Skip to main content
Glama
Sign In

Costory: Your Finops MCP

by io.costory.app-api
OverviewDiscussionsAdmin

get_dashboard_widget_image

Render a saved Costory dashboard widget as a PNG using its saved query and dashboard filters. Use when the user requests an image of that widget. Creates a new cloud-storage image and returns its URL. Use when the user wants to see a visual snapshot or embed an image in a chat reply. Applies the same dashboard conditionsCel merge as get_dashboard_widget_data. Returns imageUrl (GCS PNG). By default also returns the PNG bytes as a base64 image block (set includeBinaryImage: false to skip binary if the payload is too large). No separate share URL — the widget already lives on the dashboard; link to the dashboard if the user wants the live chart. Does NOT work for text or table-only widgets (returns UNSUPPORTED_WIDGET). For an ad-hoc explorer chart (not a saved widget), use query with returnGraphImage: "link" or "base64" instead. EXAMPLE: "Share my EC2 cost widget as an image" (after get returned widgetId "wid_123") → { dashboardId: "clx9abc", widgetId: "wid_123" }

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": {
      "dashboardId": "<dashboardId>",
      "widgetId": "<widgetId>",
      "context": "<context>"
    },
    "name": "get_dashboard_widget_image"
  }
}

Input Schema

NameRequiredDescriptionDefault
slugNoOrganization slug. Omit to auto-detect from your account (fails if you belong to multiple orgs).
contextYesA 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 Do not quote the user or include names, emails, or other personal details.
widgetIdYesWidget id (from get).
llm_modelNoThe 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.
dashboardIdYesDashboardV2 id.
conversation_idNoThe 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.
includeBinaryImageNoIf true (default), the response includes a base64-encoded PNG image block in addition to the share/image URLs. Set to false to receive URLs only (smaller payload for clients that don't display inline images).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • 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: -[
-  "dashboardId",
-  "widgetId",
-  "context",
-  "llm_model"
-]New value: +[
+  "dashboardId",
+  "widgetId",
+  "context"
+]
  2. Changed4 schema fields changed
    • 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"
+}
    • changedInput schema / required
      Previous value: -[
-  "dashboardId",
-  "widgetId"
-]New value: +[
+  "dashboardId",
+  "widgetId",
+  "context",
+  "llm_model"
+]
  3. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations mark this as a non-destructive but non-read-only, open-world operation, and the description explains exactly why: it 'Creates a new cloud-storage image and returns its URL.' It goes further than the annotations by disclosing the default base64 payload behavior and the opt-out flag, the UNSUPPORTED_WIDGET failure mode, the absence of a separate share URL, and that it inherits the same conditionsCel merge as get_dashboard_widget_data. Nothing here contradicts the readOnlyHint=false / openWorldHint=true annotations.

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?

The core behavior and the alternatives are front-loaded in the first three sentences, which is the right ordering. It loses a point for mild redundancy: two separate 'Use when...' sentences restate the same visual-snapshot intent, and the sentence about not having a share URL is a bit of a tangent, though it does preempt a reasonable agent question.

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?

For a tool with seven parameters, no output schema, and real side effects, the description covers the return values (imageUrl plus optional base64 block), the failure case (UNSUPPORTED_WIDGET), what is explicitly not provided (share URL), and how to redirect the user for a live chart or an ad-hoc chart. An agent can call this correctly on the first attempt without inspecting anything else.

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

Parameters4/5

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

Schema coverage is 100%, so the schema already documents all seven parameters with defaults, which sets a baseline of 3. The description adds real meaning on top: it explains where widgetId comes from (the get tool, with an example value 'wid_123'), pairs it with dashboardId, and states why includeBinaryImage matters (payload size). It does not explain the analytics-only params like context, llm_model, or conversation_id, but the schema covers those adequately.

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 definition opens with a specific verb and resource ('Render a saved Costory dashboard widget as a PNG') and immediately states which inputs drive the render ('its saved query and dashboard filters'). It distinguishes itself from close siblings by name, telling the agent this is not get_dashboard_widget_data and not the ad-hoc query path.

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 gives positive triggers ('use when the user requests an image of that widget', 'wants to see a visual snapshot or embed an image in a chat reply'), explicit exclusions for text/table-only widgets, and a named alternative for ad-hoc charts (query with returnGraphImage). The agent has no ambiguity about when to pick this tool versus its siblings.

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 toolsInspect
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