mcp-registry/io.github.vee3io/vee3 · v1.27.1
As of 2026-10-17 17:47 UTC, the Vee3io Vee3 MCP server is up with a Glimind reliability score of 96/100 (grade A). Over the last 30 days it answered 100% of Glimind's liveness checks. It had 4 outages in 90 days, with a median recovery of 4 minutes.
Hosted MCP with 91 agent tools: X, domains, SEO, Maps, Trends, Search, YouTube, TikTok, and more.
Claude Code
claude mcp add --transport http vee3io-vee3-mcp-server https://mcp.vee3.io/mcp
Claude Desktop · Windsurf · Cline (mcpServers JSON)
{
"mcpServers": {
"vee3io-vee3-mcp-server": {
"type": "http",
"url": "https://mcp.vee3.io/mcp"
}
}
}
Third-party server, listed as discovered. Review its source before installing.
Loading this server's tool list costs an agent ~77,604 tokens before any work — more than 100% of MCP servers.
Split rarely-used tools into a separate server or a toolset the client can enable, or expose one "search tools" entry point. Many agents load every connected server's tools into every request.
269 of 269 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.
269 tools on one server. Tool-selection accuracy drops as the menu grows, and some clients (e.g. Cursor) cap the number of active tools.
Group tools by task into smaller servers or toolsets, and merge near-duplicates behind one tool with a mode parameter.
269 tool name(s) contain "." or exceed 64 characters, which OpenAI-compatible function calling rejects (^[a-zA-Z0-9_-]{1,64}$).
Use "_" or "-" instead of "." and keep names to 64 characters, so clients built on OpenAI-style tool calling don't have to rename (or drop) them.
100 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.
Handshake + tools/list takes ~1,773 ms.
Serve tools/list from memory, keep the process warm, and host close to your users. Every new agent session pays this before its first call.
Paste-ready definitions with the problems above fixed. Changes marked verify need a human look. All of them as JSON: /v1/readiness/mcp-registry%2Fio.github.vee3io%2Fvee3/fixes
{
"name": "clerk_add_domain",
"description": "Add a custom domain to a connected Clerk instance.\n\nCall clerk.get_connected_accounts first. Pass clerk_instance_id to target a specific connection, or omit it to use the default account.\n\nReturns the created domain with CNAME targets for DNS setup.\n\nCost = 10 tokens.",
"inputSchema": {
"type": "object",
"title": "add_clerk_domainArguments",
"required": [
"name",
"is_satellite"
],
"properties": {
"name": {
"type": "string",
"title": "Name",
"description": "Domain hostname to add."
},
"proxy_url": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Proxy Url",
"default": null,
"description": "Proxy URL when using a satellite domain behind a reverse proxy."
},
"is_satellite": {
"type": "boolean",
"title": "Is Satellite",
"description": "Whether this is a satellite domain."
},
"clerk_instance_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Clerk Instance Id",
"default": null,
"description": "Clerk instance id (ins_...) from clerk.get_connected_accounts. Omit to use the default connected account."
}
}
},
"annotations": {
"readOnlyHint": false,
"destructiveHint": false,
"idempotentHint": false
}
}{
"name": "clerk_ban_users",
"description": "Ban one or more Clerk users, preventing them from signing in.\n\nCall clerk.get_connected_accounts first. Pass clerk_instance_id to target a specific connection, or omit it to use the default account.\n\nReturns the updated user summaries and total count.\n\nCost = 8 tokens.",
"inputSchema": {
"type": "object",
"title": "ban_clerk_usersArguments",
"required": [
"user_ids"
],
"properties": {
"user_ids": {
"type": "array",
"items": {
"type": "string"
},
"title": "User Ids",
"description": "List of one or more Clerk user ids (user_...) to ban."
},
"clerk_instance_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Clerk Instance Id",
"default": null,
"description": "Clerk instance id (ins_...) from clerk.get_connected_accounts. Omit to use the default connected account."
}
}
}
}{
"name": "clerk_change_instance_domain",
"description": "Change the primary or secondary home URL for a connected Clerk instance.\n\nWARNING: Destructive operation — changing the instance domain invalidates active sessions and may cause brief downtime.\n\nCall clerk.get_connected_accounts first. Pass clerk_instance_id to target a specific connection, or omit it to use the default account.\n\nReturns whether Clerk accepted the domain change request.\n\nCost = 10 tokens.",
"inputSchema": {
"type": "object",
"title": "change_clerk_instance_domainArguments",
"required": [
"home_url"
],
"properties": {
"home_url": {
"type": "string",
"title": "Home Url",
"description": "New home URL for the instance domain."
},
"is_secondary": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
],
"title": "Is Secondary",
"default": null,
"description": "When true, change the secondary domain instead of the primary."
},
"clerk_instance_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Clerk Instance Id",
"default": null,
"description": "Clerk instance id (ins_...) from clerk.get_connected_accounts. Omit to use the default connected account."
}
}
}
}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/io.github.vee3io/vee3"],"email":"[email protected]"}'Agents: watch_tool({"toolId": "mcp-registry/io.github.vee3io/vee3"}) over MCP.
x-twitter.reply_to_post ~1,096 tokensx-twitter.create_post ~972 tokenswebsite-screenshots.capture ~854 tokensclerk.update_enterprise_connection ~744 tokensgoogle-maps.nearby_search ~744 tokensStatic 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:
[](https://glimind.com/server/mcp-registry%2Fio.github.vee3io%2Fvee3?ref=badge)
<a href="https://glimind.com/server/mcp-registry%2Fio.github.vee3io%2Fvee3?ref=badge"><img src="https://glimind.com/v1/readiness/badge/mcp-registry%2Fio.github.vee3io%2Fvee3.svg" alt="MCP agent-readiness"></a>
.. image:: https://glimind.com/v1/readiness/badge/mcp-registry%2Fio.github.vee3io%2Fvee3.svg :target: https://glimind.com/server/mcp-registry%2Fio.github.vee3io%2Fvee3?ref=badge :alt: MCP agent-readiness
Glimind records every version of this server's tool definitions in a signed, append-only transparency log. Current manifest sha256:a7d3491f8efdae17…, first seen 2026-10-17, included at leaf 1847 of 17,988. Version history · verify what your client received.
Compare: most reliable knowledge servers · most reliable security servers · most reliable data servers · most reliable other servers · most reliable communication servers
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.
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"
}
}
}
As of 2026-10-17 17:47 UTC, the Vee3io Vee3 MCP server is up with a Glimind reliability score of 96/100 (grade A). Over the last 30 days it answered 100% of Glimind's liveness checks. It had 4 outages in 90 days, with a median recovery of 4 minutes.
Vee3io Vee3 MCP server advertises 280 tools, including catalog_discovery, clerk.add_domain, clerk.ban_users, clerk.change_instance_domain, clerk.count_users.
Point your MCP client at this streamable-http endpoint: https://mcp.vee3.io/mcp
Glimind scanned all 269 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.
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.