livonian
Server Details
Grounds LLMs in the real Livonian dictionary: attested words, inflections, romanization.
- Status
- Healthy
- Last Tested
- Transport
- Streamable HTTP
- URL
Glama MCP Gateway
Connect through Glama MCP Gateway for full control over tool access and complete visibility into every call.
Full call logging
Every tool call is logged with complete inputs and outputs, so you can debug issues and audit what your agents are doing.
Tool access control
Enable or disable individual tools per connector, so you decide what your agents can and cannot do.
Managed credentials
Glama handles OAuth flows, token storage, and automatic rotation, so credentials never expire on your clients.
Usage analytics
See which tools your agents call, how often, and when, so you can understand usage patterns and catch anomalies.
Tool Definition Quality
Average 4.9/5 across 3 of 3 tools scored.
Each tool has a distinct purpose: search for dictionary lookups, get_inflections for detailed grammar tables, and romanize for ASCII conversion. No functional overlap.
All tools follow the 'livonian_verb_noun' pattern in snake_case, with verbs like get, romanize, search. Consistent and predictable.
Three tools are well-scoped for a specialized Livonian dictionary and grammar assistant. No superfluous tools, and the count matches the domain requirements.
The set covers the essential operations: searching the dictionary, retrieving inflection tables (with fallback for broad queries), and romanizing text. No obvious missing capabilities for the stated purpose.
Available Tools
3 toolslivonian_get_inflectionsGet Livonian inflection tableARead-onlyIdempotentInspect
Fetch the full declension (nouns) or conjugation (verbs) table for a word identified by a search result's inflection handle (entry_id + word_class) — the exact case, number, tense, not a guessed ending. Use this only when a search ran without inline forms, or to fetch a match a broad search left un-expanded. Never a first call — the handle values only come from livonian_search results, and a default search already returns each match's table inline, so calling this afterwards just re-fetches what you have.
Returns Markdown — a nominal gets one case × {singular, plural} table; a verb gets a table per mood/tense (person × {affirmative, negative}, the negation auxiliary folded into the negative) plus its principal-parts and participle lists — or a clean not-found message. (Grammatical labels are normalised to English; Livonian forms stay verbatim.) The same table rides along as structuredContent with the shape {"result": } per the declared outputSchema — switch on result.category ('nominal' | 'verbal' | 'not_found') before reading the body. Results are cached server-side (repeats are instant) and calls are rate limited — on a rate-limit error, wait a few seconds and retry. Table content is from livonian.tech (CC BY-SA 4.0 — attribute if republished).
| Name | Required | Description | Default |
|---|---|---|---|
| entry_id | Yes | The word id from a search result's inflection handle. Accepts a number or a digit-string (e.g. 17746 or "17746"). | |
| word_class | Yes | The word-class code from a search result's inflection handle (e.g. 's' = noun, 'adj' = adjective, 'vi' = intransitive verb, 'vt' = transitive verb). |
Output Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond annotations (readOnlyHint, idempotentHint, destructiveHint), the description details return format (Markdown, structuredContent with category), not-found messages, server-side caching, rate limits with retry advice, and attribution requirements. No contradictions with annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise, well-structured into two paragraphs. It front-loads the core purpose, then provides usage guidance, output details, and supplementary notes without unnecessary repetition.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (handling nouns/verbs, multiple output formats), the description covers all necessary aspects: input origin, usage constraints, return types, error handling, caching, rate limits, and attribution. The output schema is present, so return values are fully documented.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Both parameters have clear descriptions in the schema and are referenced in the main description. Schema coverage is 100%, so baseline is 3; the extra context about origin from search results and acceptable formats adds value, justifying a 4.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool fetches a full inflection table for a word identified by a search result's handle. It explicitly distinguishes it from siblings by noting it is not a first call and that the handle comes only from livonian_search results.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides explicit usage conditions: use only when search ran without inline forms or to expand broad search results. Emphasizes never as a first call and that default search already returns inline tables, guiding the agent to avoid redundant calls.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
livonian_romanizeRomanize Livonian to clean ASCIIARead-onlyIdempotentInspect
Strip Livonian orthography down to clean, pronounceable ASCII for an
English-trained downstream (a voice/TTS, a search box). See the text parameter
doc for the exact letter mappings. Returns Markdown plus the romanized output as
structuredContent matching the declared outputSchema. Pure local transform: no
dictionary lookup, no network, and the output is always ASCII.
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes | Livonian text to reduce to clean, pronounceable ASCII. Strips macrons, diacritics and capitals (ā→aa, š→sh, õ→u), softens a palatalized consonant (ņ ļ ŗ ţ ḑ) only before a vowel (ņ+a→nya, else ikšiggiņ→ikshiggin), and hyphenates the broken tone (si'zzõl→siz-zul) and long-vowel diphthong glides (kīen→kee-en). Pass a word, phrase, or several lines. |
Output Schema
| Name | Required | Description |
|---|---|---|
| text | Yes | The romanized ASCII output. |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, destructiveHint. Description adds detailed behavioral traits: stripping diacritics, softening palatalized consonants, hyphenating tones. No contradiction.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Concise, front-loaded description with no unnecessary information. Every sentence contributes to understanding.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the simple tool, the description covers purpose, behavior, parameter semantics, and output. Output schema exists, so no need to explain return values.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema has 100% description coverage for the single parameter. Description adds a summary of the mapping rules, but the schema already provides the full specification. Slight value added.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the tool romanizes Livonian text to clean ASCII for English-trained downstream systems. It distinguishes from sibling tools like livonian_get_inflections and livonian_search by focusing on a simple character transformation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides context that it's a pure local transform with no network or dictionary lookup, implying when to use. Lacks explicit when-not guidance, but the sibling tools cover alternative use cases.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
livonian_searchSearch the Livonian dictionaryARead-onlyIdempotentInspect
Look a word up in the real Livonian–Estonian–Latvian dictionary and return only attested content, so translations are grounded, not invented.
Search a meaning (in English/Latvian/Estonian) to find the Livonian headword, or a
Livonian word to confirm it exists and read its sense, part of speech and examples.
See the query and search_language parameter docs for how to phrase a query. By
default each match's full inflection table is returned inline, so one call usually
suffices; on a broad query only the first N tables expand (the rest are listed as
handles to fetch with livonian_get_inflections). Returns Markdown plus the same result as
structuredContent matching the declared outputSchema.
Results are cached server-side, so repeating a query is instant and free; a first-time query reaches the live dictionary and calls are rate limited — on a rate-limit error, wait a few seconds and retry instead of re-issuing immediately. Dictionary content is from livonian.tech (CC BY-SA 4.0 — attribute if republished).
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | A SINGLE content word, not a phrase. Exactly one word per call — even with several candidates or synonyms in mind, search them one at a time ('see', then 'look'), never combined into one query like 'see look'. Drop function words and infinitive markers — search 'to water' as 'water', 'the sea' as 'sea'. The dictionary matches one attested headword, so a multi-word query often returns nothing even when the word exists; search the main word first, then refine. May be Livonian, Latvian, Estonian, or English (e.g. 'jarā', 'away', 'sea'). Matching is bidirectional. An inflected Livonian form (search_language='liv') is resolved to its dictionary lemma automatically when the form is known — the result says so when that happened. | |
| max_forms | No | Optional override for how many inflection tables to expand this call (0–12). Raise it to pull more tables in ONE call on a broad query, or set a small value to keep a broad query cheap. On an uncached query each table is fetched sequentially with polite pacing toward the upstream, so a high value on a cold broad query is slow — the bound limits upstream fan-out, not just response size. Omit to use the server's default cap. | |
| include_forms | No | When true (default), each match's full inflection table is returned INLINE — usable cases/tenses in ONE call, no follow-up livonian_get_inflections. Set false to get just the headword handles + glosses: a cheap way to SCREEN several candidate words or synonyms (which exist? which sense?) before spending forms on the one you pick. Bounded by a per-search cap — use max_forms to raise or lower it for this call. | |
| search_language | No | Language your query word is in — selects which language the search matches against: 'eng' (default), 'liv', 'lat', or 'est'. For English→Livonian translation, keep 'eng'. Glosses are in English. | eng |
Output Schema
| Name | Required | Description |
|---|---|---|
| found | Yes | False when nothing matched. |
| query | Yes | |
| source | No | |
| entries | No | Structured dictionary entries: headword, pronunciation, part of speech, paradigm anchors, and senses with example sentences. |
| handles | No | |
| language | Yes | |
| resolved_from | No | The original inflected query when search_method='lemma_index'; empty on a direct match. |
| search_method | No | How the match was found: 'direct' = the query itself matched; 'lemma_index' = the query was an inflected Livonian form, resolved to its dictionary lemma via the cached paradigm index and re-searched. |
| resolved_lemma | No | The dictionary lemma actually searched when search_method='lemma_index'; empty on a direct match. |
| forms_truncated | No | How many handles did NOT get an inline table because the per-search cap was reached. Refine the query or call livonian_get_inflections. |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate readOnlyHint, openWorldHint, idempotentHint, destructiveHint. The description adds caching, rate limits, output format (Markdown plus structuredContent), and that inflected forms are resolved to lemmas. No contradictions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Well-structured, front-loaded with purpose, then usage guidelines, then parameter details, then caching and rate limits. Every sentence adds value; no fluff.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the output schema exists, description covers all necessary context: query constraints, caching, rate limits, attribution, and the workflow for expanding inflections. Complete for a dictionary search tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, but the description adds significant meaning: query must be a single content word, max_forms relates to upstream pacing, include_forms false provides screening, search_language determines query language but glosses remain in English.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool searches a Livonian-Estonian-Latvian dictionary, returning attested content. It distinguishes from siblings like livonian_get_inflections by noting that inflection tables can be fetched separately for broader queries.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides explicit guidance on query phrasing (single content word, drop function words), language selection, and when to use include_forms=false for screening before using livonian_get_inflections. Covers rate limiting and caching behavior.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Claim this connector by publishing a /.well-known/glama.json file on your server's domain with the following structure:
{
"$schema": "https://glama.ai/mcp/schemas/connector.json",
"maintainers": [{ "email": "your-email@example.com" }]
}The email address must match the email associated with your Glama account. Once published, Glama will automatically detect and verify the file within a few minutes.
Control your server's listing on Glama, including description and metadata
Access analytics and receive server usage reports
Get monitoring and health status updates for your server
Feature your server to boost visibility and reach more users
For users:
Full audit trail – every tool call is logged with inputs and outputs for compliance and debugging
Granular tool control – enable or disable individual tools per connector to limit what your AI agents can do
Centralized credential management – store and rotate API keys and OAuth tokens in one place
Change alerts – get notified when a connector changes its schema, adds or removes tools, or updates tool definitions, so nothing breaks silently
For server owners:
Proven adoption – public usage metrics on your listing show real-world traction and build trust with prospective users
Tool-level analytics – see which tools are being used most, helping you prioritize development and documentation
Direct user feedback – users can report issues and suggest improvements through the listing, giving you a channel you would not have otherwise
The connector status is unhealthy when Glama is unable to successfully connect to the server. This can happen for several reasons:
The server is experiencing an outage
The URL of the server is wrong
Credentials required to access the server are missing or invalid
If you are the owner of this MCP connector and would like to make modifications to the listing, including providing test credentials for accessing the server, please contact support@glama.ai.
Discussions
No comments yet. Be the first to start the discussion!