Is the 21st MCP server down?

mcp-registry/dev.21st/mcp · v0.1.0

up · requires sign-in
Last checked 2026-10-21 20:01 UTC · handshake 68ms

As of 2026-10-21 20:01 UTC, the 21st MCP server is up (it requires sign-in) with a Glimind reliability score of 83/100 (grade B). Over the last 30 days it answered 100% of Glimind's liveness checks.

uptime (30d checks)
100%
checks observed
93
outages (90d)
0
tools
21

Find UI components and themes, retrieve code, and generate with hosted 21st AI when enabled.

Install 21st MCP server

Add to Cursor Add to VS Code

Claude Code

claude mcp add --transport http 21st-mcp-server https://21st.dev/api/mcp

Claude Desktop · Windsurf · Cline (mcpServers JSON)

{
  "mcpServers": {
    "21st-mcp-server": {
      "type": "http",
      "url": "https://21st.dev/api/mcp"
    }
  }
}

Third-party server, listed as discovered. Review its source before installing.

Agent-readiness: C (79/100)

C (79/100): 0 error(s), 3 warning(s) across 21 tool(s); ~3,398 tokens of tool definitions.
Scores higher than 31% of 15,459 MCP servers Glimind has audited.
Its tool list costs an agent ~3,398 tokens per session — more than 55% of servers.
77 → 79 since 2026-10-17
no tool-poisoning patterns
Schemas100
Descriptions87
Safety hints5
Token cost100
Client compatibility70
Protocol100
Reliability100
Stability100

What to fix (5)

21 of 21 tool(s) carry no readOnlyHint/destructiveHint annotations.

Annotate read-only tools with {"readOnlyHint": true}. Agents and gateways can then run them without a confirmation prompt, and route around destructive ones. How to fix →

Tools: add_to_list, bookmark, create_bookmark_list, delete_component, delete_template and 16 more

4 tool(s) look like they change state (create/send/delete/pay…) but declare no destructiveHint.

Set annotations {"readOnlyHint": false, "destructiveHint": true|false, "idempotentHint": …}. Clients use these to ask the user before a side effect and to auto-approve safe reads. How to fix →

Tools: bookmark, delete_component, delete_template, delete_theme

2 parameter(s) across 1 tool(s) have no description.

Add a "description" to each parameter with its format and an example ("ISO 8601 date, e.g. 2026-10-17"). This is the commonest cause of wrong arguments on the first call. How to fix →

Tools: edit_template

No tool declares an outputSchema.

Declare outputSchema and return structuredContent (MCP 2025-06-18+). Agents can then parse results without guessing, and chain tools reliably. How to fix →

Requires authentication (Bearer); tool definitions could not be read anonymously.

If discovery should be public, allow initialize + tools/list without credentials and gate only tools/call. Directories and routers can then list your tools.

Auto-fix: 17 corrected tool definitions

Paste-ready definitions with the problems above fixed. Changes marked verify need a human look. 1 tool(s) still need parameter descriptions written by someone who knows the API. All of them as JSON: /v1/readiness/mcp-registry%2Fdev.21st%2Fmcp/fixes

add_to_list 1 change
{
  "name": "add_to_list",
  "description": "Add (or with remove:true, remove) a component/theme/template to one of the caller's bookmark lists. Idempotent; adding also ensures the item is bookmarked. Use the list id from list_bookmark_lists and the item id+type from a search result.",
  "inputSchema": {
    "type": "object",
    "required": [
      "listId",
      "type",
      "id"
    ],
    "properties": {
      "id": {
        "type": [
          "number",
          "string"
        ],
        "description": "The item id (component demo id / theme uuid / template id)."
      },
      "type": {
        "enum": [
          "component",
          "theme",
          "template"
        ],
        "type": "string",
        "description": "What kind of item the id refers to."
      },
      "listId": {
        "type": "string",
        "description": "The bookmark list id (uuid)."
      },
      "remove": {
        "type": "boolean",
        "description": "Set true to remove the item from the list."
      }
    }
  },
  "annotations": {
    "readOnlyHint": false,
    "destructiveHint": true,
    "idempotentHint": true
  },
  "title": "Add / remove an item in a bookmark list"
}
bookmark 1 change
{
  "name": "bookmark",
  "description": "Add (or with remove:true, delete) a bookmark - the 'heart'/save - for a component, theme, or template on the signed-in account. Idempotent. Use the id + type from a search or list result.",
  "inputSchema": {
    "type": "object",
    "required": [
      "type",
      "id"
    ],
    "properties": {
      "id": {
        "type": [
          "number",
          "string"
        ],
        "description": "The item id (component demo id / theme uuid / template id)."
      },
      "type": {
        "enum": [
          "component",
          "theme",
          "template"
        ],
        "type": "string",
        "description": "What kind of item the id refers to."
      },
      "remove": {
        "type": "boolean",
        "description": "Set true to remove the bookmark instead of adding it."
      }
    }
  },
  "annotations": {
    "readOnlyHint": false,
    "destructiveHint": false,
    "idempotentHint": false
  },
  "title": "Bookmark / unbookmark a 21st item"
}
create_bookmark_list 1 change
{
  "name": "create_bookmark_list",
  "description": "Create a new personal named bookmark list on the signed-in account.",
  "inputSchema": {
    "type": "object",
    "required": [
      "name"
    ],
    "properties": {
      "name": {
        "type": "string",
        "description": "The list name."
      }
    }
  },
  "annotations": {
    "readOnlyHint": false,
    "destructiveHint": false,
    "idempotentHint": false
  },
  "title": "Create a bookmark list"
}

Get alerted

Get an email or webhook when this server's readiness drops by 10+ points, tool-poisoning text appears, or a tool breaks:

curl -X POST https://glimind.com/v1/subscriptions -H 'content-type: application/json' -d '{"tools":["mcp-registry/dev.21st/mcp"],"email":"[email protected]"}'

Agents: watch_tool({"toolId": "mcp-registry/dev.21st/mcp"}) over MCP.

Passed

Largest tool definitions

Static checks of the advertised tools/list (schema, descriptions, annotations, tool-poisoning patterns, names, size) plus observed protocol, uptime, latency and contract changes. Read-only: no tool is ever called. Weights: schema 15, docs 20, safety 15, efficiency 15, compatibility 15, protocol 5, reliability 10, stability 5. Token counts are estimates (~3.6 characters per token).

Operator? Fix these, then re-check live. Embed the readiness badge:

Markdown
[![MCP agent-readiness](https://glimind.com/v1/readiness/badge/mcp-registry%2Fdev.21st%2Fmcp.svg)](https://glimind.com/server/mcp-registry%2Fdev.21st%2Fmcp?ref=badge)
HTML
<a href="https://glimind.com/server/mcp-registry%2Fdev.21st%2Fmcp?ref=badge"><img src="https://glimind.com/v1/readiness/badge/mcp-registry%2Fdev.21st%2Fmcp.svg" alt="MCP agent-readiness"></a>
reStructuredText
.. image:: https://glimind.com/v1/readiness/badge/mcp-registry%2Fdev.21st%2Fmcp.svg
   :target: https://glimind.com/server/mcp-registry%2Fdev.21st%2Fmcp?ref=badge
   :alt: MCP agent-readiness

Tool-definition log

Glimind records every version of this server's tool definitions in a signed, append-only transparency log. Current manifest sha256:ab592c78a684df8d…, first seen 2026-10-17, included at leaf 3353 of 41,379. Version history · verify what your client received.

Tools (21)

Compare: most reliable productivity servers · most reliable other servers · most reliable code servers · most reliable web servers · most reliable data servers

Know before your agent calls it

Glimind tells agents whether a server is up right now and how to call it, then fails over to a live alternative when it isn't.

Add Glimind — free, no signup:

Add to Cursor Add to VS Code

Claude Code

claude mcp add --transport http glimind https://glimind.com/mcp

Claude Desktop · Windsurf · Cline (mcpServers JSON)

{
  "mcpServers": {
    "glimind": {
      "type": "http",
      "url": "https://glimind.com/mcp"
    }
  }
}

FAQ

Is the 21st MCP server down right now?

As of 2026-10-21 20:01 UTC, the 21st MCP server is up (it requires sign-in) with a Glimind reliability score of 83/100 (grade B). Over the last 30 days it answered 100% of Glimind's liveness checks.

How many tools does 21st MCP server provide?

21st MCP server advertises 21 tools, including add_to_list, bookmark, create_bookmark_list, delete_component, delete_template.

How do I install 21st MCP server?

Point your MCP client at this streamable-http endpoint: https://21st.dev/api/mcp

Is the 21st MCP server safe to connect to an AI agent?

Glimind scanned all 21 tool definitions for tool-poisoning patterns — hidden or invisible characters, instructions that override the model, concealment from the user, requests to read credential or MCP config files, conversation exfiltration and cross-tool shadowing — and found none. This checks what the server tells the model, not what its code does; review the source before granting access to sensitive data.

Operator of 21st MCP server?

Status page: 90-day uptime, every outage and how long it lasted.

Claim this listing to get the Verified operator marker, a remediation checklist and owner analytics, or embed the live badge from any of the tool pages above. Maintainers: alerts, deploy attestation and monthly reports.

Status is an automated estimate from Glimind's liveness checks (handshake and tool listing only; no tool is ever called) and may lag or differ from your network. Glimind is not affiliated with this server or its operator. Operator? Request a correction or opt out at https://glimind.com/opt-out.

Feedback
Help us improve