HubVibe: Pay-per-Call Agent Tools: Web Search, Email Verify, KYC Screening, Stocks, Crypto, News

Detect anomalies in a time series

hubvibe_data_anomalies

Read-onlyIdempotent

Anomaly detection on a time series: score recent periods against history with BigQuery AI.DETECT_ANOMALIES (TimesFM). Give one table and its latest periods are scored against its own history, or a history and a target table. Returns every checked row with bounds, anomaly flag and probability, plus the anomaly count. Input: history_table, target_table, timestamp_col, data_col; optional target_last, threshold, id_cols. $10.00 per call. Returns: history_table, target_table, timestamp_col, data_col, anomaly_prob_threshold, mode, target_periods, columns[], rows[], row_count, anomaly_count, gib_processed.

Input Schema

TableJSON Schema

Name	Required	Description
`id_cols`	No	Optional: one series per value of these columns.
`data_col`	Yes
`language`	No	Optional BCP-47 language tag (en, ja, ko, pt-BR): the human-readable strings of the result (notes, details, reasons) are translated into this language; data, codes, numbers and URLs are untouched. Default: as produced.
`target_last`	No	Same table as history and target: score its latest N timestamps. Default 30.
`max_scan_gib`	No
`target_table`	Yes	project.dataset.table
`history_table`	Yes	project.dataset.table
`timestamp_col`	Yes
`anomaly_prob_threshold`	No	0.5-0.999, default 0.95.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes
`status`	Yes
`worker`	Yes
`price_usd`	Yes
`provenance`	Yes
`receipt_id`	Yes
`attribution`	No
`receipt_url`	Yes
`billing_warning`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed23 schema fields changedOct 1, 2026

removedOutput schema / description

Removed value: -"The 200 body of every paid /work call. `result` is the worker's own output (its schema is per route); everything else is the same on every /work route. A receipt for the job is at `receipt_url`."

removedOutput schema / properties / attribution / description

Removed value: -"Present only when the result's text was machine-translated: the credit to show with it."

removedOutput schema / properties / attribution / items / description
```
Removed value: -"A credit."
```

removedOutput schema / properties / attribution / items / properties

Removed value: -{
-  "text": {
-    "description": "Credit.",
-    "examples": [
-      "Translated by Google"
-    ],
-    "type": "string"
-  },
-  "url": {
-    "description": "Link.",
-    "examples": [
-      "https://translate.google.com"
-    ],
-    "type": "string"
-  }
-}

removedOutput schema / properties / attribution / items / required
```
Removed value: -[
-  "text",
-  "url"
-]
```
removedOutput schema / properties / attribution / items / type
```
Removed value: -"object"
```

removedOutput schema / properties / billing_warning / description

Removed value: -"Present only when the charge was recorded with a caveat."

removedOutput schema / properties / billing_warning / examples
```
Removed value: -[
-  "settlement pending"
-]
```
removedOutput schema / properties / price_usd / description
```
Removed value: -"What this call cost, in USD."
```
removedOutput schema / properties / price_usd / examples
```
Removed value: -[
-  0.02
-]
```

removedOutput schema / properties / provenance / description

Removed value: -"How the result was produced: which providers ran and how long each took."

removedOutput schema / properties / provenance / properties

Removed value: -{
-  "attempts": {
-    "description": "Provider attempts made, including retries and failovers.",
-    "examples": [
-      1
-    ],
-    "type": "integer"
-  },
-  "elapsed_ms": {
-    "description": "Wall-clock milliseconds for the whole job.",
-    "examples": [
-      340
-    ],
-    "type": "integer"
-  },
-  "providers_used": {
-    "description": "Providers that served the job.",
-    "examples": [
-      [
-        "coinbase-advanced-trade-public"
-      ]
-    ],
-    "items": {
-      "description": "Provider name.",
-      "examples": [
-        "coinbase-advanced-trade-public"
-      ],
-      "type": "string"
-    },
-    "type": "array"
-  },
-  "steps": {
-    "description": "Every step the job ran, in order.",
-    "items": {
-      "description": "One step of the job.",
-      "properties": {
-        "ms": {
-          "description": "Milliseconds the step took.",
-          "examples": [
-            312
-          ],
-          "type": "integer"
-        },
-        "ok": {
-          "description": "Whether the step succeeded.",
-          "examples": [
-            true
-          ],
-          "type": "boolean"
-        },
-        "provider": {
-          "description": "Provider that served the step.",
-          "examples": [
-            "coinbase-advanced-trade-public"
-          ],
-          "type": "string"
-        },
-        "reason": {
-          "description": "Failure reason, on a failed step.",
-          "examples": [
-            "provider_timeout"
-          ],
-          "type": "string"
-        },
-        "step": {
-          "description": "Step name inside the worker.",
-          "examples": [
-            "quote"
-          ],
-          "type": "string"
-        }
-      },
-      "required": [
-        "step",
-        "ok",
-        "ms"
-      ],
-      "type": "object"
-    },
-    "type": "array"
-  }
-}

removedOutput schema / properties / provenance / required

Removed value: -[
-  "steps",
-  "providers_used",
-  "attempts",
-  "elapsed_ms"
-]

removedOutput schema / properties / receipt_id / description
```
Removed value: -"Receipt id for this job."
```
removedOutput schema / properties / receipt_id / examples
```
Removed value: -[
-  "rcpt_9f1c2b3a4d5e6f70"
-]
```

removedOutput schema / properties / receipt_url / description

Removed value: -"Where to fetch the machine-readable receipt (free, no payment)."

removedOutput schema / properties / receipt_url / examples

Removed value: -[
-  "/work/receipts/rcpt_9f1c2b3a4d5e6f70"
-]

removedOutput schema / properties / result / properties

Removed value: -{
-  "anomaly_count": {
-    "description": "Rows flagged as anomalies at the threshold.",
-    "examples": [
-      2
-    ],
-    "type": "integer"
-  },
-  "anomaly_prob_threshold": {
-    "description": "Probability threshold used.",
-    "examples": [
-      0.95
-    ],
-    "type": "number"
-  },
-  "columns": {
-    "description": "AI.DETECT_ANOMALIES output columns.",
-    "examples": [
-      [
-        "state_name",
-        "date",
-        "confirmed_cases",
-        "is_anomaly",
-        "lower_bound",
-        "upper_bound",
-        "anomaly_probability"
-      ]
-    ],
-    "items": {
-      "description": "AI.DETECT_ANOMALIES output column.",
-      "examples": [
-        "is_anomaly"
-      ],
-      "type": "string"
-    },
-    "type": "array"
-  },
-  "data_col": {
-    "description": "Value column.",
-    "examples": [
-      "confirmed_cases"
-    ],
-    "type": "string"
-  },
-  "gib_processed": {
-    "description": "Gibibytes BigQuery scanned; the metered cost basis.",
-    "examples": [
-      0.012
-    ],
-    "type": "number"
-  },
-  "history_table": {
-    "description": "Table the forecast is fitted on.",
-    "examples": [
-      "bigquery-public-data.covid19_nyt.us_states"
-    ],
-    "type": "string"
-  },
-  "mode": {
-    "description": "split_by_time: one table, its latest periods scored against the rest; two_tables: target scored against history.",
-    "enum": [
-      "split_by_time",
-      "two_tables"
-    ],
-    "examples": [
-      "split_by_time"
-    ],
-    "type": "string"
-  },
-  "row_count": {
-    "description": "Rows returned.",
-    "examples": [
-      10
-    ],
-    "type": "integer"
-  },
-  "rows": {
-    "description": "Checked rows with their anomaly flag.",
-    "examples": [
-      [
-        {
-          "anomaly_probability": "0.12",
-          "confirmed_cases": "8631000",
-          "date": "2023-03-20",
-          "is_anomaly": "false",
-          "state_name": "Texas"
-        }
-      ]
-    ],
-    "items": {
-      "additionalProperties": true,
-      "description": "One checked point.",
-      "examples": [
-        {
-          "anomaly_probability": "0.12",
-          "confirmed_cases": "8631000",
-          "date": "2023-03-20",
-          "is_anomaly": "false",
-          "state_name": "Texas"
-        }
-      ],
-      "properties": {},
-      "required": [],
-      "type": "object"
-    },
-    "type": "array"
-  },
-  "target_periods": {
-    "description": "Latest timestamps scored in split_by_time mode; null for two tables.",
-    "examples": [
-      30
-    ],
-    "type": [
-      "integer",
-      "null"
-    ]
-  },
-  "target_table": {
-    "description": "Table checked for anomalies.",
-    "examples": [
-      "bigquery-public-data.covid19_nyt.us_states"
-    ],
-    "type": "string"
-  },
-  "timestamp_col": {
-    "description": "Timestamp column.",
-    "examples": [
-      "date"
-    ],
-    "type": "string"
-  }
-}

removedOutput schema / properties / result / required

Removed value: -[
-  "history_table",
-  "target_table",
-  "timestamp_col",
-  "data_col",
-  "anomaly_prob_threshold",
-  "mode",
-  "target_periods",
-  "columns",
-  "rows",
-  "row_count",
-  "anomaly_count",
-  "gib_processed"
-]

removedOutput schema / properties / status / description

Removed value: -"Present only on a delivered result."

removedOutput schema / properties / worker / description

Removed value: -"Catalog name of the worker that ran."

removedOutput schema / properties / worker / examples
```
Removed value: -[
-  "market.quote"
-]
```

removedOutput schema / title

Removed value: -"data.anomalies response"

Changed1 schema field changedSep 28, 2026

addedOutput schema / properties / attribution

Added value: +{
+  "description": "Present only when the result's text was machine-translated: the credit to show with it.",
+  "items": {
+    "description": "A credit.",
+    "properties": {
+      "text": {
+        "description": "Credit.",
+        "examples": [
+          "Translated by Google"
+        ],
+        "type": "string"
+      },
+      "url": {
+        "description": "Link.",
+        "examples": [
+          "https://translate.google.com"
+        ],
+        "type": "string"
+      }
+    },
+    "required": [
+      "text",
+      "url"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}

Changed5 schema fields changedSep 28, 2026

addedInput schema / properties / target_last

Added value: +{
+  "description": "Same table as history and target: score its latest N timestamps. Default 30.",
+  "maximum": 366,
+  "minimum": 1,
+  "type": "integer"
+}

addedOutput schema / properties / result / properties / anomaly_count

Added value: +{
+  "description": "Rows flagged as anomalies at the threshold.",
+  "examples": [
+    2
+  ],
+  "type": "integer"
+}

addedOutput schema / properties / result / properties / mode

Added value: +{
+  "description": "split_by_time: one table, its latest periods scored against the rest; two_tables: target scored against history.",
+  "enum": [
+    "split_by_time",
+    "two_tables"
+  ],
+  "examples": [
+    "split_by_time"
+  ],
+  "type": "string"
+}

addedOutput schema / properties / result / properties / target_periods

Added value: +{
+  "description": "Latest timestamps scored in split_by_time mode; null for two tables.",
+  "examples": [
+    30
+  ],
+  "type": [
+    "integer",
+    "null"
+  ]
+}

changedOutput schema / properties / result / required

Previous value: -[
-  "history_table",
-  "target_table",
-  "timestamp_col",
-  "data_col",
-  "anomaly_prob_threshold",
-  "columns",
-  "rows",
-  "row_count",
-  "gib_processed"
-]New value: +[
+  "history_table",
+  "target_table",
+  "timestamp_col",
+  "data_col",
+  "anomaly_prob_threshold",
+  "mode",
+  "target_periods",
+  "columns",
+  "rows",
+  "row_count",
+  "anomaly_count",
+  "gib_processed"
+]

Changed1 schema field changedSep 27, 2026

addedInput schema / properties / language

Added value: +{
+  "description": "Optional BCP-47 language tag (en, ja, ko, pt-BR): the human-readable strings of the result (notes, details, reasons) are translated into this language; data, codes, numbers and URLs are untouched. Default: as produced.",
+  "maxLength": 35,
+  "pattern": "^[A-Za-z]{2,3}(-[A-Za-z0-9]{2,8})*$",
+  "type": "string"
+}

Changed1 schema field changedSep 27, 2026

changedOutput schema / description

Previous value: -"The 200 body of every paid /work call. `result` is the worker's own output (its schema is per route); everything else is the same on all 38 routes. A receipt for the job is at `receipt_url`."New value: +"The 200 body of every paid /work call. `result` is the worker's own output (its schema is per route); everything else is the same on every /work route. A receipt for the job is at `receipt_url`."

AddedSep 24, 2026

TDQS

A3.9/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover safety (readOnly, idempotent, non-destructive, openWorld). The description adds genuinely useful non-annotation context: per-call pricing ($10.00), the row-level output shape (bounds, flag, probability) and the anomaly count, including a gib_processed cost signal. It omits auth/permission requirements that a BigQuery-backed tool likely needs.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core purpose and mechanism, then modes, then I/O. It is dense and mostly earns its space, but the trailing 'Returns: ...' inventory duplicates the output schema field-by-field and is largely redundant.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, the return-value restatement is unnecessary; the description's real value is the mode semantics and the cost signal. Given a 9-parameter tool with 67% schema coverage, it covers the call pattern adequately but leaves max_scan_gib and the required-vs-optional boundary partly to the schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 67%, so the schema already documents several parameters (target_last, anomaly_prob_threshold, language, id_cols). The description largely restates parameter names and the two mode-setting parameters, adding modest value such as the single-table-vs-history+target semantics. Two parameters (max_scan_gib, data_col) remain undocumented in either place.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('anomaly detection on a time series') and names the underlying mechanism (BigQuery AI.DETECT_ANOMALIES / TimesFM), which is unusually concrete. It does not differentiate itself from the closest sibling, hubvibe_data_forecast, so an agent must infer that distinction from the name alone.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explains the two operating modes clearly: one table whose latest periods are scored against its own history (via target_last), or a separate history and target table. This tells the agent how to configure a call, but gives no explicit when-not or alternative-tool guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All HubVibe: Pay-per-Call Agent Tools: Web Search, Email Verify, KYC Screening, Stocks, Crypto, News tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.