Skip to main content
Glama
OrygnsCode

opa-mcp-server

by OrygnsCode
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Explain Rego decision

rego_explain_decision

Evaluate a Rego query with tracing to explain why a decision was denied or a rule did not match, listing rules evaluated, fired, and failure lines.

Instructions

Evaluate a Rego query with full tracing and return the result, the rules entered (rulesEvaluated) and those that produced a value (rulesFired), and the trace as readable lines: location, nesting, operation, the expression in Rego syntax, and the values of the variables it names. Backtracking (Redo) events are left out. Use it to answer "why was this denied?" or "why did this rule not match?": the Fail lines name the condition that stopped a rule. A trace too long for the response cap is cut from the end (traceTruncated); narrow the query or the input to see the rest.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
inputNoInline input document.
pathsNoPolicy / data file or directory paths. Each must be inside an allowed root.
queryYesRego query to evaluate, e.g. "data.example.allow".
sourceNoInline Rego policy source. Optional: without `source` or `paths` the query runs on its own, which is enough to try a built-in or an expression.
partialNoRun partial evaluation rather than full evaluation.
unknownsNoRefs to treat as unknown during partial evaluation.
inputPathNoPath to a JSON input file. Mutually exclusive with `input`.
v0CompatibleNoRead the policy as Rego v0 (`--v0-compatible`), the syntax OPA used before 1.0: rules without `if`, partial sets as `deny[msg] { ... }`. Needed for a policy that has not been migrated, which OPA 1.x otherwise refuses to load. Where the tool also takes a query, the query is read as v0 too, with the future keywords imported so `in`, `every` and `some x in` still work in it.
strictBuiltinErrorsNoTreat builtin errors as fatal instead of returning undefined.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.8.0
    • changedInput schema / properties / v0Compatible / description
      Previous value: -"Read the policy as Rego v0 (`--v0-compatible`), the syntax OPA used before 1.0: rules without `if`, partial sets as `deny[msg] { ... }`. Needed for a policy that has not been migrated, which OPA 1.x otherwise refuses to load."New value: +"Read the policy as Rego v0 (`--v0-compatible`), the syntax OPA used before 1.0: rules without `if`, partial sets as `deny[msg] { ... }`. Needed for a policy that has not been migrated, which OPA 1.x otherwise refuses to load. Where the tool also takes a query, the query is read as v0 too, with the future keywords imported so `in`, `every` and `some x in` still work in it."
  2. Changed2 schema fields changedv0.7.0
    • changedInput schema / properties / source / description
      Previous value: -"Inline Rego policy source. Mutually exclusive with `paths`."New value: +"Inline Rego policy source. Optional: without `source` or `paths` the query runs on its own, which is enough to try a built-in or an expression."
    • addedInput schema / properties / v0Compatible
      Added value: +{
+  "description": "Read the policy as Rego v0 (`--v0-compatible`), the syntax OPA used before 1.0: rules without `if`, partial sets as `deny[msg] { ... }`. Needed for a policy that has not been migrated, which OPA 1.x otherwise refuses to load.",
+  "type": "boolean"
+}
  3. Addedv0.1.13
  4. Removedv0.1.5
  5. Addedv0.1.2
  6. Removedv0.1.1
  7. First observedv0.1.0

TDQS

A3.9/5.0
Behavior4/5

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

Discloses real behavior beyond the annotations: Redo/backtracking events are omitted, output is truncated from the end when it exceeds the response cap with a `traceTruncated` flag, and Fail lines identify the stopping condition. Annotation readOnlyHint=false is left unexplained for what is essentially an evaluation tool, which is a minor gap rather than a contradiction.

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-loads the core action and its return shape, then moves to usage and the truncation caveat. It is dense but every sentence carries information; only the trace-format enumeration is slightly over-detailed.

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?

There is no output schema, so the description must describe returns, and it does so thoroughly (result, rulesEvaluated, rulesFired, trace line anatomy, truncation). Combined with 100% schema coverage, an agent has enough to invoke it correctly, though sibling disambiguation is missing.

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%, so the schema already documents all 9 parameters in detail (including v0Compatible, partial, unknowns, strictBuiltinErrors). The description adds little parameter-level meaning beyond restating that trace values come from named variables, so the baseline 3 applies.

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?

States a specific verb and resource ('Evaluate a Rego query with full tracing') and enumerates the distinctive outputs (rulesEvaluated, rulesFired, readable trace lines). It is clear what the tool does, but it never names or contrasts the close siblings rego_explain_undefined, rego_eval_with_explain, or rego_eval, so an agent must infer differentiation.

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

Usage Guidelines4/5

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

Gives an explicit use context: 'why was this denied?' / 'why did this rule not match?', and points at the Fail lines as the diagnostic signal. It offers no when-not conditions and does not route the agent away from the many overlapping eval/explain siblings, so it stops short of full selection guidance.

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

Deploy Server

Other Tools