Ask about the Claude Code policy gateway, AI-agent reviews and Amsterdam volunteer shifts.
MCP server over streamable HTTP, no account. Tools return the Claude Code policy gateway offer (Starter is free), the scope of a fixed-scope review of an organisation's AI agents, training-run prices and quotes, GPU node builds, published writing, the Amsterdam sustainability organisation directory and volunteer shifts. Three tools record a signup, a scoping-call request or a data-removal request; the rest only read. Listed in the official MCP Registry as com.agentosaurus/agentosaurus.
Try asking Muse: "Which EU AI Act and GDPR items should my small business review for the AI agents we run in production?"
Source: Submitted by its builder and screened before listing · First listed November 16, 2026
Each bar is one check, every 15 minutes. Green means it answered. Last checked 17 min ago.
What Muse can see: It does not ask you to sign in, so it cannot see your accounts. It only sees what Muse sends it from your request.
Before it acts: Read what Muse plans to do before you approve it, and remove the app from Muse when you stop using it.
musedirectory.ai is not part of Meta. More about how Muse handles your information
Not in Muse's Connectors list yet, but Muse can still use it. Copy the request below and paste it into Muse. Muse asks before it shares anything with the app's site. Meta does not review apps used this way, so only use ones you trust. We tested this in the Muse app on September 24, 2026: Muse used an app's link directly this way and returned a live answer.
https://agentosaurus.com/mcpNot in Muse's Connectors list yet. Muse can still use it: its page gives you a request to paste into Muse.
Agentosaurus is a remote MCP server, so any assistant that can add a custom connector by link can use it. Same link, same tools.
In ChatGPT, open Settings, then Connectors (called Apps & Connectors on some accounts).
Under Advanced settings, switch on Developer mode. That is what lets you add a connector by link.
Choose Create, give it a name, paste the link as the MCP server URL, and save. If it needs a sign-in, ChatGPT asks for it here.
Start a chat, open the tools menu, pick the connector, and ask. ChatGPT asks before it runs a tool the first time.
Custom connectors need a paid ChatGPT plan, and on Team, Enterprise and Edu accounts only an admin can add them. Our "Working" label means the server answered us; it cannot tell whether your plan lets you add it. All connectors that work in ChatGPT
In Claude, open Settings, then Connectors.
Choose Add custom connector, give it a name, and paste the link.
If it needs a sign-in, Claude sends you to it. Then turn the connector on in a chat from the tools menu and ask.
Custom connectors are available on paid Claude plans; on Team and Enterprise accounts an admin may need to add them. Our "Working" label means the server answered us; it cannot tell whether your plan lets you add it. All connectors that work in Claude
https://agentosaurus.com/mcpResponse time at the last check: 54ms. Worked in n/a of checks over 30 days.
Screened, no issues found
Screening looks for known threats and hidden instructions at the time of the check, and runs again weekly and whenever the tool list changes. It cannot see the server's code, so only connect what you need and review what Muse asks to do. How screening works.
get_pricingPublished 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_quoteAn itemised quote for one model size, with dataset-only, dataset-plus-compute and selection totals. Same data as /agents/quote.json.get_review_scopeThe 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_offerThe 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. Samlist_nodesGPU 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_costWhat 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.list_blog_postsPublished blog posts, newest first, with excerpts and tags.get_blog_postThe full Markdown of one published post.about_wingieWho wingie, the AI agent at Agentosaurus, is, what it may do and how to reach the team. Same text as /wingie.txt.how_to_contactThe contact address and the ways to reach a person at Agentosaurus.search_organizationsSearch the public directory of analysed organisations (the /planet-agent/ directory) by name, city and SDG goal. Returns public profile fields only.get_organizationThe public profile of one organisation and the questions ask_organization can answer about it.ask_organizationAnswers 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.list_eventsUpcoming published volunteer events, soonest first, with their shifts. Same events as /events/volunteer/find/.find_volunteer_shiftsUpcoming volunteer shifts with the spots still open, the event and the organiser's public page.get_eventOne published volunteer event with its shifts and the organiser's public page.partner_matchRanks organisations by alignment with the SDG goals a business wants to advance, the same matching as /partner-match/.food_rescue_amsterdamDonating surplus food to Taste Before You Waste in Amsterdam, joining them as a volunteer, and what the organisation does.get_lab_experimentsEvery experiment on /lab/: what ran, the number, its state, and the compute a queued run needs. Same text as /lab.txt.get_topicThe text of one topic page: AI safety, AI sovereignty, AI security, or the Dutch sovereign-hardware page.get_inventoryWhich parts of Agentosaurus you can use today and which are not built yet. Same text as /inventory.txt.review_readinessA 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.search_kitsKits and reports on sale in the shop, with price in EUR and the product page to buy from.get_kitOne kit or report on sale, with its price in EUR and the product page to buy from.esg_report_offerWhat a full VerifyAgent ESG due-diligence report contains and costs, with the upgrade and investigate pages.signupRegisters an email address with Agentosaurus, optionally with an interest. A person replies. Charges nothing. Limited to 5 per hour per address.request_scoping_callAsks Agentosaurus for a scoping call about the Review, the policy gateway (tier policy_gateway, Starter included), LOGOS or sovereign training. A person replies by email. Charges nothing. Limited to 5 per hour per address.request_data_removalAsks 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. A person reviews it and replies by email within 30 days; nothing is removed automatically. Returns a reference code only. Limited https://agentosaurus.com/mcpNot in Muse's Connectors list yet, but Muse can still use it. Paste this into Muse: "Use Agentosaurus to help me. It is a free service with an MCP server at https://agentosaurus.com/mcp. It does not need an API key. Ask me before you share anything with it." Muse asks before it shares anything with the app's site. Meta does not review apps used this way, so only use ones you trust. We tested this in the Muse app on September 24, 2026: Muse used an app's link directly this way and returned a live answer.
At the last check (November 16, 2026, 15:31 UTC) the endpoint was working, answering in 54ms. It is checked every 15 minutes.
It was screened on November 16, 2026 with the result "screened, no issues found". Screening checks the domain against threat feeds and reads the tools for hidden instructions and requests for passwords or card numbers. It cannot see the server's code, so grant only the access you need.
Yes. The connector is free to use. Your Muse plan and any account with Agentosaurus are separate.
It exposes 28 tools, including get_pricing, get_quote, get_review_scope, get_policy_gateway_offer. For example, you could ask Muse: "Which EU AI Act and GDPR items should my small business review for the AI agents we run in production?"
Paste this on your site or README. It always shows the latest check.
<a href="https://musedirectory.ai/connector/agentosaurus"><img src="https://musedirectory.ai/badge/agentosaurus.svg" alt="Agentosaurus on musedirectory.ai" width="236" height="40"></a>