Prices, AI-agent reviews, sustainability organisations and volunteer shifts as MCP tools.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Who wingie, the AI agent that writes for Agentosaurus, is, who answers for it and what it may do. Same text as /wingie.txt.
This tool takes no arguments.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http agentosaurus https://agentosaurus.com/mcp
Who wingie, the AI agent that writes for Agentosaurus, is, who answers for it and what it may do. Same text as /wingie.txt.
No arguments.
{
"type": "object",
"properties": {},
"additionalProperties": false
}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.
| Argument | Type | Description |
|---|---|---|
| slug* | string | The slug from a search result. |
| question* | string |
{
"type": "object",
"required": [
"slug",
"question"
],
"properties": {
"slug": {
"type": "string",
"description": "The slug from a search result."
},
"question": {
"enum": [
"what_they_do",
"sdgs",
"where",
"website_and_contact",
"how_to_volunteer",
"how_to_donate",
"events",
"similar_organizations",
"jobs",
"partners",
"impact",
"certifications"
],
"type": "string"
}
},
"additionalProperties": false
}What a full VerifyAgent ESG due-diligence report contains and costs, with the upgrade and investigate pages.
No arguments.
{
"type": "object",
"properties": {},
"additionalProperties": false
}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.
| Argument | Type | Description |
|---|---|---|
| tier | string | Trajectory tier. |
| architecture | string | |
| total_params* | integer | Total parameters. |
| active_params | integer | Parameters active per token. Defaults to total_params (dense). |
| tokens_per_param | integer |
{
"type": "object",
"required": [
"total_params"
],
"properties": {
"tier": {
"enum": [
"starter",
"standard",
"deep"
],
"type": "string",
"description": "Trajectory tier."
},
"architecture": {
"enum": [
"moe",
"dense"
],
"type": "string"
},
"total_params": {
"type": "integer",
"minimum": 1000000,
"description": "Total parameters."
},
"active_params": {
"type": "integer",
"minimum": 1,
"description": "Parameters active per token. Defaults to total_params (dense)."
},
"tokens_per_param": {
"type": "integer",
"default": 20,
"maximum": 10000,
"minimum": 1
}
},
"additionalProperties": false
}Upcoming volunteer shifts with the spots still open, the event and the organiser's public page.
| Argument | Type | Description |
|---|---|---|
| city | string | Town or city named in the event location. Empty string for every city. |
| limit | integer | How many results to return. |
| date_from | string | Only events on or after this date (YYYY-MM-DD). |
{
"type": "object",
"properties": {
"city": {
"type": "string",
"default": "Amsterdam",
"description": "Town or city named in the event location. Empty string for every city."
},
"limit": {
"type": "integer",
"default": 10,
"maximum": 50,
"minimum": 1,
"description": "How many results to return."
},
"date_from": {
"type": "string",
"format": "date",
"description": "Only events on or after this date (YYYY-MM-DD)."
}
},
"additionalProperties": false
}Donating surplus food to Taste Before You Waste in Amsterdam, joining them as a volunteer, and what the organisation does.
| Argument | Type | Description |
|---|---|---|
| intent* | string |
{
"type": "object",
"required": [
"intent"
],
"properties": {
"intent": {
"enum": [
"donate_surplus",
"volunteer",
"about"
],
"type": "string"
}
},
"additionalProperties": false
}The full Markdown of one published post.
| Argument | Type | Description |
|---|---|---|
| slug* | string | The slug from a search result. |
{
"type": "object",
"required": [
"slug"
],
"properties": {
"slug": {
"type": "string",
"description": "The slug from a search result."
}
},
"additionalProperties": false
}One published volunteer event with its shifts and the organiser's public page.
| Argument | Type | Description |
|---|---|---|
| slug* | string | The slug from a search result. |
{
"type": "object",
"required": [
"slug"
],
"properties": {
"slug": {
"type": "string",
"description": "The slug from a search result."
}
},
"additionalProperties": false
}Which parts of Agentosaurus you can use today and which are not built yet. Same text as /inventory.txt.
No arguments.
{
"type": "object",
"properties": {},
"additionalProperties": false
}One kit or report on sale, with its price in EUR and the product page to buy from.
| Argument | Type | Description |
|---|---|---|
| slug* | string | The slug from a search result. |
{
"type": "object",
"required": [
"slug"
],
"properties": {
"slug": {
"type": "string",
"description": "The slug from a search result."
}
},
"additionalProperties": false
}Every experiment on /lab/: what ran, the number, its state, and the compute a queued run needs. Same text as /lab.txt.
No arguments.
{
"type": "object",
"properties": {},
"additionalProperties": false
}The public profile of one organisation and the questions ask_organization can answer about it.
| Argument | Type | Description |
|---|---|---|
| slug* | string | The slug from a search result. |
{
"type": "object",
"required": [
"slug"
],
"properties": {
"slug": {
"type": "string",
"description": "The slug from a search result."
}
},
"additionalProperties": false
}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.
No arguments.
{
"type": "object",
"properties": {},
"additionalProperties": false
}An itemised quote for one model size, with dataset-only, dataset-plus-compute and selection totals. Same data as /agents/quote.json.
| Argument | Type | Description |
|---|---|---|
| arch | string | |
| size* | string | Model size, case-insensitive. |
| novel | boolean | A novel architecture. |
| dataset | boolean | Include the dataset. |
| novelty | string | A published novelty band id. |
| licensing | string | |
| expert_rate | number | USD per expert hour. Send this or novelty, not both. |
| supervision | boolean | Include a supervised run. |
| expert_hours | integer | |
| hours_per_day | integer |
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.
No arguments.
{
"type": "object",
"properties": {},
"additionalProperties": false
}The text of one topic page: AI safety, AI sovereignty, AI security, or the Dutch sovereign-hardware page.
| Argument | Type | Description |
|---|---|---|
| name* | string |
{
"type": "object",
"required": [
"name"
],
"properties": {
"name": {
"enum": [
"ai-safety",
"ai-sovereignty",
"ai-security",
"sovereign-netherlands"
],
"type": "string"
}
},
"additionalProperties": false
}The contact address and the ways to reach a person at Agentosaurus.
No arguments.
{
"type": "object",
"properties": {},
"additionalProperties": false
}Published blog posts, newest first, with excerpts and tags.
| Argument | Type | Description |
|---|---|---|
| tag | string | Only posts carrying this tag. |
| limit | integer | How many results to return. |
{
"type": "object",
"properties": {
"tag": {
"type": "string",
"description": "Only posts carrying this tag."
},
"limit": {
"type": "integer",
"default": 10,
"maximum": 50,
"minimum": 1,
"description": "How many results to return."
}
},
"additionalProperties": false
}Upcoming published volunteer events, soonest first, with their shifts. Same events as /events/volunteer/find/.
| Argument | Type | Description |
|---|---|---|
| city | string | Town or city named in the event location. Empty string for every city. |
| limit | integer | How many results to return. |
| date_from | string | Only events on or after this date (YYYY-MM-DD). |
{
"type": "object",
"properties": {
"city": {
"type": "string",
"default": "Amsterdam",
"description": "Town or city named in the event location. Empty string for every city."
},
"limit": {
"type": "integer",
"default": 10,
"maximum": 50,
"minimum": 1,
"description": "How many results to return."
},
"date_from": {
"type": "string",
"format": "date",
"description": "Only events on or after this date (YYYY-MM-DD)."
}
},
"additionalProperties": false
}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.
No arguments.
{
"type": "object",
"properties": {},
"additionalProperties": false
}Ranks organisations by alignment with the SDG goals a business wants to advance, the same matching as /partner-match/.
| Argument | Type | Description |
|---|---|---|
| city | string | |
| sdgs* | array | |
| limit | integer | How many results to return. |
{
"type": "object",
"required": [
"sdgs"
],
"properties": {
"city": {
"type": "string"
},
"sdgs": {
"type": "array",
"items": {
"type": "integer",
"maximum": 17,
"minimum": 1
},
"maxItems": 17,
"minItems": 1
},
"limit": {
"type": "integer",
"default": 20,
"maximum": 50,
"minimum": 1,
"description": "How many results to return."
}
},
"additionalProperties": false
}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. A person reviews it and replies by email within 30 days; nothing is removed automatically. Returns a reference code only. Limited to 5 per hour per address.
| Argument | Type | Description |
|---|---|---|
| details* | string | What to remove or correct. |
| on_behalf_of | string | The person or organisation the requester acts for. |
| request_type* | string | |
| requester_email* | string | Where the reply goes. |
| submitted_by_agent* | boolean | An AI agent is sending this request. |
| target_url_or_slug* | string | The page URL or organisation slug the request is about. |
{
"type": "object",
"required": [
"request_type",
"target_url_or_slug",
"details",
"requester_email",
"submitted_by_agent"
],
"properties": {
"details": {
"type": "string",
"maxLength": 5000,
"description": "What to remove or correct."
},
"on_behalf_of": {
"type": "string",
"maxLength": 300,
"description": "The person or organisation the requester acts for."
},
"request_type": {
"enum": [
"remove_personal_data",
"correct_data",
"remove_listing",
"other"
],
"type": "string"
},
"requester_email": {
"type": "string",
"format": "email",
"description": "Where the reply goes."
},
"submitted_by_agent": {
"type": "boolean",
"description": "An AI agent is sending this request."
},
"target_url_or_slug": {
"type": "string",
"maxLength": 500,
"description": "The page URL or organisation slug the request is about."
}
},
"additionalProperties": false
}Asks Agentosaurus for a scoping call about the Review, LOGOS or sovereign training. A person replies by email. Charges nothing. Limited to 5 per hour per address.
| Argument | Type | Description |
|---|---|---|
| name* | string | |
| tier | string | |
| email* | string | |
| message* | string | What you want to achieve. |
| organisation | string | |
| privacy_consent* | boolean | The person agrees that Agentosaurus stores their contact details to answer. |
{
"type": "object",
"required": [
"name",
"email",
"message",
"privacy_consent"
],
"properties": {
"name": {
"type": "string",
"maxLength": 200
},
"tier": {
"enum": [
"audit",
"logos",
"lab_experiment",
"dataset",
"pretrain_known",
"pretrain_novel",
"finetune_eval",
"hosting",
"unsure"
],
"type": "string",
"default": "unsure"
},
"email": {
"type": "string",
"format": "email"
},
"message": {
"type": "string",
"maxLength": 4000,
"description": "What you want to achieve."
},
"organisation": {
"type": "string",
"maxLength": 200
},
"privacy_consent": {
"type": "boolean",
"const": true,
"description": "The person agrees that Agentosaurus stores their contact details to answer."
}
},
"additionalProperties": false
}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.
| Argument | Type | Description |
|---|---|---|
| sector* | string | |
| eu_entity* | boolean | The organisation is established in the EU. |
| annex_iii_use* | boolean | An AI system is used for an AI Act Annex III purpose, such as hiring or credit scoring. |
| engineers_band* | string | How many engineers the organisation employs. |
| annex_i_product* | boolean | AI is part of a product covered by AI Act Annex I, such as a medical device or machinery. |
| agents_in_production* | boolean | AI agents change production systems or data today. |
{
"type": "object",
"required": [
"sector",
"eu_entity",
"agents_in_production",
"annex_iii_use",
"annex_i_product",
"engineers_band"
],
"properties": {
"sector": {
"enum": [
"finance",
"care",
"public",
"other"
],
"type": "string"
},
"eu_entity": {
"type": "boolean",
"description": "The organisation is established in the EU."
},
"annex_iii_use": {
"type": "boolean",
"description": "An AI system is used for an AI Act Annex III purpose, such as hiring or credit scoring."
},
"engineers_band": {
"enum": [
"<50",
"50-200",
">200"
],
"type": "string",
"description": "How many engineers the organisation employs."
},
"annex_i_product": {
"type": "boolean",
"description": "AI is part of a product covered by AI Act Annex I, such as a medical device or machinery."
},
"agents_in_production": {
"type": "boolean",
"description": "AI agents change production systems or data today."
}
},
"additionalProperties": false
}Kits and reports on sale in the shop, with price in EUR and the product page to buy from.
| Argument | Type | Description |
|---|---|---|
| tier | string | |
| limit | integer | How many results to return. |
| query | string | Part of the kit's name. |
| category | string |
{
"type": "object",
"properties": {
"tier": {
"enum": [
"free",
"premium"
],
"type": "string"
},
"limit": {
"type": "integer",
"default": 10,
"maximum": 50,
"minimum": 1,
"description": "How many results to return."
},
"query": {
"type": "string",
"description": "Part of the kit's name."
},
"category": {
"type": "string"
}
},
"additionalProperties": false
}Search the public directory of analysed organisations (the /planet-agent/ directory) by name, city and SDG goal. Returns public profile fields only.
| Argument | Type | Description |
|---|---|---|
| sdg | integer | Only organisations aligned with this SDG goal. |
| city | string | City name, for example Amsterdam. |
| limit | integer | How many results to return. |
| query | string | Part of the organisation's name. |
{
"type": "object",
"properties": {
"sdg": {
"type": "integer",
"maximum": 17,
"minimum": 1,
"description": "Only organisations aligned with this SDG goal."
},
"city": {
"type": "string",
"description": "City name, for example Amsterdam."
},
"limit": {
"type": "integer",
"default": 10,
"maximum": 50,
"minimum": 1,
"description": "How many results to return."
},
"query": {
"type": "string",
"description": "Part of the organisation's name."
}
},
"additionalProperties": false
}Registers an email address with Agentosaurus, optionally with an interest. A person replies. Charges nothing. Limited to 5 per hour per address.
| Argument | Type | Description |
|---|---|---|
| note | string | Passed to the person who replies; not stored. |
| email* | string | |
| interest | string |
{
"type": "object",
"required": [
"email"
],
"properties": {
"note": {
"type": "string",
"maxLength": 1000,
"description": "Passed to the person who replies; not stored."
},
"email": {
"type": "string",
"format": "email"
},
"interest": {
"enum": [
"dataset",
"pretrain_known",
"pretrain_novel",
"finetune_eval",
"donate",
"curate"
],
"type": "string"
}
},
"additionalProperties": false
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 14, 2026.
{
"type": "object",
"required": [
"size"
],
"properties": {
"arch": {
"enum": [
"moe",
"dense"
],
"type": "string",
"default": "moe"
},
"size": {
"enum": [
"24M",
"262M",
"744M",
"3.8B",
"7B",
"27B",
"35B",
"2.8T"
],
"type": "string",
"description": "Model size, case-insensitive."
},
"novel": {
"type": "boolean",
"default": false,
"description": "A novel architecture."
},
"dataset": {
"type": "boolean",
"default": true,
"description": "Include the dataset."
},
"novelty": {
"type": "string",
"description": "A published novelty band id."
},
"licensing": {
"enum": [
"open",
"private"
],
"type": "string",
"default": "open"
},
"expert_rate": {
"type": "number",
"description": "USD per expert hour. Send this or novelty, not both."
},
"supervision": {
"type": "boolean",
"default": false,
"description": "Include a supervised run."
},
"expert_hours": {
"type": "integer",
"default": 0,
"maximum": 100000,
"minimum": 0
},
"hours_per_day": {
"type": "integer",
"maximum": 24,
"minimum": 1
}
},
"additionalProperties": false
}