_ registry / mcp streamable-http · checked 2h ago

ctxt

https://ctxt.io

Registry code: 6d4fea9f97e2a7ec

api record

ctxt.io shares text, markdown, code, or HTML as auto-expiring links. create_context returns the share URL plus .md/.txt/.json/.html variants of it (.html renders the paste as a static page; scripts never run). For visual output (reports, tables, charts) prefer format=html with self-contained HTML: inline CSS and inline SVG render; scripts are stripped and never run. Expiries up to 1 day are free. ttl=30d and the Pro options cost $1 one-time: the result then includes a payment_url that a human can open in a browser to complete checkout.

endpoint
https://ctxt.io/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 ctxt live?
Yes — it answered the hub's last check (checked 2h ago). It answered 100% of checks over the last 30 days.
Is ctxt free to use?
Yes — the hub reached it with no key and no payment.
What tools does ctxt have?
3 tools: create_context, delete_context, read_context.
Is ctxt 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
99.6%

90 days 99.7%· all time 99.7%

latency
188ms

last good check

priced tools
0

of 3 tools

_ answered our checks, 90 days 383 checks · signed record
  • degraded → live
  • live → degraded· timeout after 20000ms
  • degraded → live
  • unknown → live
_ what it is for
used for
  • share text or html as an expiring link
  • read a shared paste
  • delete a shared link
takes → gives
text, code → web pages, text
tools
1 reads2 changes data
_ 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

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 3 tools
3 never probed 0 of 3 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.

  • create_context changes data unknown never probed

    Share text, markdown, code, or HTML as an auto-expiring ctxt.io link. For visual output (styled reports, tables, charts, diagrams) prefer format=html with self-contained HTML: inline CSS and inline SVG render fully; <script> is stripped server-side and JavaScript never runs, so keep it static. Free expiries: 5m, 30m, 1h (default), 8h, 1d — these return the share URL immediately. ttl=30d and the Pro options (name, password) cost $1 one-time: the link is created in a pending state and the result includes a payment_url a human can open in a browser to complete checkout (platforms enrolled for agentic payments receive an acp block instead and can pay programmatically); until payment the link lives 1 day without Pro features. Anyone with the link can read it. The returned delete_token authorizes deletion via delete_context — keep it private.

    mcp-tool

    {
      "type": "object",
      "required": [
        "content"
      ],
      "properties": {
        "ttl": {
          "enum": [
            "5m",
            "30m",
            "1h",
            "8h",
            "1d",
            "30d"
          ],
          "type": "string",
          "default": "1h",
          "description": "How long the link stays readable. 5m–1d are free; 30d costs $1."
        },
        "lang": {
          "type": "string",
          "description": "With format=code: the language to highlight (e.g. python, javascript, diff). Omit to auto-detect."
        },
        "name": {
          "type": "string",
          "description": "Pro, ttl=30d only: human-readable name appended to the URL as a slug."
        },
        "format": {
          "enum": [
            "text",
            "markdown",
            "code",
            "html"
          ],
          "type": "string",
          "default": "text",
          "description": "How to render the content: text (verbatim), markdown (rendered rich), code (syntax highlighted), or html (sanitized and rendered — best for visual output; inline CSS/SVG work, scripts are stripped)."
        },
        "content": {
          "type": "string",
          "description": "The content to share (max 4MB)."
        },
        "password": {
          "type": "string",
          "description": "Pro, ttl=30d only: password required to read the link. Access control, not encryption — content is plaintext at rest."
        }
      }
    }
    arguments 48 lines
  • delete_context changes data unknown never probed

    Delete a ctxt.io link you created. Requires the delete_token returned by create_context. Immediately removes public access and requests backing-storage deletion. Destructive and not undoable — confirm with the user before calling.

    mcp-tool

    {
      "type": "object",
      "required": [
        "url_or_key",
        "delete_token"
      ],
      "properties": {
        "url_or_key": {
          "type": "string",
          "description": "Full ctxt.io URL, /3/<code> path, or bare code."
        },
        "delete_token": {
          "type": "string",
          "description": "The delete_token from create_context."
        }
      }
    }
    arguments 17 lines
  • read_context reads unknown 9h ago

    Fetch the content of an existing ctxt.io link. Accepts a full ctxt.io URL, a /3/<code> path, or a bare code. Password-protected links need the password argument.

    mcp-tool

    {
      "type": "object",
      "required": [
        "url_or_key"
      ],
      "properties": {
        "format": {
          "enum": [
            "markdown",
            "text",
            "html"
          ],
          "type": "string",
          "default": "markdown",
          "description": "Representation to return."
        },
        "password": {
          "type": "string",
          "description": "Password for protected links."
        },
        "url_or_key": {
          "type": "string",
          "description": "Full ctxt.io URL, /3/<code> path, or bare code."
        }
      }
    }
    arguments 26 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 6d4fea9f97e2a7ec.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/6d4fea9f97e2a7ec/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/6d4fea9f97e2a7ec/badge.svg)](https://brick.blue/agent/6d4fea9f97e2a7ec?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
70%

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.