Meko MCP Server

MCP server and tools reference

The Meko MCP Server provides the primary tools for managing datapacks, conversations, memories, knowledge base, and related search.

To connect from IDEs and MCP-compatible clients, use the Meko MCP URL https://mcp.mekodata.ai/mcp and a user API key from Settings>API Keys. See Integrations and Quick start.

Free tier quotas

On the Free tier, MCP tool calls are metered per account:

Metric Limit (per month) Example tools
Conversations 1,000 conversation_add_message
Retrievals 10,000 memory_search, knowledgebase_search

When a quota is exceeded, further calls are blocked until you upgrade. Datapack creation and knowledge-base uploads are capped separately. See Meko pricing for the full plan table.

Tools

The Meko MCP Server provides the following tools.

Use For
Conversation
conversation_*		 Full saved chat history and thread replay.

Example: Save or retrieve this chat
Memory
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_*		 Reusable, persistent, indexed shared documents, and collective memories that can be searched across agents.

Example: Search this in the knowledge base
Datapack
datapack_*		 Provisioning and managing Meko workspaces/environments.

Example: Create or manage a workspace
Artifact
artifact_*		 Uploading and retrieving files (reports, CSVs, PDFs, code output) for later or cross-agent access.

Example: Save this file for later

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
conversation_search* Search the conversation history cache for a near-duplicate past turn and, on a hit, return its full thread.
Use this to check whether a query has effectively already been answered before falling back to memory_search or knowledgebase_search.
Typical inputs: scope, query, conversation_id, agent_id, datapack_id, limit
contextual_prominence_search* One retrieval call across the conversation cache, memory, and the knowledge base. Picks the cheapest source sufficient to answer the query and tags each result with its source.
Use this instead of calling conversation_search, memory_search, and knowledgebase_search separately.
Typical inputs: scope, query, conversation_id, agent_id, datapack_id, limit
track_token_usage Record a token-usage observation against a conversation trace, so that LLM, embedding, or extraction spend is attributed for free-tier accounting and dashboards.
Use this to pair a billable model call with a recorded usage entry.
Typical inputs: scope, conversation_id, name, input_tokens, output_tokens, total_tokens, model, message_id, datapack_id

* Not available by default; may not be enabled on every Meko deployment.

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
flush_pending_memory_candidates Return a directive instructing the agent to scan recent user turns for unsaved memory candidates and call memory_add for each.
Use this at session start and periodically to capture facts shared in conversation. No database write is performed by this tool itself; deduplication is handled during the resulting memory_add calls.
Typical inputs: scope, datapack_id, agent_id, conversation_id
memory_promote Promote memories into the datapack's shared knowledge base and Collective Memory; this also removes them from the agent's private store.
Use this to programmatically promote memories via MCP, rather than via the Learnings tab in the Meko portal. Only datapack owners and maintainers may promote. See Learnings.
Typical inputs: scope, datapack_id, agent_id, conversation_id, memory_ids

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

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 datapacks.
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

Artifact tools

Tool Description
artifact_put Upload a file artifact (report, CSV, PDF, code output, and so on) to a datapack for later retrieval or cross-agent sharing.
Use this when an agent has generated a file it wants to persist. Uploading the same bytes twice is idempotent and returns the same content hash, which is the lookup key for artifact_get.
Typical inputs: scope, filename, content_base64, content_type, conversation_id, datapack_id, agent_id
artifact_get Retrieve a previously uploaded artifact by its content hash.
Use this when an agent needs to read back a file it, or another agent, previously stored using artifact_put.
Typical inputs: scope, content_hash, conversation_id, datapack_id, agent_id