results to return.
- `query` (string): Part of the organisation's name.
- `sdg` (integer): Only organisations aligned with this SDG goal.

### `get_organization` (~39 tokens)

One organisation's public profile

The public profile of one organisation and the questions ask_organization can answer about it.

Input parameters:

- `slug` (string, required): The slug from a search result.

### `ask_organization` (~61 tokens)

Ask a fixed question about an organisation

Answers one question from a fixed list using the organisation's stored public profile. Nothing is generated; a question with no stored data says so and links the profile.

Input parameters:

- `question` (string, required)
- `slug` (string, required): The slug from a search result.

### `list_events` (~83 tokens)

Upcoming volunteer events

Upcoming published volunteer events, soonest first, with their shifts. Same events as /events/volunteer/find/.

Input parameters:

- `city` (string): Town or city named in the event location. Empty string for every city.
- `date_from` (string): Only events on or after this date (YYYY-MM-DD).
- `limit` (integer): How many results to return.

### `find_volunteer_shifts` (~81 tokens)

Find volunteer shifts

Upcoming volunteer shifts with the spots still open, the event and the organiser's public page.

Input parameters:

- `city` (string): Town or city named in the event location. Empty string for every city.
- `date_from` (string): Only events on or after this date (YYYY-MM-DD).
- `limit` (integer): How many results to return.

### `get_event` (~35 tokens)

One volunteer event

One published volunteer event with its shifts and the organiser's public page.

Input parameters:

- `slug` (string, required): The slug from a search result.

### `partner_match` (~59 tokens)

Match a business to NGOs by SDG

Ranks organisations by alignment with the SDG goals a business wants to advance, the same matching as /partner-match/.

Input parameters:

- `city` (string)
- `limit` (integer): How many results to return.
- `sdgs` (array, required)

### `food_rescue_amsterdam` (~42 tokens)

Taste Before You Waste, Amsterdam

Donating surplus food to Taste Before You Waste in Amsterdam, joining them as a volunteer, and what the organisation does.

Input parameters:

- `intent` (string, required)

### `get_lab_experiments` (~41 tokens)

The lab's experiments

Every experiment on /lab/: what ran, the number, its state, and the compute a queued run needs. Same text as /lab.txt.

### `get_topic` (~39 tokens)

A regulatory topic page

The text of one topic page: AI safety, AI sovereignty, AI security, or the Dutch sovereign-hardware page.

Input parameters:

- `name` (string, required)

### `get_inventory` (~32 tokens)

What exists today

Which parts of Agentosaurus you can use today and which are not built yet. Same text as /inventory.txt.

### `review_readiness` (~167 tokens)

Articles to review

A fixed rule table over your answers that lists the AI Act, DORA, NIS2, GDPR and NEN 7510 items to review, each cited from a public page. Articles to review, not legal advice.

Input parameters:

- `agents_in_production` (boolean, required): AI agents change production systems or data today.
- `annex_i_product` (boolean, required): AI is part of a product covered by AI Act Annex I, such as a medical device or machinery.
- `annex_iii_use` (boolean, required): An AI system is used for an AI Act Annex III purpose, such as hiring or credit scoring.
- `engineers_band` (string, required): How many engineers the organisation employs.
- `eu_entity` (boolean, required): The organisation is established in the EU.
- `sector` (string, required)

### `search_kits` (~69 tokens)

Search the shop

Kits and reports on sale in the shop, with price in EUR and the product page to buy from.

Input parameters:

- `category` (string)
- `limit` (integer): How many results to return.
- `query` (string): Part of the kit's name.
- `tier` (string)

### `get_kit` (~42 tokens)

One kit or report

One kit or report on sale, with its price in EUR and the product page to buy from.

Input parameters:

- `slug` (string, required): The slug from a search result.

### `esg_report_offer` (~32 tokens)

VerifyAgent ESG report offer

What a full VerifyAgent ESG due-diligence report contains and costs, with the upgrade and investigate pages.

### `signup` (~93 tokens)

Register an email address

Registers an email address with Agentosaurus, optionally with an interest. We email the person a link to confirm; nothing is stored as consent until they click it. A person replies after that. Charges nothing. Limited to 5 per hour per address.

Input parameters:

- `email` (string, required)
- `interest` (string)
- `note` (string): Passed to the person who replies once the address is confirmed, then deleted.

### `request_scoping_call` (~142 tokens)

Request a scoping call

Asks Agentosaurus for a scoping call about the Review, the policy gateway (tier policy_gateway, Starter included), LOGOS or sovereign training. We email the person a link to confirm; nothing is stored as consent until they click it. A person replies by email after that. Charges nothing. Limited to 5 per hour per address.

Input parameters:

- `email` (string, required)
- `message` (string, required): What you want to achieve.
- `name` (string, required)
- `organisation` (string)
- `privacy_consent` (boolean): Ignored. Consent comes only from the person clicking the emailed link.
- `tier` (string)

### `request_data_removal` (~190 tokens)

Ask to remove or correct data

Asks Agentosaurus to delete or fix someone's personal data, or to take down an organisation's listing, for the requester or for someone they act for. We email the requester's address a link to confirm; nothing is stored as consent until they click it, and the request is acted on after that. A person reviews it and replies by email within one month; nothing is removed automatically. Returns a reference code only. Limited to 5 per hour per address.

Input parameters:

- `details` (string, required): What to remove or correct.
- `on_behalf_of` (string): The person or organisation the requester acts for.
- `request_type` (string, required)
- `requester_email` (string, required): Where the reply goes.
- `submitted_by_agent` (boolean): An AI agent is sending this request.
- `target_url_or_slug` (string, required): The page URL or organisation slug the request is about.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-agentosaurus-agentosaurus/agentosaurus#diagnostics

## Score history

- 2026-11-21: 74
- 2026-11-20: 73
- 2026-11-19: 73
- 2026-11-18: 72
- 2026-11-17: 72
- 2026-11-16: 71
- 2026-11-15: 71
- 2026-11-14: 70

## Common questions

### What is the Agentosaurus MCP server?

Agentosaurus is an MCP server listed in the public MCP registry as com.agentosaurus/agentosaurus. Claude Code policy gateway, prices, AI-agent reviews and Amsterdam sustainability data as MCP tools. This page covers its hosted endpoint (https://agentosaurus.com/mcp).

### Is the Agentosaurus MCP server safe to use?

Agentosaurus scores 74 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 Agentosaurus MCP server expose?

Agentosaurus exposes 28 tools: get_pricing, get_quote, get_review_scope, get_policy_gateway_offer, list_nodes, and 23 more. Their descriptions and schemas cost roughly 1,941 tokens of context every time the server is loaded.

### Does the Agentosaurus MCP server require authentication?

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

### Is the Agentosaurus MCP server still maintained?

Agentosaurus 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 Agentosaurus MCP server?

VerifyMCP ran 13 checks on Agentosaurus, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. 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://agentosaurus.com/mcp
- Website: https://agentosaurus.com/
- Changelog RSS feed: https://verifymcp.io/servers/com-agentosaurus-agentosaurus/agentosaurus.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-agentosaurus-agentosaurus/agentosaurus/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/com-agentosaurus-agentosaurus/agentosaurus.json
- HTML version of this page: https://verifymcp.io/servers/com-agentosaurus-agentosaurus/agentosaurus
