io.github.Capataina/agentfulfyl is an MCP server published by io.github.Capataina, hosted at agentfulfyl.com. When last checked on 2026-11-22 it was working: it answers and lists its tools. It declares 3 tools, including get_catalog, get_product, submit_demand.
Research storefront for AI agents: fixed GBP prices, evidence ledgers, citation-refund guarantee.
1 connections through 4 shared values. Tap any node.
The full catalogue as JSON: every product with its per-tier prices in GBP, deliverables, input contract, and status, plus store info, the five rigour tiers, and the citation-refund guarantee. Same data as https://agentfulfyl.com/catalog.json.
No parameters.
{
"name": "get_catalog",
"description": "The full catalogue as JSON: every product with its per-tier prices in GBP, deliverables, input contract, and status, plus store info, the five rigour tiers, and the citation-refund guarantee. Same data as https://agentfulfyl.com/catalog.json.",
"inputSchema": {
"type": "object",
"properties": {},
"additionalProperties": false
}
}One product in full: summary, per-tier GBP prices, deliverables, and the exact input contract an order must fill. Ids come from get_catalog.
| Parameter |
|---|
None yet. Changes appear after a server's second daily check.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
Inferred from the host name and headers: what a server runs on, not who runs it.
| Type |
|---|
| Description |
|---|
| product_id * | string | Product id from get_catalog, e.g. "business-idea-gap-scan". |
{
"name": "get_product",
"description": "One product in full: summary, per-tier GBP prices, deliverables, and the exact input contract an order must fill. Ids come from get_catalog.",
"inputSchema": {
"type": "object",
"required": [
"product_id"
],
"properties": {
"product_id": {
"type": "string",
"description": "Product id from get_catalog, e.g. \"business-idea-gap-scan\"."
}
},
"additionalProperties": false
}
}Tell the store why you came: what you looked for and did not find (kind "unmet_need" decides what gets built next), or introduce yourself. One row stored per submission, nothing else. Leave a channel to hear back if your request becomes a product.
| Parameter | Type | Description |
|---|---|---|
| kind | string | Why you are here. Optional. |
| query * | string | The request, introduction, or note. 3 to 500 characters. |
| channel | string | Optional email or webhook URL to hear back on. |
| requester * | string | Who is submitting. |
{
"name": "submit_demand",
"description": "Tell the store why you came: what you looked for and did not find (kind \"unmet_need\" decides what gets built next), or introduce yourself. One row stored per submission, nothing else. Leave a channel to hear back if your request becomes a product.",
"inputSchema": {
"type": "object",
"required": [
"requester",
"query"
],
"properties": {
"kind": {
"enum": [
"unmet_need",
"exploring",
"introduction",
"other"
],
"type": "string",
"description": "Why you are here. Optional."
},
"query": {
"type": "string",
"maxLength": 500,
"minLength": 3,
"description": "The request, introduction, or note. 3 to 500 characters."
},
"channel": {
"type": "string",
"maxLength": 200,
"description": "Optional email or webhook URL to hear back on."
},
"requester": {
"enum": [
"agent",
"human"
],
"type": "string",
"description": "Who is submitting."
}
},
"additionalProperties": false
}
}AgentFulfyl is a research storefront built for AI agents: fixed-price research deliverables in GBP, each shipped with a machine-checkable Evidence Ledger and a citation-refund guarantee (any cited claim that fails a citation-support spot-check refunds the order in full). Canonical URL: https://agentfulfyl.com. The full agent guide is at https://agentfulfyl.com/llms.txt. Ordering and payments arrive with v1 and are not live yet; today you can read the catalogue (get_catalog, get_product) and leave a demand signal (submit_demand). Unmet requests decide which product gets built next, so telling us what you came for is genuinely useful. No accounts, no CAPTCHA, no analytics.
Names, descriptions and schemas were written by the server and are shown as data.