agentfulfyl

Research storefront for AI agents: fixed GBP prices, evidence ledgers, citation-refund guarantee.

Should I use this

Quality & Safety

A
Description quality
100%
Schema completeness
77%
Naming quality
100%
Poisoning risk
80%
Permission match
100%
Protocol compliance
100%

Findings (2)

  • HIGHTool poisoning patterns detected
  • MEDIUMTool description contains URL to non-standard domainin get_catalog

Based on automated analysis of tool definitions and protocol compliance.

Context Cost

~374Tokens (tool definitions)
~804 BTypical response size
Minimal attention impact (0.29% of 128k context)

This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.

Install

One-Click Install

Add this to your `claude_desktop_config.json` file:

{
  "mcpServers": {
    "agentfulfyl": {
      "url": "https://agentfulfyl.com/mcp"
    }
  }
}

Remote endpoints

https://agentfulfyl.com/mcpstreamable-http

What it can do

Tool inventory

Tools (3)

🟢 Read-only🟡 Write🔴 Delete⚪ Unknown
🟢get_catalog

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.

Input Schema

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
🟢get_product(product_id)

One product in full: summary, per-tier GBP prices, deliverables, and the exact input contract an order must fill. Ids come from get_catalog.

Input Schema

{
  "type": "object",
  "properties": {
    "product_id": {
      "type": "string",
      "description": "Product id from get_catalog, e.g. \"business-idea-gap-scan\"."
    }
  },
  "required": [
    "product_id"
  ],
  "additionalProperties": false
}
🟡submit_demand(requester, kind, query, channel)

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.

Input Schema

{
  "type": "object",
  "properties": {
    "requester": {
      "type": "string",
      "enum": [
        "agent",
        "human"
      ],
      "description": "Who is submitting."
    },
    "kind": {
      "type": "string",
      "enum": [
        "unmet_need",
        "exploring",
        "introduction",
        "other"
      ],
      "description": "Why you are here. Optional."
    },
    "query": {
      "type": "string",
      "minLength": 3,
      "maxLength": 500,
      "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."
    }
  },
  "required": [
    "requester",
    "query"
  ],
  "additionalProperties": false
}

Community

Rate this Server

Evidence

Recent observations

verifiedversion not recorded3 tools
verifiedversion not recorded3 tools
verifiedversion not recorded3 tools