MVR API - Minimum Viable Relationships

Compile evidence context

mvr_context_compile

Read-only

Use after evidence capture to separate safe from unsafe inferences across formal, field, market, trust, and stakeholder context. It compiles context; it does not authorize action. Use when: Use when evidence is mixed and the agent needs safe claims versus unsafe claims before a verdict. Do not use when: Do not use as a go/no-go decision. Submit only consented, data-minimized, redacted or aggregated evidence; never raw confidential datasets, secrets, credentials, or personal identifiers.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`payload`	Yes	Resolved subject, market scope, and mixed evidence to compile into safe and unsafe inferences.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`status`	No
`next_steps`	No
`workflow_id`	No
`formal_proof`	No
`mcp_next_call`	No
`mcp_next_tool`	No
`response_meta`	No
`safe_inferences`	No
`workflow_status`	No
`unsafe_inferences`	No
`workflow_expires_at`	No
`mvr_response_receipt`	No
`required_user_inputs`	No
`verification_required`	No
`sentiment_trust_signal`	No
`continuation_disposition`	No
`informal_operating_signal`	No

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

Changed1 schema field changedSep 5, 2026

addedOutput schema / properties / next_steps

Added value: +{
+  "additionalProperties": false,
+  "properties": {
+    "automatic_action_authorized": {
+      "const": false,
+      "type": "boolean"
+    },
+    "boundary": {
+      "type": "string"
+    },
+    "offer_registry": {
+      "format": "uri",
+      "type": "string"
+    },
+    "options": {
+      "items": {
+        "additionalProperties": false,
+        "properties": {
+          "id": {
+            "type": "string"
+          },
+          "label": {
+            "type": "string"
+          },
+          "url": {
+            "format": "uri",
+            "type": "string"
+          },
+          "when_to_use": {
+            "type": "string"
+          }
+        },
+        "required": [
+          "id",
+          "label",
+          "url",
+          "when_to_use"
+        ],
+        "type": "object"
+      },
+      "maxItems": 3,
+      "type": "array"
+    },
+    "purpose": {
+      "const": "optional_routing_not_recommendation",
+      "type": "string"
+    },
+    "schema_version": {
+      "const": "mvr-optional-routing@1.0",
+      "type": "string"
+    }
+  },
+  "required": [
+    "schema_version",
+    "purpose",
+    "automatic_action_authorized",
+    "boundary",
+    "offer_registry",
+    "options"
+  ],
+  "type": "object"
+}

Changed7 schema fields changedAug 11, 2026

addedOutput schema / properties / continuation_disposition

Added value: +{
+  "enum": [
+    "call_now",
+    "await_input",
+    "terminal"
+  ],
+  "type": "string"
+}

addedOutput schema / properties / mcp_next_call

Added value: +{
+  "anyOf": [
+    {
+      "type": "null"
+    },
+    {
+      "additionalProperties": false,
+      "properties": {
+        "arguments": {
+          "additionalProperties": false,
+          "properties": {
+            "payload": {
+              "additionalProperties": true,
+              "type": "object"
+            }
+          },
+          "required": [
+            "payload"
+          ],
+          "type": "object"
+        },
+        "name": {
+          "type": "string"
+        }
+      },
+      "required": [
+        "name",
+        "arguments"
+      ],
+      "type": "object"
+    }
+  ]
+}

addedOutput schema / properties / mcp_next_tool

Added value: +{
+  "anyOf": [
+    {
+      "type": "null"
+    },
+    {
+      "additionalProperties": false,
+      "properties": {
+        "arguments": {
+          "additionalProperties": false,
+          "properties": {
+            "payload": {
+              "additionalProperties": true,
+              "type": "object"
+            }
+          },
+          "required": [
+            "payload"
+          ],
+          "type": "object"
+        },
+        "tool_name": {
+          "type": "string"
+        }
+      },
+      "required": [
+        "tool_name",
+        "arguments"
+      ],
+      "type": "object"
+    }
+  ]
+}

addedOutput schema / properties / required_user_inputs

Added value: +{
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

addedOutput schema / properties / workflow_expires_at

Added value: +{
+  "type": [
+    "string",
+    "null"
+  ]
+}

addedOutput schema / properties / workflow_id

Added value: +{
+  "type": [
+    "string",
+    "null"
+  ]
+}

addedOutput schema / properties / workflow_status
```
Added value: +{
+  "type": "string"
+}
```

Changed2 schema fields changedJul 29, 2026

addedOutput schema / properties / mvr_response_receipt / properties / mcp_protocol_versions
```
Added value: +{
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}
```

changedOutput schema / properties / mvr_response_receipt / required

Previous value: -[
-  "receipt_schema_version",
-  "mcp_tool",
-  "core_api_version",
-  "mcp_contract_version",
-  "tool_profile_version",
-  "sdk_version",
-  "policy_version",
-  "calibration_version",
-  "deployment_revision",
-  "host_recipe_version",
-  "authority_boundary"
-]New value: +[
+  "receipt_schema_version",
+  "mcp_tool",
+  "core_api_version",
+  "mcp_protocol_versions",
+  "mcp_contract_version",
+  "tool_profile_version",
+  "sdk_version",
+  "policy_version",
+  "calibration_version",
+  "deployment_revision",
+  "host_recipe_version",
+  "authority_boundary"
+]

Changed1 schema field changedJul 27, 2026

addedOutput schema / properties / mvr_response_receipt

Added value: +{
+  "additionalProperties": false,
+  "properties": {
+    "authority_boundary": {
+      "type": "string"
+    },
+    "calibration_version": {
+      "type": "string"
+    },
+    "core_api_version": {
+      "type": "string"
+    },
+    "deployment_revision": {
+      "type": "string"
+    },
+    "host_recipe_version": {
+      "type": "string"
+    },
+    "mcp_contract_version": {
+      "type": "string"
+    },
+    "mcp_tool": {
+      "type": "string"
+    },
+    "policy_version": {
+      "type": "string"
+    },
+    "receipt_schema_version": {
+      "type": "string"
+    },
+    "sdk_version": {
+      "type": "string"
+    },
+    "tool_profile_version": {
+      "type": "string"
+    }
+  },
+  "required": [
+    "receipt_schema_version",
+    "mcp_tool",
+    "core_api_version",
+    "mcp_contract_version",
+    "tool_profile_version",
+    "sdk_version",
+    "policy_version",
+    "calibration_version",
+    "deployment_revision",
+    "host_recipe_version",
+    "authority_boundary"
+  ],
+  "type": "object"
+}

Changed2 schema fields changedJul 12, 2026

changedInput schema / properties / payload / description

Previous value: -"Context compiler request body."New value: +"Resolved subject, market scope, and mixed evidence to compile into safe and unsafe inferences."

addedInput schema / properties / payload / properties

Added value: +{
+  "decision_stage": {
+    "type": "string"
+  },
+  "evidence_items": {
+    "description": "Alias for evidence_pack when the host already uses this field name.",
+    "items": {
+      "additionalProperties": true,
+      "type": "object"
+    },
+    "type": "array"
+  },
+  "evidence_pack": {
+    "description": "Formal, informal, field, sentiment, administrative, or telemetry evidence.",
+    "items": {
+      "additionalProperties": true,
+      "properties": {
+        "claim": {
+          "type": "string"
+        },
+        "evidence_type": {
+          "type": "string"
+        },
+        "id": {
+          "type": "string"
+        },
+        "source_date": {
+          "type": "string"
+        },
+        "source_grade": {
+          "type": "string"
+        },
+        "source_url": {
+          "type": "string"
+        },
+        "stakeholder_class": {
+          "type": "string"
+        },
+        "verification_status": {
+          "type": "string"
+        }
+      },
+      "type": "object"
+    },
+    "type": "array"
+  },
+  "market_scope": {
+    "additionalProperties": true,
+    "description": "Geography to which the compiled inferences apply.",
+    "properties": {
+      "city": {
+        "type": "string"
+      },
+      "corridor": {
+        "type": "string"
+      },
+      "country": {
+        "type": "string"
+      },
+      "region": {
+        "type": "string"
+      }
+    },
+    "type": "object"
+  },
+  "subject": {
+    "additionalProperties": true,
+    "description": "Resolved or supplied entity under assessment.",
+    "properties": {
+      "entity_archetype": {
+        "type": "string"
+      },
+      "entity_name": {
+        "type": "string"
+      },
+      "sector": {
+        "type": "string"
+      }
+    },
+    "type": "object"
+  },
+  "target_claim": {
+    "type": "string"
+  }
+}

Changed1 schema field changedJul 11, 2026
- removedInput schema / properties / api_key
```
Removed value: -{
-  "type": "string"
-}
```

Changed1 schema field changedMay 27, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "properties": {
+    "formal_proof": {
+      "type": "number"
+    },
+    "informal_operating_signal": {
+      "type": "number"
+    },
+    "response_meta": {
+      "type": "object"
+    },
+    "safe_inferences": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "sentiment_trust_signal": {
+      "type": "number"
+    },
+    "status": {
+      "type": "string"
+    },
+    "unsafe_inferences": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "verification_required": {
+      "type": "boolean"
+    }
+  },
+  "type": "object"
+}

First observedMay 24, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Annotations already signal readOnly and non-destructive, and the description adds the behavioral nuance that the tool compiles context but does not authorize action. It also discloses data-handling expectations (data-minimized, redacted, no secrets or personal identifiers), which is meaningful behavioral context beyond the annotations. It stops short of describing processing details, so not a 5.

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 description is front-loaded with the primary purpose and uses clear 'Use when'/'Do not use when' sections with a final data safety instruction. It is slightly redundant ('Use when: Use when') and could be trimmed, but overall every clause earns its place.

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?

With an output schema present, the description doesn't need to detail return values. It covers temporal placement, selection criteria, exclusions, and privacy constraints, which is enough for an agent to call it correctly in a pipeline. A slight gap is that it doesn't explain how the safe/unsafe output should feed the sibling decision tool, though 'before a verdict' implies the workflow.

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 for the single payload parameter is complete, so the baseline is 3. The description adds value by mapping evidence categories (formal, field, market, trust, stakeholder) to the expected payload content and by imposing data minimization/privacy constraints on the evidence_pack. It doesn't enumerate individual fields, but the schema already does.

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 specific verb and resource: it separates safe from unsafe inferences across named context types (formal, field, market, trust, stakeholder) after evidence capture. This goes beyond the title and clearly distinguishes the tool from siblings like mvr_decision_check, especially with the explicit 'does not authorize action' clause.

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 an explicit 'Use when' condition (mixed evidence before a verdict), a 'Do not use when' exclusion (not a go/no-go decision), and a temporal placement ('after evidence capture'). It also adds operational constraints about submitting only consented, redacted, or aggregated evidence, which is actionable guidance.

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

All MVR API - Minimum Viable Relationships tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.2/5.0

Disambiguation5/5

Each tool maps to a distinct pipeline stage: initial preflight, entity resolution, evidence completeness, context compilation, and decision routing. There is no functional overlap, and the 'do not use' guidance reinforces clear boundaries.

Naming Consistency3/5

All tools share the mvr_ prefix, but the post-prefix patterns are inconsistent: entity_resolve, context_compile, and decision_check are object_verb, while evidence_completeness and first_call do not follow that pattern. The names are still readable, but the convention is mixed.

Tool Count5/5

Five tools form a tight, purposeful pipeline for MVR preflight governance. Each tool earns its place, and the count is well within the ideal 3-15 range.

Completeness5/5

The set covers the full public decision-governance flow from initial trigger through entity resolution, evidence completeness, context compilation, and routing to licensed scoring or abstention. External scoring is explicitly out of scope, so no meaningful gap remains for a public preflight API.

Compile evidence context

Input Schema

Output Schema

Schema Changelog

TDQS

Glama MCP Gateway

TDQS

Resources