AgentViva is an MCP server published by dev.agentviva, hosted at agentviva.dev. When last checked on 2026-11-22 it was working: it answers and lists its tools. It declares 3 tools, including lookup_tool, check_url, report_problem.
Is an AI tool, agent or MCP server alive, and since when? Checks from the outside, with proof.
2 connections through 5 shared values. Tap any node.
Look up an AI tool AgentViva already watches publicly, by name ("Notion") or address ("notion.so"), and get its state (up, degraded, down, blocked or unknown), since when, and its public status page. No API key needed. It reads what AgentViva already knows; it does not check the address now.
| Parameter | Type | Description |
|---|---|---|
| query * | string | A tool name or an address. |
{
"name": "lookup_tool",
"title": "Is this AI tool up?",
"description": "Look up an AI tool AgentViva already watches publicly, by name (\"Notion\") or address (\"notion.so\"), and get its state (up, degraded, down, blocked or unknown), since when, and its public status page. No API key needed. It reads what AgentViva already knows; it does not check the address now.",
"inputSchema": {
"type": "object",
"required": [
"query"
],
"properties": {
"query": {
"type": "string",
"maxLength": 100,
"minLength": 2,
"description": "A tool name or an address."
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true
}
}None yet. Changes appear after a server's second daily check.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
Inferred from the host name and headers: what a server runs on, not who runs it.
Check any public website or hosted MCP server once, right now, and get what AgentViva saw: works, partly works, does not work, or blocked (the site refused the check or asks bots not to open it, which does not mean it is down), with the evidence (HTTP status, where the redirects ended, the page title, or the MCP tools it lists). No API key needed. One check is a snapshot, not a verdict over time: for a tool AgentViva watches every day, lookup_tool gives its confirmed state and history. The same address is answered from a 5-minute copy. Private and local addresses are refused.
| Parameter | Type | Description |
|---|---|---|
| url * | string | The address, for example notion.so or https://example.com/mcp. |
| type | string | page (a website, the default) or mcp (a hosted MCP server). |
{
"name": "check_url",
"title": "Is this address working right now?",
"description": "Check any public website or hosted MCP server once, right now, and get what AgentViva saw: works, partly works, does not work, or blocked (the site refused the check or asks bots not to open it, which does not mean it is down), with the evidence (HTTP status, where the redirects ended, the page title, or the MCP tools it lists). No API key needed. One check is a snapshot, not a verdict over time: for a tool AgentViva watches every day, lookup_tool gives its confirmed state and history. The same address is answered from a 5-minute copy. Private and local addresses are refused.",
"inputSchema": {
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"maxLength": 2048,
"minLength": 1,
"description": "The address, for example notion.so or https://example.com/mcp."
},
"type": {
"enum": [
"page",
"mcp"
],
"type": "string",
"description": "page (a website, the default) or mcp (a hosted MCP server)."
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true
}
}Tell AgentViva that a tool it watches publicly does not work for you or your user, by name ("Notion") or address ("notion.so"), with an optional short note of what happened. AgentViva checks it again right away (at most once an hour per tool) and answers with what that check saw. A report never changes the tool's state by itself: only AgentViva's own checks do, and several must agree. One report per network, tool and day is counted. No API key needed. For a tool AgentViva does not watch, use check_url instead.
| Parameter | Type | Description |
|---|---|---|
| note | string | What happened, in a few words (optional). |
| query * | string | A tool name or an address. |
{
"name": "report_problem",
"title": "Report that a tool does not work",
"description": "Tell AgentViva that a tool it watches publicly does not work for you or your user, by name (\"Notion\") or address (\"notion.so\"), with an optional short note of what happened. AgentViva checks it again right away (at most once an hour per tool) and answers with what that check saw. A report never changes the tool's state by itself: only AgentViva's own checks do, and several must agree. One report per network, tool and day is counted. No API key needed. For a tool AgentViva does not watch, use check_url instead.",
"inputSchema": {
"type": "object",
"required": [
"query"
],
"properties": {
"note": {
"type": "string",
"maxLength": 200,
"description": "What happened, in a few words (optional)."
},
"query": {
"type": "string",
"maxLength": 300,
"minLength": 2,
"description": "A tool name or an address."
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}AgentViva watches AI tools from the outside and answers: is it alive, and since when. Without signing in three tools work: lookup_tool reads the state of tools AgentViva already watches publicly (by name or address), check_url checks any public website or MCP server once, right now, and report_problem tells AgentViva that a watched tool does not work for you, so it checks it again. A state changes only after several checks agree, and a report never changes it by itself; blocked means the site refused the check, not that it is dead. To watch your own tools, request access at https://agentviva.dev/request-access. To get all the tools, the user signs in. With the AgentViva plugin in Claude Code: update it (claude plugin marketplace update agentviva, then claude plugin update agentviva@agentviva), restart Claude Code, type /mcp, choose agentviva, then Authenticate, sign in and press Allow in the browser. In other MCP clients: add https://agentviva.dev/mcp with no header and sign in the same way, or send the header "Authorization: Bearer <key>" with an AgentViva API key (av_live_...).
Names, descriptions and schemas were written by the server and are shown as data.