Costory: Your Finops MCP

get_context

Read-only

Retrieve the authorized Costory workspace's commonly used grouping dimensions, recent dashboards, and connected metric integrations. Use when a cost-analysis request needs grouping dimensions or integration details. Each dimension has name (CEL/groupBy field: cos_* native or virtual_* bqName) and label (pretty display name) — use label only in user-facing text; use name for filterCel/groupBy (never the label). To discover CEL field names and dimension values for filterCel/groupBy, use search instead — pass type: ["dimensions"] with an empty query to list all dimensions, or a keyword (e.g. "account", "environment") to narrow results. For billing keys that are not dimensions yet, call list_dimension_candidates; import or normalize them with publish_label_dimensions (operations merge onto existing labels — do not resend the full list; preview dryRun: true, then call once with dryRun: false and confirm: true; about 10 minutes to show in Explorer). When externalMetricIntegrations is non-empty, call list_metrics with includeExternal: true and a specific search term to browse matching live integration metrics. For new virtual-dimension telemetry (split-by-usage-metric) reallocations, use that same includeExternal search and persist an inline externalMetric (do not set datasource). For BigQuery or S3, pick dateColumn / metricColumn from the returned schema (DATE / NUMERIC) and set gapFillingMethod (default FORWARD_FILL). Custom virtual dimensions: use immutable bqName from list/get VDIM tools as groupBy / filterCel (not display name). Poll computeStatus until COMPLETED after publish. EXAMPLE: "What cloud cost data do you have available?" → {}

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": "get_context"
  }
}

Input Schema

Name	Required	Description
`slug`	No	Organization slug. Omit to auto-detect from your account (fails if you belong to multiple orgs).
`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 Do not quote the user or include names, emails, or other personal details.
`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.
`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.

Changed2 schema fields changedNov 14, 2026

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"
+]

First observedAug 19, 2026

TDQS

A3.9/5.0

Behavior4/5

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

Annotations already declare this a safe, read-only, non-open-world call, so the remaining burden is light. The description still adds real context beyond them: the data is limited to the authorized workspace, the returned dimension objects carry both `name` and `label` with a strict rule about which to use where, and it discloses a roughly 10-minute propagation delay for related publish operations.

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

Conciseness2/5

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

Purpose is front-loaded, but the body is a dense run-on that spends most of its length prescribing the invocation of unrelated tools — dryRun/confirm sequences, `gapFillingMethod`, `dateColumn`/`metricColumn` selection, and `computeStatus` polling. Those sentences serve the wider workflow rather than telling an agent how to call `get_context`, so much of the text does not earn its place here.

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?

For a read-only tool with no output schema, the description does explain what comes back (dimensions with name/label, recent dashboards, integration list) and the workspace scoping. It is more than complete for the call itself, with the surplus being off-topic orchestration guidance rather than a gap.

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 100% and all four parameters (slug, context, llm_model, conversation_id) are documented in the schema itself, so the baseline of 3 applies. The description adds nothing about slug auto-detection or the analytics parameters beyond what the schema already states.

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?

The first sentence names a specific verb and enumerates the three resources returned: "grouping dimensions, recent dashboards, and connected metric integrations," scoped to the authorized workspace. It is distinguishable from the vague sibling `get`, though the later flood of downstream workflow text dilutes the focus of the opening statement.

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?

It states an explicit trigger ("Use when a cost-analysis request needs grouping dimensions or integration details") and names concrete alternatives with the conditions that select them: `search` with `type: ["dimensions"]` for field names and values, `list_dimension_candidates` for unmodeled billing keys, and `list_metrics` with `includeExternal: true` when `externalMetricIntegrations` is non-empty.

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?