The Meko MCP Server provides the primary tools for managing datapacks, conversations, memories, knowledge base search, and connecting to the PostgreSQL-compatible YugabyteDB database for executing database commands. To connect from IDEs and MCP-compatible clients using your datapack URL and API key, see [Quick start — Connect your AI client](../../quick-start/#connect-your-ai-client). ## Tools The Meko MCP Server provides the following tools. | Use | For | | :--- | :--- | | [Conversation](#conversation-tools)
`conversation_*` | Full saved chat history and thread replay.

Example: _Save or retrieve this chat_ | | [Memory](#memory-tools)
`memory_*` | Durable facts, preferences, decisions, and useful outcomes you want to recall across agents.

Example: _Remember this about me or the project_ | | [Knowledge base](#knowledgebase-tools)
`knowledgebase_*` | Reusable, persistent, indexed shared documents, and collective memories that can be searched across agents.

Example: _Search this in the knowledge base_ | | [Database](#database-tools)
`db_*` | Structured operational data you want to query or modify with SQL.

Example: _Run SQL on my data_ | | [Datapack](#datapack-tools)
`datapack_*` | Provisioning and managing Meko workspaces/environments.

Example: _Create or manage a workspace_ | ### Conversation tools | Tool | Description | | :--- | :---------- | | `conversation_create` | Create a stored conversation container for all conversations in a datapack.
Use this to save a chat/thread, not just a fact or document.
Typical inputs: `scope, agent_id, session_id, datapack_id, title, run_id, metadata` | | `conversation_add_message` | Add a user/assistant turn to a stored conversation.
Use this to preserve full exchanges rather than storing long-term facts.
Typical inputs: `scope, seed, datapack_id, conversation_id, agent_id, input, output, reasoning, metadata` | | `conversation_get` | Fetch a stored conversation, optionally with messages.
Use this to review or replay a past conversation.
Typical inputs: `scope, datapack_id, agent_id, conversation_id, include_messages, limit, offset` | | `conversation_list` | List stored conversations.
Use this to browse saved chat history.
Typical inputs: `scope, datapack_id, agent_id, limit, offset` | | `conversation_update` | Update a conversation title or metadata.
Use this when organizing or relabeling stored conversations.
Typical inputs: `scope, datapack_id, conversation_id, agent_id, title, metadata` | | `conversation_delete` | Permanently delete a stored conversation.
Use this to remove saved conversation history.
Typical inputs: `scope, datapack_id, conversation_id, agent_id` | ### Memory tools | Tool | Description | | :--- | :---------- | | `memory_add` | Store durable facts, preferences, decisions, or useful outcomes for a better context.
Use this to add long-term reusable memory across threads.
Typical inputs: `scope, datapack_id, agent_id, conversation_id, text, messages, run_id, metadata` | | `memory_search` | Search stored memories semantically and return related graph relations.
Use this to recall prior facts, preferences, or decisions.
Typical inputs: `scope, datapack_id, agent_id, conversation_id, query, limit`| | `memory_get_all` | List all memories for an agent or user scope.
Use this to audit or inspect what's been remembered.
Typical inputs: `scope, datapack_id, agent_id, conversation_id, run_id` | | `memory_get_by_id` | Retrieve a single memory by ID.
Use this to inspect a memory.
Typical inputs: `scope, datapack_id, agent_id, conversation_id, memory_id` | | `memory_update` | Replace the text of an existing memory.
Use this to correct a remembered fact.
Typical inputs: `scope, datapack_id, agent_id, conversation_id, memory_id, text` | | `memory_delete_by_id` | Delete one memory.
Use this to remove a specific stored memory.
Typical inputs: `scope, datapack_id, agent_id, conversation_id, memory_id` | | `memory_delete_all` | Delete all memories in a scope.
Use this for a full reset or broad cleanup.
Typical inputs: `scope, datapack_id, agent_id, conversation_id, run_id` | ### Knowledgebase tools | Tool | Description | | :--- | :---------- | | `knowledgebase_search` | Perform a similarity search based on the user query.
Use this when you want to search the knowledge base for your queries.
Typical inputs: `scope, datapack_id, agent_id, conversation_id` | ### Database tools | Tool | Description | | :--- | :---------- | | `db_run_read_only_query` | Run a read-only SQL query and return JSON results.
Use this for direct structured data access using YSQL.
Typical inputs: `scope, datapack_id, conversation_id, query` | | `db_run_write_query` | Run a write SQL statement in a transaction.
Use this to insert, update, or delete structured data.
Typical inputs: `scope, datapack_id, conversation_id, query` | | `db_summarize_database` | Summarize tables, schema, and row counts.
Use this to explore a datapack's database before writing queries.
Typical inputs: `scope, datapack_id, conversation_id, schema` | ### Datapack tools | Tool | Description | | :--- | :---------- | | `datapack_create` | Provision a new datapack with database and MCP details.
Use this to set up a new isolated Meko environment.
Typical inputs: `scope, conversation_id, datapack_id, name` | | `datapack_describe` | Return datapack details and optional status.
Use this to inspect an existing datapack.
Typical inputs: `scope, conversation_id, datapack_id, name, include_status` | | `datapack_list` | List available datapacks.
Use this to see all workspaces/environments.
Typical inputs: `scope, conversation_id, datapack_id, name` | | `datapack_update` | Update a datapack's database connection string.
Use this to point a datapack to a new database connection. Typically used when you have access to multiple datpacks.
Typical inputs: `scope, conversation_id, datapack_id, name, include_status, connection_string` | | `datapack_delete` | Permanently delete a datapack.
Use this to completely delete an environment.
Typical inputs: `scope, conversation_id, datapack_id, name` |