Meko for CrewAI
Meko gives your CrewAI crews memory. Your code decides what to remember, when to recall, and what to record. What one crew learns is available to the next, and to every other agent that uses your datapack.
Over MCP, Meko provides CrewAI with:
Agent-scoped memory
What your agent learns persists beyond the session and is readable via every AI tool you connect to.
A shared knowledge base
Documents and promoted conclusions are searchable by all agents and teammates with access to the datapack.
A trace of every read and write
Each conversation is stored with its reasoning, so you can see what an agent did and why.
Your CrewAI MCP adapter is the integration point
CrewAI connects to MCP servers via crewai-tools’ MCPServerAdapter, so a few lines give your agents access to all of Meko’s tools.
Operations covering memory, conversations, knowledge base, datapacks, artifacts, and observability are available for you. Your agents call them mid-task, and your code calls the same endpoint directly when an operation must happen every time.
How Meko Benefits CrewAI
Remember in one kickoff, recall in the next
Tell an agent to remember a decision, and ask for it in a later kickoff in plain language. The answer comes from the datapack. Ask from the same crew, a new crew, or a different tool entirely. Using memory tools, you can read any agent’s memories on the datapack by agent ID.
Search before the crew reasons
Call the memory and knowledge base search tools before kickoff, and agents begin with prior conclusions, uploaded documents, and team knowledge instead of a blank context.
Record a kickoff and its files, read them back later
Conversation tools log the steps you choose to record: what each agent was asked, what it did, and why, tagged by agent. Artifact tools store the files the crew produced next to it. Open both later from any tool on the datapack.
Promote conclusions to team knowledge
Memory starts private to the datapack. Memory tools can promote a crew’s conclusion to the shared knowledge base, where every agent and teammate with access can search it.
Give each role only the tools it needs
The adapter exposes Meko’s tools individually. Give the researcher the search tools, give the writer the memory tools, and keep datapack administration off the crew.
Connecting Meko in CrewAI
1. Install the tools package: pip install crewai-tools[mcp]
2. Connect Meko as a remote server:
from crewai import Agent
from crewai_tools import MCPServerAdapter
server_params = {
"url": "https://mcp.mekodata.ai/mcp",
"transport": "streamable-http",
"headers": {
"Authorization": "Bearer <your-api-key>",
"User-Agent": "meko-crewai/1.0",
},
}
with MCPServerAdapter(server_params) as mcp_tools:
researcher = Agent(role="Researcher", tools=mcp_tools, ...)
3. Generate the API key in the Meko portal under Settings, then API Keys.
4. Kick off the crew. All of Meko’s tools are available to your agents, and your code can call the same endpoint directly whenever you want recall or logging guaranteed.