Costory: Your Finops MCP

suggest_groupby

Read-only

Suggest dimensions for grouping costs, ranked by their contribution, based on an optional filterCel (CEL). Call this when the user asks "what should I look at?" or when you need columns for query or find_cost_change_factors. Use datePreset for preset ranges and from/to for custom ranges. Omit compare for current-window ranking. Pass compare ({} auto-derives, or { from, to }) when the user asks what changed — then pass 2–4 of the returned column names (max 8; { column, contains } for token columns, dropping metrics) into find_cost_change_factors. Returns { column } or { column, contains } plus metrics; do not invent columns. filterCel omitted or "" is unfiltered (not AWS-only). filterCel supports == null for unlabelled dimension values (e.g. cos_environment == null). EXAMPLES: • "What should I split last month's EC2 cost by?" → { datePreset: "LAST_MONTH", filterCel: "cos_service_name in ["AmazonEC2"]" } • "Costs of EC2 spiked last month, what should I investigate?" → { datePreset: "LAST_MONTH", compare: {}, filterCel: "cos_service_name in ["AmazonEC2"]" }

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "context": "<context>"
    },
    "name": "suggest_groupby"
  }
}

Input Schema

Name	Required	Description
`to`	No	Current period end (YYYY-MM-DD), inclusive. Omit when using datePreset.
`from`	No	Current period start (YYYY-MM-DD). Omit when using datePreset.
`slug`	No	Organization slug. Omit to auto-detect from your account (fails if you belong to multiple orgs).
`compare`	No	Optional reference (previous) period. Omit for current-window ranking. `{}` auto-derives from the current window (same helper as query). `{ from, to }` pins it. Pass this when the user asks what changed, before find_cost_change_factors.
`context`	Yes	A few words on why you are calling this tool, for the server developer's analytics. Describe people and things by role, such as "a customer". Do not quote the user or include names, emails, or other personal details.
`filterCel`	No	Optional CEL scope. Omit or "" for unfiltered (Billy where_clause TRUE). That is not an AWS-only filter even though columns_where_clause falls back to ["cos_provider"].
`llm_model`	No	The model identifier you are running as, for example "claude-opus-4-8" or "gpt-5.2". Pass "unknown" if you are not certain. Recorded for the server developer's analytics.
`datePreset`	No
`conversation_id`	No	The conversation_id this server returned earlier in this conversation, unchanged, including after later user messages. Omit it if you have none. Recorded for the server developer's analytics.

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedNov 14, 2026

changedInput schema / properties / compare / description

Previous value: -"Optional reference (previous) period. Omit for current-window ranking. `{}` auto-derives from the current window (same helper as query). `{ from, to }` pins it. Prefer passing this when the user asks what changed, before find_cost_change_factors."New value: +"Optional reference (previous) period. Omit for current-window ranking. `{}` auto-derives from the current window (same helper as query). `{ from, to }` pins it. Pass this when the user asks what changed, before find_cost_change_factors."

changedInput schema / properties / context / description

Previous value: -"Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as \"a user\", \"the customer\", or \"an account\". Example: \"Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution.\""New value: +"A few words on why you are calling this tool, for the server developer's analytics. Describe people and things by role, such as \"a customer\". Do not quote the user or include names, emails, or other personal details."

changedInput schema / required

Previous value: -[
-  "context",
-  "llm_model"
-]New value: +[
+  "context"
+]

Changed4 schema fields changedNov 12, 2026

addedInput schema / properties / context

Added value: +{
+  "description": "Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as \"a user\", \"the customer\", or \"an account\". Example: \"Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution.\"",
+  "type": "string"
+}

addedInput schema / properties / conversation_id

Added value: +{
+  "description": "The conversation_id this server returned earlier in this conversation, unchanged, including after later user messages. Omit it if you have none. Recorded for the server developer's analytics.",
+  "type": "string"
+}

addedInput schema / properties / llm_model

Added value: +{
+  "description": "The model identifier you are running as, for example \"claude-opus-4-8\" or \"gpt-5.2\". Pass \"unknown\" if you are not certain. Recorded for the server developer's analytics.",
+  "type": "string"
+}

addedInput schema / required

Added value: +[
+  "context",
+  "llm_model"
+]

Changed2 schema fields changedNov 5, 2026
- removedInput schema / properties / filterCel / anyOf
```
Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]
```
- addedInput schema / properties / filterCel / type
```
Added value: +[
+  "string",
+  "null"
+]
```

Changed1 schema field changedSep 23, 2026

changedInput schema / properties / datePreset / enum

Previous value: -[
-  "TRAILING_90_DAYS",
-  "TRAILING_30_DAYS",
-  "TRAILING_45_DAYS",
-  "TRAILING_7_DAYS",
-  "TRAILING_3_DAYS",
-  "TRAILING_14_WEEKS",
-  "MTD",
-  "QTD",
-  "YTD",
-  "CURRENT_MONTH",
-  "CURRENT_QUARTER",
-  "CURRENT_YEAR",
-  "LAST_WEEK",
-  "LAST_MONTH",
-  "LAST_6_MONTHS",
-  "LAST_12_MONTHS",
-  "LAST_4_YEARS",
-  "LAST_3_MONTHS",
-  "LAST_INVOICE_MONTH"
-]New value: +[
+  "TRAILING_90_DAYS",
+  "TRAILING_30_DAYS",
+  "TRAILING_45_DAYS",
+  "TRAILING_7_DAYS",
+  "TRAILING_3_DAYS",
+  "TRAILING_1_DAYS",
+  "TRAILING_14_WEEKS",
+  "MTD",
+  "QTD",
+  "YTD",
+  "CURRENT_MONTH",
+  "CURRENT_QUARTER",
+  "CURRENT_YEAR",
+  "LAST_WEEK",
+  "LAST_MONTH",
+  "LAST_6_MONTHS",
+  "LAST_12_MONTHS",
+  "LAST_4_YEARS",
+  "LAST_3_MONTHS",
+  "LAST_INVOICE_MONTH"
+]

Changed1 schema field changedSep 8, 2026

changedInput schema / properties / datePreset / enum

Previous value: -[
-  "TRAILING_90_DAYS",
-  "TRAILING_30_DAYS",
-  "TRAILING_45_DAYS",
-  "TRAILING_7_DAYS",
-  "TRAILING_3_DAYS",
-  "TRAILING_14_WEEKS",
-  "MTD",
-  "QTD",
-  "YTD",
-  "LAST_WEEK",
-  "LAST_MONTH",
-  "LAST_6_MONTHS",
-  "LAST_12_MONTHS",
-  "LAST_4_YEARS",
-  "LAST_3_MONTHS",
-  "LAST_INVOICE_MONTH"
-]New value: +[
+  "TRAILING_90_DAYS",
+  "TRAILING_30_DAYS",
+  "TRAILING_45_DAYS",
+  "TRAILING_7_DAYS",
+  "TRAILING_3_DAYS",
+  "TRAILING_14_WEEKS",
+  "MTD",
+  "QTD",
+  "YTD",
+  "CURRENT_MONTH",
+  "CURRENT_QUARTER",
+  "CURRENT_YEAR",
+  "LAST_WEEK",
+  "LAST_MONTH",
+  "LAST_6_MONTHS",
+  "LAST_12_MONTHS",
+  "LAST_4_YEARS",
+  "LAST_3_MONTHS",
+  "LAST_INVOICE_MONTH"
+]

Changed10 schema fields changedAug 27, 2026

addedInput schema / properties / compare

Added value: +{
+  "additionalProperties": false,
+  "description": "Optional reference (previous) period. Omit for current-window ranking. `{}` auto-derives from the current window (same helper as query). `{ from, to }` pins it. Prefer passing this when the user asks what changed, before find_cost_change_factors.",
+  "properties": {
+    "from": {
+      "format": "date",
+      "pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))$",
+      "type": "string"
+    },
+    "to": {
+      "format": "date",
+      "pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))$",
+      "type": "string"
+    }
+  },
+  "type": "object"
+}

addedInput schema / properties / datePreset

Added value: +{
+  "enum": [
+    "TRAILING_90_DAYS",
+    "TRAILING_30_DAYS",
+    "TRAILING_45_DAYS",
+    "TRAILING_7_DAYS",
+    "TRAILING_3_DAYS",
+    "TRAILING_14_WEEKS",
+    "MTD",
+    "QTD",
+    "YTD",
+    "LAST_WEEK",
+    "LAST_MONTH",
+    "LAST_6_MONTHS",
+    "LAST_12_MONTHS",
+    "LAST_4_YEARS",
+    "LAST_3_MONTHS",
+    "LAST_INVOICE_MONTH"
+  ],
+  "type": "string"
+}

changedInput schema / properties / filterCel / description

Previous value: -"Optional CEL filter to scope the suggestion (same as query)."New value: +"Optional CEL scope. Omit or \"\" for unfiltered (Billy where_clause TRUE). That is not an AWS-only filter even though columns_where_clause falls back to [\"cos_provider\"]."

changedInput schema / properties / from / description

Previous value: -"Start date (YYYY-MM-DD)"New value: +"Current period start (YYYY-MM-DD). Omit when using datePreset."

addedInput schema / properties / from / format
```
Added value: +"date"
```

addedInput schema / properties / from / pattern

Added value: +"^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))$"

changedInput schema / properties / to / description

Previous value: -"End date (YYYY-MM-DD)"New value: +"Current period end (YYYY-MM-DD), inclusive. Omit when using datePreset."

addedInput schema / properties / to / format
```
Added value: +"date"
```

addedInput schema / properties / to / pattern

Added value: +"^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))$"

removedInput schema / required
```
Removed value: -[
-  "from",
-  "to"
-]
```

First observedAug 19, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already declare readOnlyHint/openWorldHint/destructiveHint, so the safety profile is covered; the description adds real value beyond that by stating the return shape ('{ column } or { column, contains } plus metrics'), the anti-hallucination constraint ('do not invent columns'), and the important caveat that an empty filterCel is unfiltered rather than AWS-scoped. It stops short of describing ranking tie-breaking, result count limits, or cost of the call.

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 purpose, then usage triggers, then chaining rules, then examples — a sensible ordering. It is dense and slightly repetitive (the unfiltered/AWS-only caveat appears in both the description and the filterCel schema field), but every sentence is task-relevant rather than filler.

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

Completeness5/5

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

With 9 parameters, a nested compare object, and no output schema, the definition still covers everything needed to call correctly: trigger conditions, the two comparison modes, return shape, and how to hand results to find_cost_change_factors. The analytics-only params (context, llm_model, conversation_id) are adequately explained in the schema itself.

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 89%, so the schema already documents from/to, slug, compare, filterCel, and datePreset. The description's parameter guidance (datePreset vs from/to, `{}` vs `{ from, to }`, `== null` for unlabelled values) largely restates what the schema descriptions already say, adding little new meaning; the one genuinely new element — the 2–4 column-name cap for the follow-up call — concerns output consumption rather than input semantics.

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

Purpose5/5

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

The description opens with a specific verb and resource — 'Suggest dimensions for grouping costs, ranked by their contribution' — and immediately distinguishes itself from the sibling tools it feeds into (query, find_cost_change_factors). An agent can tell what this produces and how it differs from a raw query without opening the schema.

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

Usage Guidelines5/5

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

Explicit trigger conditions ('when the user asks "what should I look at?"'), explicit mode selection (omit compare for current-window ranking, pass compare when the user asks what changed), and explicit downstream chaining ('pass 2–4 of the returned column names... into find_cost_change_factors'). Both example invocations map to the two distinct usage modes.

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

All Costory: Your Finops MCP 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.

Resources

Need Help?