Is recoup-public-website live?

Yes — it answered the hub's last check (checked 19h ago). It answered 100% of checks over the last 30 days.

Is recoup-public-website free to use?

Yes — the hub reached it with no key and no payment.

What tools does recoup-public-website have?

5 tools: estimate_workflow_roi, prepare_project_brief, search_recoup, read_recoup_page, assess_workflow_readiness.

Is recoup-public-website 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.

_ registry / mcp http-sse · checked 19h ago

recoup-public-website

https://recoupable.dev

Registry code: 866493ef4a189ca8

api record

Search and read published Recoup content, calculate supplied scenarios, or prepare an unsubmitted project brief. These tools never access platform accounts. Do not send credentials or private records. ROI is illustrative capacity value, not guaranteed savings.

endpoint: https://recoupable.dev/mcp
protocol: http-sse ·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 recoup-public-website live?: Yes — it answered the hub's last check (checked 19h ago). It answered 100% of checks over the last 30 days.
Is recoup-public-website free to use?: Yes — the hub reached it with no key and no payment.
What tools does recoup-public-website have?: 5 tools: estimate_workflow_roi, prepare_project_brief, search_recoup, read_recoup_page, assess_workflow_readiness.
Is recoup-public-website 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

453ms

last good check

priced tools

of 5 tools

_ answered our checks, 90 days 1 checks · signed record

2026-11-10 04:24 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

through this hub

calls served

successful

paid through this hub

0 USDC

what callers paid

inferred, not observed

Access was read off the card rather than seen on the wire: inferred: the handshake, the tool list and a call without arguments went through with no key and no payment asked; no tool was run

_ what it can do 5 tools

5 never probed 0 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.

estimate_workflow_roi unknown 19h ago

Calculate the potential value of time saved on one workflow using five explicit assumptions. Returns hours saved, capacity value, recurring net value, first-year net value, and payback. All costs are USD. Capacity value is not guaranteed cash savings; this does not generate a quote or submit a lead.

mcp-tool

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "monthlyHours",
    "hourlyCost",
    "timeReduction",
    "monthlySystemCost",
    "setupCost"
  ],
  "properties": {
    "setupCost": {
      "type": "number",
      "maximum": 10000000,
      "minimum": 0,
      "description": "Estimated one-time implementation cost, in USD."
    },
    "hourlyCost": {
      "type": "number",
      "maximum": 10000,
      "minimum": 0,
      "description": "Loaded labor cost in USD per person-hour."
    },
    "monthlyHours": {
      "type": "number",
      "maximum": 100000,
      "minimum": 0,
      "description": "Current total team hours spent on this workflow per month, in hours/month."
    },
    "timeReduction": {
      "type": "number",
      "maximum": 100,
      "minimum": 0,
      "description": "Assumed share of current work time saved, in percent from 0 to 100. Supply your own assumption; this is not a Recoup performance promise."
    },
    "monthlySystemCost": {
      "type": "number",
      "maximum": 1000000,
      "minimum": 0,
      "description": "Estimated recurring system and operating cost, in USD/month."
    }
  },
  "additionalProperties": false
}

arguments 44 lines

prepare_project_brief unknown 19h ago

Prepare a short project inquiry draft from a workflow, desired outcome, and optional tools and frequency. Returns text the user can review on /contact. Does not save information, submit an inquiry, contact Recoup, book a call, or promise scope or pricing.

mcp-tool

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "workflow",
    "desiredOutcome"
  ],
  "properties": {
    "tools": {
      "type": "string",
      "maxLength": 500,
      "minLength": 1,
      "description": "Optional tools or data sources involved."
    },
    "interest": {
      "enum": [
        "AI strategy",
        "Custom systems",
        "Team training",
        "Podcast guest",
        "Not sure yet"
      ],
      "type": "string",
      "default": "Not sure yet"
    },
    "workflow": {
      "type": "string",
      "maxLength": 500,
      "minLength": 20,
      "description": "Describe the current workflow and where work gets difficult. Do not include passwords or confidential records."
    },
    "frequency": {
      "type": "string",
      "maxLength": 120,
      "minLength": 1,
      "description": "Optional description of how often the work happens."
    },
    "desiredOutcome": {
      "type": "string",
      "maxLength": 500,
      "minLength": 10,
      "description": "What the team would like to improve or produce."
    }
  },
  "additionalProperties": false
}

arguments 46 lines

search_recoup unknown never probed

Search Recoup’s public website, guides, API documentation, blog, and playbook. Returns matching public content with IDs for read_recoup_page. Use a relevant query and optional content type; follow the returned cursor for more matches.

mcp-tool

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "query"
  ],
  "properties": {
    "type": {
      "enum": [
        "all",
        "page",
        "blog",
        "playbook"
      ],
      "type": "string",
      "default": "all"
    },
    "limit": {
      "type": "integer",
      "default": 5,
      "maximum": 10,
      "minimum": 1
    },
    "query": {
      "type": "string",
      "maxLength": 240,
      "minLength": 1,
      "description": "Words or a question to search for."
    },
    "cursor": {
      "type": "string",
      "maxLength": 200,
      "minLength": 1,
      "description": "Opaque pagination cursor returned by the previous search."
    }
  },
  "additionalProperties": false
}

arguments 38 lines

read_recoup_page unknown never probed

Read the public text of a Recoup page by an ID returned by search_recoup. Use the returned continuation offset when the content is longer than one response. Does not browse arbitrary URLs or read private account data.

mcp-tool

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "id"
  ],
  "properties": {
    "id": {
      "type": "string",
      "maxLength": 300,
      "minLength": 1,
      "description": "Public content ID returned by search_recoup."
    },
    "offset": {
      "type": "integer",
      "default": 0,
      "maximum": 9007199254740991,
      "minimum": 0,
      "description": "Character offset supplied by the previous response; start at zero."
    },
    "maxLength": {
      "type": "integer",
      "default": 6000,
      "maximum": 12000,
      "minimum": 1,
      "description": "Maximum characters to return."
    }
  },
  "additionalProperties": false
}

arguments 30 lines

assess_workflow_readiness unknown 19h ago

Recommend a practical next step for one music-business workflow from Recoup’s readiness check. All seven answers are collected for the summary; information access, task clarity, and workflow ownership decide the recommendation. Ask the user for any missing answer; do not infer it. Returns a recommendation and next steps, not a numerical score, certification, or promise of readiness.

mcp-tool

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "answers"
  ],
  "properties": {
    "answers": {
      "type": "object",
      "required": [
        "workflow",
        "frequency",
        "information",
        "access",
        "method",
        "owner",
        "ai"
      ],
      "properties": {
        "ai": {
          "enum": [
            "We have a repeatable workflow",
            "A few people use individual tools",
            "We are getting started"
          ],
          "type": "string",
          "description": "How is the team using AI today?"
        },
        "owner": {
          "enum": [
            "We have someone in mind",
            "We need to agree on an owner",
            "We need help training the team"
          ],
          "type": "string",
          "description": "Who would review and own the new workflow?"
        },
        "access": {
          "enum": [
            "Yes, with the permissions we need",
            "Some of it; we need to arrange access",
            "We are not sure yet"
          ],
          "type": "string",
          "description": "Can your team access that information?"
        },
        "method": {
          "enum": [
            "Yes, the steps are documented",
            "With help from the person doing it",
            "Not yet; it changes each time"
          ],
          "type": "string",
          "description": "Could someone else follow your current process?"
        },
        "workflow": {
          "enum": [
            "Reporting and finance",
            "Research and acquisition review",
            "Content and release planning",
            "Still deciding"
          ],
          "type": "string",
          "description": "Which recurring work would you like to improve?"
        },
        "frequency": {
          "enum": [
            "Every day",
            "Every week",
            "Every month",
            "Occasionally"
          ],
          "type": "string",
          "description": "How often does your team do this work?"
        },
        "information": {
          "enum": [
            "Mostly in one system",
            "Across several tools and files",
            "We need to identify it"
          ],
          "type": "string",
          "description": "Where is the information the task needs?"
        }
      },
      "additionalProperties": false
    }
  },
  "additionalProperties": false
}

arguments 90 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.

Sign any request with an ed25519 key — that binds it: GET /api/v1/me, then POST /api/v1/passport.
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.
Ask the hub to check: POST /api/v1/passport/claim-endpoint with this listing's id 866493ef4a189ca8.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/866493ef4a189ca8/claim. Over MCP: the claim_endpoint tool.

_ for your README measured, not declared

[![measured by brick.blue](https://brick.blue/api/v1/agents/866493ef4a189ca8/badge.svg)](https://brick.blue/agent/866493ef4a189ca8?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

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.

_ also on recoupable.dev 2 entries

Served from the same domain, which is what was measured. Not a claim that one owner runs them: ownership is what a passport proves, and each of these says for itself.

docs.recoupable.dev recoup-docs mcp · 2 tools
api.recoupable.dev api.recoupable.dev mcp · 0 tools