_ registry / mcp streamable-http

Decknote

https://decknote.app

Registry code: aee3bdd3a4ae7fb7

api record

Decknote task memory. Call list_boards first to discover board and list ids, then create_task / search_tasks / complete_task. search_tasks is your recall tool. create_board / create_list set up new structure; task descriptions accept Markdown.

endpoint
https://decknote.app/api/v1/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 Decknote live?
Not measured yet: the hub has not completed a check of this server.
Is Decknote free to use?
Not measured yet.
What tools does Decknote have?
12 tools: list_boards, create_list, search_tasks, get_task, archive_task, create_board, create_task, update_task, ….
Is Decknote 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
unknown
uptime
—
latency
—

last good check

priced tools
0

of 12 tools

_ 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 12 tools
12 never probed 0 of 12 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.

  • list_boards unknown never probed

    List the boards you can access and their lists. Start here: the returned board and list ids are what the other tools need.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "includeArchived": {
      "type": "boolean",
      "description": "Include archived boards. Default false."
    }
  }
}
    arguments 9 lines
  • create_list unknown never probed

    Add a list (column) at the end of a board. Returns its id for create_task / move_task.

    mcp-tool

    {
  "type": "object",
  "required": [
    "boardId",
    "title"
  ],
  "properties": {
    "title": {
      "type": "string"
    },
    "boardId": {
      "type": "string"
    }
  }
}
    arguments 15 lines
  • search_tasks unknown never probed

    Search your tasks (cards) — the recall tool. Filter by free text (matches title and description), board, list, status and due date. Use this to answer 'what's still open', 'what did I note about X', 'what's due soon'.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "limit": {
      "type": "number",
      "description": "Max results, 1–100. Default 20."
    },
    "query": {
      "type": "string",
      "description": "Free text; matches card title and description."
    },
    "listId": {
      "type": "string"
    },
    "status": {
      "enum": [
        "open",
        "completed",
        "all"
      ],
      "type": "string",
      "description": "Default 'open'."
    },
    "boardId": {
      "type": "string"
    },
    "dueBefore": {
      "type": "string",
      "description": "ISO 8601; only tasks due before this instant."
    }
  }
}
    arguments 32 lines
  • get_task unknown never probed

    Read one task in full: title, description, due date, completion, and which board/list it's in.

    mcp-tool

    {
  "type": "object",
  "required": [
    "cardId"
  ],
  "properties": {
    "cardId": {
      "type": "string"
    }
  }
}
    arguments 11 lines
  • archive_task unknown never probed

    Archive a task — the cleanup tool. Soft-delete: the card leaves the board but keeps its data and can be restored from the board's Archived panel. Archiving a dated recurring task schedules its next occurrence, same as archiving from the UI.

    mcp-tool

    {
  "type": "object",
  "required": [
    "cardId"
  ],
  "properties": {
    "cardId": {
      "type": "string"
    }
  }
}
    arguments 11 lines
  • create_board unknown never probed

    Create a new board you own. Optional template picks the initial lists and labels (created in your account's language): 'blank' (To do / In progress / Done), 'kanban', 'content' or 'personal'. Returns the board with its list ids, ready for create_task.

    mcp-tool

    {
  "type": "object",
  "required": [
    "title"
  ],
  "properties": {
    "title": {
      "type": "string"
    },
    "template": {
      "enum": [
        "blank",
        "kanban",
        "content",
        "personal"
      ],
      "type": "string",
      "description": "Initial lists/labels. Default 'blank'."
    }
  }
}
    arguments 21 lines
  • create_task unknown never probed

    Add a task (card). Provide listId, or boardId to drop it in that board's first list. Title is required; description becomes the card's page and accepts Markdown (headings, bullet/numbered lists, - [ ] task lists, bold/italic/code, links, fenced code).

    mcp-tool

    {
  "type": "object",
  "required": [
    "title"
  ],
  "properties": {
    "title": {
      "type": "string"
    },
    "listId": {
      "type": "string"
    },
    "boardId": {
      "type": "string",
      "description": "Used if listId is omitted."
    },
    "dueDate": {
      "type": "string",
      "description": "ISO 8601."
    },
    "description": {
      "type": "string"
    }
  }
}
    arguments 25 lines
  • update_task unknown never probed

    Edit a task's title, description or due date. Description accepts Markdown; note that setting it REPLACES the card's page (use add_comment for incremental notes). Pass dueDate null to clear it.

    mcp-tool

    {
  "type": "object",
  "required": [
    "cardId"
  ],
  "properties": {
    "title": {
      "type": "string"
    },
    "cardId": {
      "type": "string"
    },
    "dueDate": {
      "type": [
        "string",
        "null"
      ],
      "description": "ISO 8601, or null to clear."
    },
    "description": {
      "type": "string"
    }
  }
}
    arguments 24 lines
  • complete_task unknown never probed

    Mark a task done.

    mcp-tool

    {
  "type": "object",
  "required": [
    "cardId"
  ],
  "properties": {
    "cardId": {
      "type": "string"
    }
  }
}
    arguments 11 lines
  • reopen_task unknown never probed

    Reopen a completed task.

    mcp-tool

    {
  "type": "object",
  "required": [
    "cardId"
  ],
  "properties": {
    "cardId": {
      "type": "string"
    }
  }
}
    arguments 11 lines
  • move_task unknown never probed

    Move a task to a different list (e.g. from 'To do' to 'Doing'). The target list must be one you can edit.

    mcp-tool

    {
  "type": "object",
  "required": [
    "cardId",
    "listId"
  ],
  "properties": {
    "cardId": {
      "type": "string"
    },
    "listId": {
      "type": "string",
      "description": "Target list id."
    }
  }
}
    arguments 16 lines
  • add_comment unknown never probed

    Add a comment to a task — useful for leaving progress notes a human will read.

    mcp-tool

    {
  "type": "object",
  "required": [
    "cardId",
    "text"
  ],
  "properties": {
    "text": {
      "type": "string"
    },
    "cardId": {
      "type": "string"
    }
  }
}
    arguments 15 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 aee3bdd3a4ae7fb7.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/aee3bdd3a4ae7fb7/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/aee3bdd3a4ae7fb7/badge.svg)](https://brick.blue/agent/aee3bdd3a4ae7fb7?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
100%

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.