msza.ai — Polish Catholic Sermons ✝

Search public msza.ai sources

search_msza_ai

Read-onlyIdempotent

Search public, predominantly Polish-language msza.ai sermons plus sermon studies, Bible passages, prayers, songs, people, and places for focused topic, keyword, or relevance discovery. Returned source text stays in its stored language. Use it only when no exact ID or dedicated lookup applies; do not invoke it for a generic faith or prayer conversation without a request to discover msza.ai material, and do not invoke it automatically for every request. For a non-Polish topic, use one focused Polish query while preserving proper names, IDs, Bible references, and date, church, and content filters. Do not fan out translation variants; after an empty or weak topic result, use at most one useful Polish rephrase with the same constraints. Use days_back for rolling periods and date_from/date_to for any absolute historical period. Missing results do not prove absence. Returned hits are candidates: a query may match other session content, so verify selected sermon text and do not treat retrieval.topicMatch as evidence for every result. Returns source IDs, stable citation labels, short excerpts, dates, and links. Priest names are not stored.

Input Schema

TableJSON Schema

Name	Required	Description
`limit`	No	Maximum number of compact source results to return.
`query`	Yes	Focused Polish retrieval query for a topical request. For another user language, translate only topical terms into Polish while preserving proper names, exact IDs, Bible references, and supplied filters.
`date_to`	No	Optional last Warsaw calendar day of an absolute archive period, inclusive.
`weekday`	No	Optional Warsaw weekday filter: Sunday=0, Monday=1, ..., Saturday=6.
`camera_id`	No	Optional stable church profile ID. When supplied, only public sermons from that church are searched.
`date_from`	No	Optional first Warsaw calendar day of an absolute archive period, inclusive.
`days_back`	No	Optional rolling calendar-day window ending today, for example 7 or 28. Omit when using date_from or date_to.
`content_types`	No	Optional content categories to search; omitted preserves automatic mixed discovery. Unselected categories are not queried. prayer_book covers prayers, songs and fixed liturgical texts. ai_study results are AI-generated orientation, not evidence. Explicit bible selection enables bounded Scripture search without intent inference. Date/weekday/church filters apply only to sermons; camera_id requires sermon when content_types is supplied. Up to 6 entries; duplicates are removed. Existing source kind labels remain unchanged.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`query`	Yes
`filters`	Yes
`sources`	Yes
`retrieval`	No
`archiveCapabilities`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 1, 2026

changedInput schema / properties / query / description

Previous value: -"Focused natural-language search query in Polish or English."New value: +"Focused Polish retrieval query for a topical request. For another user language, translate only topical terms into Polish while preserving proper names, exact IDs, Bible references, and supplied filters."

Changed2 schema fields changedSep 17, 2026

addedInput schema / properties / content_types

Added value: +{
+  "description": "Optional content categories to search; omitted preserves automatic mixed discovery. Unselected categories are not queried. prayer_book covers prayers, songs and fixed liturgical texts. ai_study results are AI-generated orientation, not evidence. Explicit bible selection enables bounded Scripture search without intent inference. Date/weekday/church filters apply only to sermons; camera_id requires sermon when content_types is supplied. Up to 6 entries; duplicates are removed. Existing source kind labels remain unchanged.",
+  "items": {
+    "enum": [
+      "sermon",
+      "ai_study",
+      "prayer_book",
+      "person",
+      "place",
+      "bible"
+    ],
+    "type": "string"
+  },
+  "maxItems": 6,
+  "minItems": 1,
+  "type": "array"
+}

addedOutput schema / properties / filters / properties / content_types

Added value: +{
+  "description": "Normalized requested categories, present only when explicitly supplied.",
+  "items": {
+    "enum": [
+      "sermon",
+      "ai_study",
+      "prayer_book",
+      "person",
+      "place",
+      "bible"
+    ],
+    "type": "string"
+  },
+  "maxItems": 6,
+  "minItems": 1,
+  "type": "array"
+}

Changed6 schema fields changedSep 16, 2026

addedOutput schema / properties / sources / items / properties / content_origin

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

addedOutput schema / properties / sources / items / properties / prayer_id

Added value: +{
+  "description": "Exact get_prayer argument for a prayer-book search result.",
+  "type": "string"
+}

addedOutput schema / properties / sources / items / properties / recommended_use

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

addedOutput schema / properties / sources / items / properties / study_id

Added value: +{
+  "description": "Exact get_ai_study argument for an AI-generated study result.",
+  "type": "string"
+}

addedOutput schema / properties / sources / items / properties / usage_guidance
```
Added value: +{
+  "type": "string"
+}
```
addedOutput schema / properties / sources / items / properties / verification_required
```
Added value: +{
+  "const": true,
+  "type": "boolean"
+}
```

Changed1 schema field changedSep 15, 2026

addedOutput schema / properties / sources / items / properties / licensing

Added value: +{
+  "additionalProperties": false,
+  "properties": {
+    "copyright": {
+      "type": "string"
+    },
+    "license": {
+      "type": "string"
+    },
+    "license_url": {
+      "type": "string"
+    },
+    "source_url": {
+      "type": "string"
+    },
+    "translation": {
+      "type": "string"
+    },
+    "translation_id": {
+      "type": "string"
+    }
+  },
+  "required": [
+    "translation",
+    "translation_id",
+    "copyright",
+    "license",
+    "license_url",
+    "source_url"
+  ],
+  "type": "object"
+}

Changed1 schema field changedSep 1, 2026
- addedInput schema / properties / limit / description
```
Added value: +"Maximum number of compact source results to return."
```
First observedSep 1, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations only declare read-only/idempotent safety, but the description adds substantial behavioral context beyond them: results are candidates that may match other session content, retrieval.topicMatch is not proof, empty results do not prove absence, and priest names are not stored. These are non-obvious traits an agent could not infer from the schema or 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 and scope are front-loaded in the first sentence, followed by usage rules and retrieval strategy. It is dense and longer than typical, but nearly every sentence carries a distinct constraint (language policy, filter semantics, verification caveat), so little is wasted.

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?

Given eight parameters, an output schema, and rich annotations, the description covers everything an agent needs: intent gating, query language policy, filter selection, and result-verification caveats. Return fields are already covered by the output schema, so the brief return summary is sufficient.

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 goes further by explaining cross-parameter semantics the schema does not: days_back for rolling windows vs date_from/date_to for absolute periods, and that date/weekday/camera_id filters apply only to sermons while camera_id requires sermon selection. That is real added meaning, though it does not restate the limit or query length constraints.

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?

Names a specific verb (Search) and resource (public Polish-language msza.ai sermons, studies, Bible passages, prayers, songs, people, places) with explicit scope (focused topic/keyword/relevance discovery). It is clearly distinguishable from the sibling get_* / list_* lookup tools, which the description itself calls out.

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?

Gives explicit when-to-use ('only when no exact ID or dedicated lookup applies'), when-not ('do not invoke for a generic faith or prayer conversation', 'not automatically for every request'), and recovery behavior ('after an empty or weak result, at most one Polish rephrase'). It also routes the agent away from fanning out translation variants, which is exactly the kind of alternative-selection guidance the dimension rewards.

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

All msza.ai — Polish Catholic Sermons ✝ 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?