chaoslimba-mcp-server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@chaoslimba-mcp-server show grammar features for A2 level"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
chaoslimba-mcp-server
MCP server for ChaosLimba — provides read-only access to the Romanian language learning platform's database via the Model Context Protocol.
Built with TypeScript, the @modelcontextprotocol/sdk, and PostgreSQL.
Tools
Tool | Description |
| Returns all tables and columns in the database. Good starting point for orientation. |
| Lists grammar features from |
| Traces the full recursive prerequisite tree for a given grammar feature. |
| Browses content items with optional filters for difficulty, topic, and type (audio/text). |
| Cross-references grammar features against content items to identify coverage gaps. |
| Aggregates anonymized error logs to show where learners struggle most. |
| Summarizes fossilization interventions — escalation tiers, counts, and resolution rates. |
Related MCP server: maimemo-mcp
Setup
Prerequisites
Node.js 18+
A PostgreSQL database with the ChaosLimba schema
Install & Build
npm install
npm run buildEnvironment Variables
Variable | Required | Description |
| Yes | PostgreSQL connection string |
Run
CHAOSLIMBA_DATABASE_URL="postgresql://..." npm startClaude Desktop Configuration
Add to your claude_desktop_config.json:
{
"mcpServers": {
"chaoslimba": {
"command": "node",
"args": ["/absolute/path/to/chaoslimba-mcp-server/dist/index.js"],
"env": {
"CHAOSLIMBA_DATABASE_URL": "postgresql://..."
}
}
}
}Available Tools
20 toolscl_add_contentAdd Content ItemA
Inserts a new content item into the content_items table. Use during dev sessions to seed reading passages, audio content, etc.
Inputs: type (required), title (required), topic (required), difficultyLevel (required), +10 more.
cl_add_reading_questionAdd Reading QuestionA
Inserts a new reading comprehension question into the reading_questions table. Provide a passage, question, answer options, and the index of the correct answer.
Inputs: level (required), options (required), passage (required), question (required), +2 more.
cl_coverage_reportGrammar Coverage ReportARead-only
Cross-references grammar_feature_map against content_items.language_features to show which grammar features have content coverage and which are gaps. The core instructional design audit tool.
Inputs: no named parameters.
cl_get_adaptation_summaryGet Adaptation SummaryARead-only
Returns a summary of fossilization interventions — which patterns are being escalated and whether they are resolving. Shows max tier reached, total interventions, and resolution counts.
Inputs: no named parameters.
cl_get_contentGet Content ItemsARead-only
Returns content items, optionally filtered by difficulty level, topic, or type. When no difficulty filter is set, results are stratified across difficulty levels for even coverage.
Inputs: type, limit, topic, difficultyLevel.
cl_get_error_patternsGet Error PatternsARead-only
Returns aggregated error patterns from error_logs across all users (anonymized). Useful for understanding where learners actually struggle.
Inputs: limit, errorType.
cl_get_feature_exposureGet Feature ExposureARead-only
Returns aggregated feature exposure data — how many times each grammar feature has been seen by learners, with correctness rates. Anonymized. Useful for finding undertaught or poorly-performing features.
Inputs: limit, featureKey.
cl_get_generated_content_summaryGet Generated Content SummaryARead-only
Returns aggregated stats on AI-generated content — what types are being generated, for which error targets, listening rates, and estimated TTS costs. Anonymized. Useful for auditing the AI tutor's output quality and cost.
Inputs: limit, contentType.
cl_get_grammar_mapGet Grammar Feature MapARead-only
Returns all entries from grammar_feature_map, optionally filtered by CEFR level. Shows feature keys, names, categories, descriptions, prerequisites, and sort order.
Inputs: cefrLevel.
cl_get_learning_narrativesGet Learning NarrativesARead-only
Returns AI-generated learning narrative summaries — periodic reflections on learner progress with stats. Anonymized. Useful for auditing narrative quality and checking if the reflection system captures meaningful patterns.
Inputs: limit.
cl_get_mystery_itemsGet Mystery ItemsARead-only
Returns mystery vocabulary items — words learners encountered and flagged for exploration. Shows word, context, definition, examples, grammar info, and whether the learner has explored it. Useful for understanding organic vocabulary discovery.
Inputs: limit, explored.
cl_get_prerequisite_chainGet Prerequisite ChainARead-only
For a given grammar feature, returns its full recursive prerequisite chain so you can audit whether the sequencing is pedagogically sound. Caps depth at 10.
Inputs: featureKey (required).
cl_get_proficiency_trendsGet Proficiency TrendsARead-only
Returns proficiency score history over time — overall, listening, reading, speaking, writing scores by period. Anonymized across all users. Useful for tracking whether content improvements translate to learner gains.
Inputs: limit.
cl_get_reading_questionsGet Reading QuestionsARead-only
Returns reading comprehension questions, optionally filtered by CEFR level. Shows passage text, question, answer options, and correct index. Useful for auditing question quality and level coverage.
Inputs: level, limit.
cl_get_schemaGet Database SchemaARead-only
Returns a summary of all tables and their columns in the ChaosLimba database. Use this to orient yourself when first connecting.
Inputs: no named parameters.
cl_get_session_summaryGet Session SummaryARead-only
Returns aggregated session data — session counts by type, average duration, and content engagement. All data is anonymized (no user IDs returned). Useful for understanding how learners actually use the app.
Inputs: limit, sessionType.
cl_get_stress_pairsGet Stress Minimal PairsARead-only
Returns stress minimal pairs — words where stress placement changes meaning (e.g., CÁsă vs caSĂ). Core pronunciation training data.
Inputs: limit.
cl_get_suggested_questionsGet Suggested QuestionsARead-only
Returns AI tutor conversation starter questions, optionally filtered by CEFR level or category. Useful for auditing prompt quality and topic coverage.
Inputs: limit, category, cefrLevel.
cl_get_tts_usageGet TTS UsageARead-only
Returns TTS (text-to-speech) usage stats — characters consumed per day. Useful for monitoring costs and usage trends.
Inputs: days.
cl_get_tutor_openingsGet Tutor Opening MessagesARead-only
Returns tutor opening messages keyed by self-assessment level. Shows how the AI tutor greets learners at different proficiency levels.
Inputs: selfAssessmentKey.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 20 tools
Every tool targets a distinct data area or action: schema, grammar maps, prerequisite chains, content, coverage, error patterns, adaptations, reading questions, stress pairs, and various analytics. There is no meaningful overlap among the getters or between getters and the two add tools.
Almost all tools follow the cl_ + verb + noun pattern, e.g., cl_get_content, cl_add_content, cl_get_tts_usage. The single outlier is cl_coverage_report, which omits the get_ verb, causing a minor inconsistency in an otherwise predictable naming convention.
20 tools is on the heavy side and falls in the 16-25 range that feels borderline. However, the tools cover a broad educational analytics domain with distinct read-only queries, so each tool serves a reasonably identifiable purpose.
The read/audit surface is quite comprehensive, covering grammar, content, reading questions, learner behavior, proficiency trends, generated content, and TTS costs. The main gaps are the lack of update/delete operations and write tools for most entities beyond content and reading questions, but that appears intentional for an analytics-and-seeding server.
Maintenance
Related MCP Connectors
Read-only MCP server for ClassQuill, a tutoring-business-management platform.
Read-only MCP server for The Quiet Protocol's engines, benchmarks, proof, and business data.
Text-to-SQL MCP server: read-only queries on PostgreSQL, MySQL and SQL Server with your real schema
Read-only MCP server exposing a user ORANO library to their own AI agent.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceA Model Context Protocol server that provides tools for connecting to and interacting with various database systems (SQLite, PostgreSQL, MySQL/MariaDB, SQL Server) through a unified interface.3-
- AlicenseAqualityDmaintenanceA read-only MCP server that provides access to Maimemo study data, including vocabulary progress, word lists, and notepads. It supports both stdio and HTTP transports with authentication and rate limiting for secure data access.6MIT
- AlicenseAqualityCmaintenanceA Model Context Protocol (MCP) server for Firebird databases intended for local use. It reads connection details from FlameRobin's fr_databases.conf so no extra configuration is needed — if you have FlameRobin set up with your Firebird databases, this server works out of the box.292MIT
- AlicenseNot gradedqualityFmaintenanceRead-only MCP server for SQL databases (SQL Server, Postgres, SQLite) with multi-server support and three-layer safety using AST validation and linting.MIT