# Lyzr — MCP server on mcp.ai
> Connect your Lyzr account and use 22 tools for AI agents straight from your AI agent. Connect with your own API key. Build, run, evaluate, and manage AI agents and related Lyzr Studio services, including voice, responsible AI, simulation, memory, scheduling, workflows, and knowledge bases.

By: mcp.ai · official
Page: https://mcp.ai/lyzr

## Connect (MCP protocol)
Remote MCP endpoint (HTTP, streamable): https://api.mcp.ai/p_lyzr?ms=1787293560000
Add it as a custom/remote MCP connector, then authenticate when prompted.

## REST API (no MCP client required)
Every tool is also a REST endpoint, authed with a workspace API key.
Discover: GET https://api.mcp.ai/api/lyzr/_endpoints   # public; lists every endpoint
Call:     POST https://api.mcp.ai/api/lyzr/<endpoint>
  Authorization: Bearer sk_live_…   # create one at https://mcp.ai/settings/api-keys
  Content-Type: application/json
  Body: { …args }   →   { "ok": true, "tool": "<id>", "result": { … } }

## Developer docs
How to use (MCP or REST), markdown: https://mcp.ai/lyzr/skill.md
Postman collection (v2.1): https://mcp.ai/lyzr/postman.json

## Tools
- lyzr_add_memory_messages(agent_id?: string, messages: object[], owner_id: string, session_id: string, instructions?: string, document_mode?: boolean, provider_type?: string, sync_extraction?: boolean, memory_credential_id?: string, extract_assistant_facts?: boolean) — Store a batch of conversation messages in Lyzr Memory for an owner, session, and optional agent, with optional synchronous fact extraction.
- lyzr_chat_with_agent(assets?: string[], message?: string, user_id?: string, agent_id: string, messages?: object[], session_id: string, filter_variables?: object, system_prompt_variables?: object) — Send a message or message history to an active Agent Studio agent and return its synchronous inference response for a session.
- lyzr_clear_memory_session(agent_id?: string, owner_id: string, session_id: string, provider_type?: string) — Permanently clear messages and memories for one explicit owner and session in Lyzr Memory. Cross-session deletion is always disabled.
- lyzr_create_agent(name: string, tool?: string, model: string, top_p?: number, is_active?: boolean, agent_goal?: string, agent_role?: string, description?: string, provider_id: string, temperature?: number, agent_output?: string, agent_context?: string, max_iterations?: integer, store_messages?: boolean, llm_credential_id?: string, agent_instructions: string, tool_usage_description?: string) — Create a single-task Agent Studio agent with an LLM provider, model, instructions, and optional tool configuration.
- lyzr_create_agent_schedule(message?: string, user_id: string, agent_id: string, timezone?: string, max_retries?: integer, retry_delay?: integer, cron_expression: string) — Create a cron schedule that runs one Agent Studio agent with a message in a specified timezone.
- lyzr_delete_agent(agent_id: string) — Permanently delete one Agent Studio agent by ID.
- lyzr_delete_agent_schedule(schedule_id: string) — Permanently delete one agent cron schedule and remove its associated scheduler job.
- lyzr_evaluate_text_with_rai_policy(query?: string, stage?: string, agent_id?: string, policy_id: string, input_text: string, session_id?: string, grounding_source?: string, agent_instructions?: string) — Apply one owned Responsible AI policy to text and return processed text, block decisions, warnings, detections, and redactions.
- lyzr_get_agent(agent_id: string) — Return the current configuration and status of one Agent Studio agent by ID.
- lyzr_get_knowledge_base(config_id: string) — Return one Lyzr Knowledge Base configuration by its known RAG configuration ID.
- lyzr_get_simulation_overview() — Return aggregate Agent Simulation counts and average evaluation pass rate for the connected workspace.
- lyzr_list_agent_schedules(limit?: integer, user_id?: string, agent_id?: string, is_active?: boolean, next_cursor?: string) — Return one page of agent cron schedules, optionally filtered by user, agent, or active state.
- lyzr_list_agent_simulation_issues(limit?: integer, resolved?: boolean, severity?: string) — Return recent performance, error, and Responsible AI issues across monitored agents, optionally filtered by resolution and severity.
- lyzr_list_agents() — Return all Agent Studio agents owned by the connected API key, including IDs needed by lifecycle and inference tools.
- lyzr_list_rai_policies() — Return Responsible AI policies owned by the authenticated user, including policy IDs and enabled guardrail configuration.
- lyzr_list_superflow_executions(limit?: integer, status?: string, next_cursor?: string, workflow_id?: string) — Return one page of SuperFlow execution records, optionally filtered by workflow and execution status.
- lyzr_list_superflow_workflows() — Return all SuperFlow workflow definitions accessible to the connected API key, including workflow IDs and graph data.
- lyzr_list_voice_agents() — Return saved Voice agents accessible to the connected organization, including IDs used to filter transcripts.
- lyzr_list_voice_transcripts(limit?: integer, to_time?: string, agent_id?: string, from_time?: string, session_id?: string, sort_order?: string, next_cursor?: string, organization_id?: string) — Return one page of accessible Voice call transcripts, optionally filtered by agent, session, organization, or date range.
- lyzr_retrieve_knowledge(query: string, top_k?: integer, retrieval_type?: string, score_threshold?: number, knowledge_base_id: string, time_decay_factor?: number, mmr_relevance_diversity_balance?: number) — Retrieve relevant documents from a known Lyzr Knowledge Base using configurable basic, MMR, hypothetical-document, or time-aware retrieval.
- lyzr_search_memories(limit?: integer, query: string, agent_id?: string, category?: string, owner_id: string, session_id?: string, cross_session?: boolean, provider_type?: string, include_historical?: boolean, memory_credential_id?: string) — Semantically search stored memories for one owner, within one session or across that owner's sessions, using Lyzr's hybrid vector and BM25 retrieval.
- lyzr_set_agent_status(agent_id: string, is_active: boolean) — Activate or deactivate an Agent Studio agent. Deactivated agents reject inference until reactivated.

## Example prompts
- "What can I do in Lyzr?"
- "Show me a summary of my Lyzr account"

## Links
Docs: https://mcp.ai/docs/mcps/lyzr
Website: https://mcp.ai/mcps/lyzr