Vedha JSON MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| vedha_list_contextsA | List the altitudes, workflows, and flows of the DataOrbit operating model (Atlas scope map). Call this first when scope is ambiguous. |
| vedha_get_canvasA | Read one workflow's bounded semantic model (goal, drivers, inputs, guardrails, funnel, entities, dimensions). Optionally narrow to one dimension and value. |
| vedha_get_diagnosisA | Return the guardrails and a dimension breakdown for one canvas, to support a causal 'why' question. Thread-scoped: stays inside one canvas. Never use it for cross-canvas questions — escalate to vedha_get_atlas_review instead. |
| vedha_get_atlas_reviewA | Deterministically compose an Atlas-level review by walking a named recipe's steps, resolving each step's declared field reads against the named canvases. Use for cross-canvas/cross-altitude reviews (e.g. the Monthly Business Review). Fill each step's emits_template from the returned resolved values only — never invent a value not present in |
| vedha_get_auditA | Explain which canvases and route produced a result returned earlier in this session. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 5 tools
Each tool targets a distinct operation: listing scope, reading a canvas, diagnosing a single canvas, composing a cross-canvas review, and explaining prior results. The descriptions reinforce boundaries, especially between vedha_get_diagnosis and vedha_get_atlas_review.
All tools follow a clear vedha_<verb>_<noun> pattern, with vedha_get_* for resource retrieval and vedha_list_* for enumerating contexts. The naming is uniform and predictable.
Five tools is well-scoped for this server's read-only, explanation-oriented purpose. Each tool covers a distinct aspect of the domain without redundancy or unnecessary bulk.
The tool surface covers the full workflow: scoping, single-canvas reading, single-canvas diagnosis, cross-canvas review, and audit of prior answers. There are no obvious dead ends or significant missing operations for the stated domain.