Retrieve configured Large Language Models on Polarion to verify AI availability and select a valid model for generation. Paginated; empty result signals no LLM configured.
MIT
679,816 tools. Updated 2026-10-20 03:48
"Finding tasks for large language model agents" matching MCP tools:
- Delete a Cognigy.AI large language model configuration. Features using this model stop working. Use dryRun parameter to validate before deletion.MITDestructive
- Test the connection to a Cognigy.AI large language model provider to validate credentials and reachability before using it in flows.MIT
- Convert lists of texts into embedding vectors for similarity comparisons, duplicate detection, or topic-based sorting without invoking a large language model.MIT
- Retrieve all available large language model providers to see which models are supported for your AI workflows.MIT
- Run multiple AI agents in parallel, each with its own model and task, to split large coding jobs into smaller parts. Receive combined outputs from coders, testers, and reviewers.MIT
Matching MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables MCP-aware clients to use a reliable multi-agent tool system with tiered model routing, schema-validated decisions, and graceful tool degradation, allowing small models to handle complex tasks.MIT
- FlicenseNot gradedqualityDmaintenanceMCP server that silently monitors state changes in structured data sources (e.g., government open data) and provides a pull-based channel for AI agents to retrieve real mutations since their last cursor.-
Matching MCP Connectors
- TasksOAuth
Read and edit your Tasks boards: create and update tasks, comment, and track time.
- zoom-tasksOAuth
Zoom Tasks server for creating, updating, assigning, and synchronizing task workflows.
- Lists large language model configurations for Cognigy.AI generative AI features like Knowledge AI and AI Agents, showing provider, model type, and connection info, with pagination and filtering options.MIT
- Retrieves detailed configuration of a specific large language model, including provider settings, model type, connection details, and fallback configuration.MIT
- Find registered agents by skill and minimum tier to discover agents that can complete specific tasks.-
- Aggregate token and cost usage across tasks, agents, projects, and date ranges to return totals and breakdowns by agent and model.MIT
- List AI agents in your organization to retrieve their voice, LLM, language settings, and call statistics.MIT
- Search for AI agents by capability or natural language query to find agents that assist with specific tasks.MIT
- Retrieve integration examples for any AI model and programming language from APIAny. Use to see code snippets for your chosen model and language.MIT
- Add your own custom large language model to Bolna by providing its API endpoint. Enable your voice agents to use your preferred LLM.MIT
- Retrieve tasks from a checklist in a readable text format. Choose preview mode for a quick overview of large lists or compact mode to see all tasks with IDs and titles.-
- Monitor active and recent execute_subtask calls. View elapsed time, model, prompt excerpt, and target file for tasks. Track parallel background work.Apache 2.0
- Analyze a video from a URL using a large visual memory model. Custom prompts enable asking specific questions, with reasoning mode for deep understanding.-
- Quickly classify a coding task using heuristics to return the optimal model, score, reason, and agents without invoking an LLM, ideal for simple tasks or when speed is critical.Apache 2.0
- Publish immutable, persistent text artifacts without starting a model. Use source_path for large files so their bodies stay out of the model context.MIT
- Update project-level overrides for a configured model; omitted fields stay unchanged, while null or empty lists clear overrides so the project inherits them. Changes apply on agents' next model call.Apache 2.0Destructive
- Perform deep forensic safety checks for high-stakes crypto transactions. Covers cross-chain analysis, multi-language data, and detailed reasoning for due diligence on large transfers and fraud investigations.MIT