OrionBI

Read a dashboard's figures

dashboard_read

Read-only

Read the figures a dashboard shows — what someone opening it sees — for any dashboard you can open: your own, or one shared with you to view or to edit. dashboard is its name, or its /d/owner/slug path when a name is ambiguous. Returns each canvas and its panels (kind, title, which columns they draw) and, per query those panels read, the columns and rows as the page shows them with every filter at its default. The data is read as the dashboard's publisher, exactly like the page; the SQL behind it is never returned. Rows are capped per query (rowsPerQuery, default 100, at most 500); truncated says when there are more. Use dashboard_get for an owned dashboard's spec, and postgres_query or dataset_query for your own data.

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": {
      "dashboard": "<dashboard>"
    },
    "name": "dashboard_read"
  }
}

Input Schema

Name	Required	Description	Default
`dashboard`	Yes	Name of the dashboard, from dashboard_list, or its /d/owner/slug path
`rowsPerQuery`	No	Most rows to return per query. Defaults to 100.

Output Schema

Name	Required	Description	Default
`url`	No
`data`	Yes
`name`	Yes
`note`	No
`path`	Yes
`role`	Yes
`notes`	Yes
`theme`	No
`title`	Yes
`filters`	Yes
`takenAt`	Yes
`version`	Yes
`canvases`	Yes
`subtitle`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 4, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Beyond readOnlyHint=true, it discloses non-obvious behavior: data is read with the publisher's permissions ('exactly like the page'), the underlying SQL is never returned, rows are capped per query (default 100, max 500), and a `truncated` flag signals more rows exist. That is substantial context an agent could not infer from the 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?

Purpose is front-loaded and no sentence is filler, but the return-shape sentence ('Returns each canvas and its panels ... with every filter at its default') is long and partly redundant given an output schema exists. Dense but navigable.

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 read tool with annotations and an output schema, the description covers everything an agent needs: who the data is read as, that SQL is withheld, truncation semantics, and which sibling to prefer. No material gap remains.

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 baseline is 3, but the description adds real meaning: `dashboard` may be a name or a /d/owner/slug path when a name is ambiguous, and rowsPerQuery is tied to the `truncated` signal. The added ambiguity-resolution rule goes beyond the schema's brief parameter note.

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 concrete verb+resource ('Read the figures a dashboard shows') and immediately scopes it ('what someone opening it sees'), then differentiates from siblings by naming dashboard_get for specs and postgres_query/dataset_query for raw data. An agent can distinguish this from dashboard_get without opening either 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?

It states the eligibility condition ('for any dashboard you can open: your own, or one shared with you to view or to edit') and explicitly routes to alternatives: dashboard_get for an owned dashboard's spec, postgres_query or dataset_query for your own data. Both when-to-use and when-to-use-something-else are present.

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

All OrionBI 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?