Vascue Public Knowledge Search

Search Vascue's public documentation

search

Read-onlyIdempotent

Hybrid keyword + semantic search over the public pages of vascue.io: healthcare-operations guides, Vascue Front Desk for clinics, provider-side insurance-claims automation, practice-management integrations (two-way sync with Cliniko and Nookal; Jane, Mindbody, PracticeHub, HexaHealth, Halaxy, Clinicea, ClinicOffice, Semble, Plato Medical and JERA in progress), security and compliance pages, case studies, pricing and blog posts.

Use it to answer questions about what Vascue offers, how its products work and what it has published. One topic per call; cite the returned page URL for every excerpt you use.

Returns a JSON text payload: result.chunks[] ordered by relevance, each with text (a Markdown excerpt), score (0-1, higher is better) and item.metadata.url (the canonical https://www.vascue.io/... page). Off-topic queries still return the nearest chunks, so treat scores below about 0.5 as weak evidence and say so when the site does not cover a topic.

Read-only and idempotent; no authentication; 60 requests per minute per client. Public content only: never send patient information, claim documents, clinic credentials or booking requests. It cannot book appointments or look up clinic data.

Input Schema

Name	Required	Description	Default
`query`	Yes	What to look for, as a natural-language question or keywords, e.g. "how does claims pre-authorisation work" or "Cliniko integration". 3-15 words works best; one topic per call.
`ai_search_options`	No	Optional retrieval tuning. Omit for the defaults: hybrid search, 8 results, score threshold 0.35.

Schema Changelog

Changes observed during successful MCP inspections.

Changed15 schema fields changedAug 23, 2026

removedInput schema / $schema

Removed value: -"http://json-schema.org/draft-07/schema#"

changedInput schema / properties / ai_search_options / description

Previous value: -"Options for customizing the AI search behavior."New value: +"Optional retrieval tuning. Omit for the defaults: hybrid search, 8 results, score threshold 0.35."

removedInput schema / properties / ai_search_options / properties / cache

Removed value: -{
-  "properties": {
-    "cache_threshold": {
-      "type": "string"
-    },
-    "enabled": {
-      "type": "boolean"
-    }
-  },
-  "type": "object"
-}

removedInput schema / properties / ai_search_options / properties / query_rewrite

Removed value: -{
-  "properties": {
-    "enabled": {
-      "const": false,
-      "type": "boolean"
-    },
-    "rewrite_prompt": {
-      "type": "string"
-    }
-  },
-  "type": "object"
-}

removedInput schema / properties / ai_search_options / properties / reranking

Removed value: -{
-  "properties": {
-    "enabled": {
-      "const": false,
-      "type": "boolean"
-    },
-    "match_threshold": {
-      "maximum": 1,
-      "minimum": 0,
-      "type": "number"
-    }
-  },
-  "type": "object"
-}

addedInput schema / properties / ai_search_options / properties / retrieval / properties / context_expansion / description
```
Added value: +"Neighbouring chunks from the same page to include around each hit (default 0)."
```

removedInput schema / properties / ai_search_options / properties / retrieval / properties / filters

Removed value: -{
-  "additionalProperties": {
-    "anyOf": [
-      {
-        "anyOf": [
-          {
-            "type": "string"
-          },
-          {
-            "type": "number"
-          },
-          {
-            "type": "boolean"
-          },
-          {
-            "type": "null"
-          }
-        ]
-      },
-      {
-        "properties": {
-          "$eq": {
-            "anyOf": [
-              {
-                "type": "string"
-              },
-              {
-                "type": "number"
-              },
-              {
-                "type": "boolean"
-              },
-              {
-                "type": "null"
-              }
-            ]
-          },
-          "$gt": {
-            "anyOf": [
-              {
-                "type": "string"
-              },
-              {
-                "type": "number"
-              }
-            ]
-          },
-          "$gte": {
-            "anyOf": [
-              {
-                "type": "string"
-              },
-              {
-                "type": "number"
-              }
-            ]
-          },
-          "$in": {
-            "items": {
-              "anyOf": [
-                {
-                  "type": "string"
-                },
-                {
-                  "type": "number"
-                },
-                {
-                  "type": "boolean"
-                },
-                {
-                  "type": "null"
-                }
-              ]
-            },
-            "type": "array"
-          },
-          "$lt": {
-            "anyOf": [
-              {
-                "type": "string"
-              },
-              {
-                "type": "number"
-              }
-            ]
-          },
-          "$lte": {
-            "anyOf": [
-              {
-                "type": "string"
-              },
-              {
-                "type": "number"
-              }
-            ]
-          },
-          "$ne": {
-            "anyOf": [
-              {
-                "type": "string"
-              },
-              {
-                "type": "number"
-              },
-              {
-                "type": "boolean"
-              },
-              {
-                "type": "null"
-              }
-            ]
-          },
-          "$nin": {
-            "items": {
-              "anyOf": [
-                {
-                  "type": "string"
-                },
-                {
-                  "type": "number"
-                },
-                {
-                  "type": "boolean"
-                },
-                {
-                  "type": "null"
-                }
-              ]
-            },
-            "type": "array"
-          }
-        },
-        "type": "object"
-      }
-    ]
-  },
-  "propertyNames": {
-    "type": "string"
-  },
-  "type": "object"
-}

removedInput schema / properties / ai_search_options / properties / retrieval / properties / fusion_method
```
Removed value: -{
-  "enum": [
-    "max",
-    "rrf"
-  ],
-  "type": "string"
-}
```

addedInput schema / properties / ai_search_options / properties / retrieval / properties / match_threshold / description

Added value: +"Minimum relevance score for a chunk to be included (default 0.35); raise for precision, lower for recall."

addedInput schema / properties / ai_search_options / properties / retrieval / properties / max_num_results / description
```
Added value: +"Maximum chunks to return (default 8)."
```
removedInput schema / properties / ai_search_options / properties / retrieval / properties / metadata_only
```
Removed value: -{
-  "type": "boolean"
-}
```

addedInput schema / properties / ai_search_options / properties / retrieval / properties / retrieval_type / description

Added value: +"hybrid (default) fuses keyword and vector ranking; keyword for exact phrases or product names; vector for paraphrased questions."

changedInput schema / properties / ai_search_options / properties / retrieval / properties / retrieval_type / enum

Previous value: -[
-  "vector",
-  "keyword",
-  "hybrid"
-]New value: +[
+  "hybrid",
+  "vector",
+  "keyword"
+]

removedInput schema / properties / ai_search_options / properties / retrieval / properties / return_on_failure
```
Removed value: -{
-  "type": "boolean"
-}
```

changedInput schema / properties / query / description

Previous value: -"The input query."New value: +"What to look for, as a natural-language question or keywords, e.g. \"how does claims pre-authorisation work\" or \"Cliniko integration\". 3-15 words works best; one topic per call."

First observedAug 21, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Goes well past the annotations: discloses the 60 req/min limit, that no auth is needed, that the return is a JSON text payload with chunks ordered by relevance, and the important caveat that off-topic queries still return nearest chunks so scores below ~0.5 are weak evidence. Also states a hard content restriction (no patient information, claim documents, clinic credentials or booking requests).

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-loaded with what is searched and when to use it, followed by return format and constraints — a sensible order. The long parenthetical list of integrations and in-progress products is somewhat bloated, though it does convey index coverage.

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?

With no output schema, the description carries the return-value burden and does so fully: chunk shape, score semantics, and URL metadata. Combined with the access constraints and content prohibitions, nothing an agent needs in order to call this correctly is missing.

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; the description still adds value by reinforcing "one topic per call" and by telling the agent how to interpret returned scores relative to the match_threshold default, which the schema alone does not explain. It does not add further detail on retrieval_type or context_expansion beyond what the schema already provides.

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?

States a specific mechanism (hybrid keyword + semantic search) over a specific, named corpus (public pages of vascue.io) and enumerates the content domains covered. An agent knows exactly what this retrieves and over what scope, with no siblings to distinguish it from.

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?

"Use it to answer questions about what Vascue offers, how its products work and what it has published" gives explicit positive conditions, and "It cannot book appointments or look up clinic data" gives explicit exclusions. "One topic per call" plus the citation requirement further constrain correct invocation.

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

All Vascue Public Knowledge Search 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?