ai.getvda/integration-agent is an MCP server published by ai.getvda, hosted at drift.getvda.ai. When last checked on 2026-11-22 it was working: it answers and lists its tools. It declares 6 tools, including drift_status, drift_hash, drift_check, drift_diff, drift_probe.
MCP Drift Observatory: has a public MCP server's declared tools changed? Free check, archive, feeds.
303 connections through 4 shared values. Tap any node.
Inferred from the host name and headers: what a server runs on, not who runs it.
Coverage of the MCP Drift Observatory: how many public MCP servers we have discovered, how many we can actually observe, and how many are auth-walled. Reports the denominator, not just the flattering numerator.
No parameters.
{
"name": "drift_status",
"title": "Observatory coverage",
"description": "Coverage of the MCP Drift Observatory: how many public MCP servers we have discovered, how many we can actually observe, and how many are auth-walled. Reports the denominator, not just the flattering numerator.",
"inputSchema": {
"type": "object",
"properties": {}
},
"annotations": {
"title": "Observatory coverage",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}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.
Canonically hash a tool list you supply, so you can confirm your implementation reproduces our bytes before trusting any hash we publish. ensure_ascii=False is the flag people miss.
| Parameter | Type | Description |
|---|---|---|
| tools * | array | MCP tool objects as returned by tools/list |
{
"name": "drift_hash",
"title": "Hash a tool list",
"description": "Canonically hash a tool list you supply, so you can confirm your implementation reproduces our bytes before trusting any hash we publish. ensure_ascii=False is the flag people miss.",
"inputSchema": {
"type": "object",
"required": [
"tools"
],
"properties": {
"tools": {
"type": "array",
"description": "MCP tool objects as returned by tools/list"
}
}
},
"annotations": {
"title": "Hash a tool list",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Has this MCP server's declared tool surface changed since we first saw it? Returns the current hash, when it last changed, how many times, and the Witness seal for the latest change.
| Parameter | Type | Description |
|---|---|---|
| url * | string | the server's MCP endpoint URL |
{
"name": "drift_check",
"title": "Check a server for tool changes",
"description": "Has this MCP server's declared tool surface changed since we first saw it? Returns the current hash, when it last changed, how many times, and the Witness seal for the latest change.",
"inputSchema": {
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"description": "the server's MCP endpoint URL"
}
}
},
"annotations": {
"title": "Check a server for tool changes",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}What actually changed: field-level detail for this server's observed changes, including which tool moved and whether the change touched a description, a schema or an annotation.
| Parameter | Type | Description |
|---|---|---|
| url * | string | the server's MCP endpoint URL |
{
"name": "drift_diff",
"title": "Show what changed",
"description": "What actually changed: field-level detail for this server's observed changes, including which tool moved and whether the change touched a description, a schema or an annotation.",
"inputSchema": {
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"description": "the server's MCP endpoint URL"
}
}
},
"annotations": {
"title": "Show what changed",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Fetch this server right now and compare it to our stored baseline. Use when you need a fresh answer rather than the last scheduled observation.
| Parameter | Type | Description |
|---|---|---|
| url * | string | the server's MCP endpoint URL |
{
"name": "drift_probe",
"title": "Probe a server now",
"description": "Fetch this server right now and compare it to our stored baseline. Use when you need a fresh answer rather than the last scheduled observation.",
"inputSchema": {
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"description": "the server's MCP endpoint URL"
}
}
},
"annotations": {
"title": "Probe a server now",
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}Free, no payment required. Runs this agent's real capability on a fixed canned input and returns the genuine result, an honest assertion grade, and the full trust manifest (signed Agent Card, JWKS, governance/licence chain, safety posture) with a proof link for every claim. Intended for registries, graders and auditors: this is behavioural evidence, not a self-description.
No parameters.
{
"name": "selftest",
"title": "Self-test",
"description": "Free, no payment required. Runs this agent's real capability on a fixed canned input and returns the genuine result, an honest assertion grade, and the full trust manifest (signed Agent Card, JWKS, governance/licence chain, safety posture) with a proof link for every claim. Intended for registries, graders and auditors: this is behavioural evidence, not a self-description.",
"inputSchema": {
"type": "object",
"properties": {}
},
"annotations": {
"title": "Self-test",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Names, descriptions and schemas were written by the server and are shown as data.
Shared addresses on big platforms (Cloudflare, Vercel and the like) put unrelated servers together; those are marked shared_infrastructure. A match is a pivot, not a link between operators.