ctxt.io MCP server
Featured official server
3 tools · Last check that passed 4 Nov 2026, 12:15 UTC
ctxt.io's own remote MCP server lets an agent share text, markdown, code or HTML as auto-expiring links on ctxt.io, read existing links and delete the links it created, with no account. Once a day, Stackduke connects to it the way any MCP client would, with no account and no sign-in, and lists its tools. It never runs them.
All 3 tools
| Tool | Counted as |
|---|---|
delete_context | Deletes |
create_context | Sends |
read_context | Said to only read |
The tools the server listed at the last check that passed, at its default address and settings, with no sign-in; an account that signs in, or other settings, may see other tools. What a tool is counted as doing is Stackduke's cautious reading of the server's labels, the tool's name and its description: where they disagree it takes whichever says the tool can do most, so it overcounts on purpose. It does not say the server is safe, and it does not list what a tool cannot do. Descriptions are not shown, because they are written for models and may try to steer them.
Recent checks
21 of the last 21 checks passed
A check passes when the server lists its tools. Checked at https://ctxt.io/mcp.
Recent changes
No change seen across the last 21 checks that passed.
From the scan of 4 Nov 2026, 12:43 UTC. "Changed" and "Can do more" count changes from the last 30 days; older ones stay listed here. A change made and undone between two checks is not seen. Every check is in the scanner's public data.
Know when ctxt.io's tools change.
One email when ctxt.io's official MCP server adds, removes or changes tools, with what changed. Nothing else.
What to watch for
- create_context publishes what the agent sends, up to 4MB, as a link anyone with the URL can read until it expires. ctxt.io says content is stored in plain form, and that password protection is an access gate, not encryption. ctxt.io's MCP documentation
- ctxt.io describes the server as a way to share diffs, logs, snippets and docs, and it needs no account, so an agent connected to it can publish what it has read. ctxt.io's MCP documentation
- A 30-day link costs $1. The result carries a payment URL, and ctxt.io says agent platforms enrolled with it can complete the purchase without a browser. ctxt.io's MCP documentation
- Pastes written by other people come back to the agent as text, and text an agent reads can carry instructions for it. OWASP, prompt injection
How to limit it
With ctxt.io's own settings, as its documentation describes them. Stackduke has not tested them.
- Keep a person approving each create_context call, as OWASP advises for high-risk actions. OWASP, prompt injection
- We recommend the shortest expiry that works. ctxt.io's free expiries run from 5 minutes to 1 day. ctxt.io's MCP documentation
- Don't reuse a password that matters, as ctxt.io advises, since passwords and delete tokens pass through the agent's transcript. ctxt.io's MCP documentation
What Stackduke is designed to do
Stackduke is designed to sit between your agents and their MCP servers: to check each tool call against your rules before it runs, hold the risky ones for a person to approve, and keep a record of what was decided.
It does not yet forward or block tool calls for customers. Today it reads what this server offers and publishes what changes.