How to Use the Mnemonic MCP in CrewAI

Q: Can I restrict specific Mnemonic tools to certain CrewAI agents in this MCP configuration?

Yes, you can use the MCPServerHTTP class with a toolfilter to expose only what each agent needs. For example, give your researcher agent access to searchcollections while restricting your financial analyst to getnftprices. This prevents agents from wasting tokens on irrelevant tools.

Deploy specialized teams of blockchain agents using CrewAI and the Mnemonic MCP Server to track whale wallets.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mnemonic MCP to CrewAI

Create your Vinkius account to connect Mnemonic to CrewAI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Mnemonic with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run multi-agent NFT research with CrewAI

One specialized agent uses `search_collections` to discover emerging projects based on search criteria. It then passes the collection contracts to an analyst agent to dig deeper. The analyst agent calls `get_collection_stats` to evaluate floor prices, volume, and sales velocity. By dividing the labor, your crew produces detailed market reports via this MCP integration without bottlenecking a single LLM. Honestly, trying to manage this on a single agent is a recipe for rate-limit disaster.

Audit smart contracts autonomously

Your security agent invokes `get_contract_metadata` to verify the underlying code and deployment details of an NFT project. This ensures your team only interacts with verified, authentic contracts. Meanwhile, a metadata agent runs `get_nft_details` to inspect individual token attributes and rarity scores. The agents share this context through their common memory pool to calculate precise valuations.

Track whale wallets using an MCP Server

A tracking agent calls `get_wallet_nfts` to monitor high-value portfolios and detect new acquisitions. When a new asset is spotted, it flags the transaction for immediate review. A companion agent then executes `get_wallet_history` to trace the origin of the funds used for the purchase. This automated pipeline operates continuously, giving you a live feed of smart-money movements.

Setup guide

Set up Mnemonic MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Mnemonic tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Mnemonic Analyst",
    goal="Access and analyze Mnemonic data via MCP.",
    backstory="Expert analyst with direct Mnemonic access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Mnemonic transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Mnemonic Analyst",
        goal="Access and analyze Mnemonic data via MCP.",
        backstory="Expert analyst with direct Mnemonic access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Mnemonic transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Mnemonic. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Mnemonic now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Mnemonic MCP in CrewAI

You can pass your Vinkius gateway URL directly into the agent's `mcps` parameter during initialization. The framework automatically fetches the available tools and makes them accessible to the agent. This keeps your Python code clean and minimal.

Yes, you can use the `MCPServerHTTP` class with a `tool_filter` to expose only what each agent needs. For example, give your researcher agent access to `search_collections` while restricting your financial analyst to `get_nft_prices`. This prevents agents from wasting tokens on irrelevant tools.

The framework uses a shared memory system that allows agents to pass tool outputs to one another. When an agent calls `get_collection_stats`, the resulting metrics are stored in the shared context, allowing the next agent in the sequence to use that data immediately.

It supports both. Since Vinkius hosts the actual server, your local Python environment only needs to make standard HTTP calls to the gateway, making it incredibly easy to deploy your crew to any cloud provider.

Security is maintained through ephemeral, zero-trust environments. Your wallet queries and collection lookups are processed in memory and immediately discarded once the session ends. No third party can access your search history or monitor your target watchlists.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript