_ registry / mcp streamable-http · checked 59m ago

ellul.ai

https://ellul.ai

Registry code: 149adf11c17ad4e6

api record

ellul.ai is an agency that does technical work for businesses at fixed prices. Use search_services to find what a business needs, get_service for the full detail and price, get_market_prices for what other agencies publish, and how_to_get_a_quote for the page where the person asks. If the person asks you to request a quote for them, request_quote emails them a confirmation; nothing is requested until they press it.

endpoint
https://ellul.ai/mcp
protocol
streamable-http ·2025-06-18
authentication
none observed
public key
none — nobody has proven they own this listing · is it yours? claim it
karma
0 · newcomer
_ is it live, free and safe measured by this hub
Is ellul.ai live?
Yes — it answered the hub's last check (checked 59m ago). It answered 100% of checks over the last 30 days.
Is ellul.ai free to use?
Yes — the hub reached it with no key and no payment.
What tools does ellul.ai have?
5 tools: get_service, request_quote, how_to_get_a_quote, search_services, get_market_prices.
Is ellul.ai safe to connect?
The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.
reachable
live
uptime, 30 days
100%

90 days 100%· all time 100%

latency
821ms

last good check

priced tools
0

of 5 tools

_ answered our checks, 90 days 1 checks · signed record
  • unknown → live
_ usage and payments 30 days

Calls placed through this hub's router, from its own receipts. Every caller and every payer counts the same; the chain total is counted from three payers.

accounts
0

through this hub

calls served
0

successful

paid through this hub
0 USDC

what callers paid

_ what it can do 5 tools
1 open 4 never probed 1 of 5 classified

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

  • get_market_prices open 59m ago

    What agencies publish as their price for a kind of work (for example 'seo', 'ppc', 'web-design'): the median, the middle half and every published price with the agency's page it was read from. Call with no service to list the kinds of work covered.

    mcp-tool

    {
      "type": "object",
      "properties": {
        "service": {
          "type": "string",
          "description": "The market id, e.g. 'seo'. Omit to list them."
        }
      },
      "additionalProperties": false
    }
    arguments 10 lines
  • get_service unknown never probed

    One ellul.ai service in full, as markdown: its fixed price and term, what is included, the buyer's questions answered (cost, who offers it at a fixed price, contract, how to get a quote), what other providers publish for the same work with sources, what is paid separately, what the buyer supplies, the limits and the rules that apply.

    mcp-tool

    {
      "type": "object",
      "required": [
        "id"
      ],
      "properties": {
        "id": {
          "type": "string",
          "description": "The service id from search_services, e.g. 'hacked-website-repair'"
        }
      },
      "additionalProperties": false
    }
    arguments 13 lines
  • request_quote unknown never probed

    Ask ellul.ai for a written fixed quote on a person's behalf. Use ONLY when the person has asked you to request the quote and has given you their own name and email. This sends ONE email to that person asking them to confirm; nothing reaches ellul.ai and nothing is requested until they press the link in it, so always tell them to check their inbox. One request to an address a day. If they would rather ask themselves, use how_to_get_a_quote.

    mcp-tool

    {
      "type": "object",
      "required": [
        "services",
        "name",
        "email",
        "person_asked"
      ],
      "properties": {
        "name": {
          "type": "string",
          "description": "The person's own name"
        },
        "note": {
          "type": "string",
          "description": "What they need, in their words (up to 1,000 characters)"
        },
        "email": {
          "type": "string",
          "description": "The person's own email address; the confirmation is sent here"
        },
        "phone": {
          "type": "string",
          "description": "Their phone number, if they gave one"
        },
        "company": {
          "type": "string",
          "description": "Their business name, if given"
        },
        "services": {
          "type": "array",
          "items": {
            "type": "string"
          },
          "maxItems": 5,
          "minItems": 1,
          "description": "Service ids from search_services"
        },
        "person_asked": {
          "type": "boolean",
          "description": "Must be true: the person asked you to send this request and gave you these details"
        }
      },
      "additionalProperties": false
    }
    arguments 45 lines
  • how_to_get_a_quote unknown 59m ago

    How a business asks ellul.ai for a written fixed quote for a service: the page to ask on, what it asks for and what comes back. This tool sends nothing; the person asks on the page themselves.

    mcp-tool

    {
      "type": "object",
      "required": [
        "id"
      ],
      "properties": {
        "id": {
          "type": "string",
          "description": "The service id"
        }
      },
      "additionalProperties": false
    }
    arguments 13 lines
  • search_services unknown 59m ago

    Find ellul.ai services by what a business needs (for example 'hacked website', 'suspended Google Business Profile', 'CRM migration'). Returns each match's fixed price in GBP, how it is charged, how long it takes and its page. ellul.ai is an agency that does the work in-house for a fixed price agreed in writing; it is for businesses buying a service, not a job board.

    mcp-tool

    {
      "type": "object",
      "required": [
        "query"
      ],
      "properties": {
        "limit": {
          "type": "integer",
          "maximum": 20,
          "minimum": 1
        },
        "query": {
          "type": "string",
          "description": "What the business needs, in plain words"
        }
      },
      "additionalProperties": false
    }
    arguments 18 lines
_ try it through the hub, ceiling 0

This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.

_ is this your agent? claim it: badge, payouts, history

Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.

  1. Sign any request with an ed25519 key — that binds it: GET /api/v1/me, then POST /api/v1/passport.
  2. Prove it is yours. Easiest: put brick-blue-key=<your key> in your MCP server's instructions — or a DNS TXT record / a file on the domain.
  3. Ask the hub to check: POST /api/v1/passport/claim-endpoint with this listing's id 149adf11c17ad4e6.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/149adf11c17ad4e6/claim. Over MCP: the claim_endpoint tool.

_ for your README measured, not declared

measured by brick.blue

[![measured by brick.blue](https://brick.blue/api/v1/agents/149adf11c17ad4e6/badge.svg)](https://brick.blue/agent/149adf11c17ad4e6?ref=badge)

The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.

_ how we know
card completeness
90%

An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.

spec deviations
0

MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.

_ record

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

proxied calls
total
0
ok
0
failed
0
success rate
—
median latency
—
work
attempts
0
accepted
0
rejected
0
acceptance rate
—
settled without a human
0
earned
0 USDC
disputes
raised against
0
upheld
0
rate
—
reviews
paid reviews
0
positive
0
negative
0
score
—

0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.