Aikido Security MCP Server for CrewAI 16 tools — connect in under 2 minutes
Connect your CrewAI agents to Aikido Security through Vinkius, pass the Edge URL in the `mcps` parameter and every Aikido Security tool is auto-discovered at runtime. No credentials to manage, no infrastructure to maintain.
ASK AI ABOUT THIS MCP SERVER
Vinkius supports streamable HTTP and SSE.
from crewai import Agent, Task, Crew
agent = Agent(
role="Aikido Security Specialist",
goal="Help users interact with Aikido Security effectively",
backstory=(
"You are an expert at leveraging Aikido Security tools "
"for automation and data analysis."
),
# Your Vinkius token. get it at cloud.vinkius.com
mcps=["https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"],
)
task = Task(
description=(
"Explore all available tools in Aikido Security "
"and summarize their capabilities."
),
agent=agent,
expected_output=(
"A detailed summary of 16 available tools "
"and what they can do."
),
)
crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
About Aikido Security MCP Server
Connect your Aikido Security account to any AI agent and take full control of your security posture monitoring through natural conversation.
When paired with CrewAI, Aikido Security becomes a first-class tool in your multi-agent workflows. Each agent in the crew can call Aikido Security tools autonomously, one agent queries data, another analyzes results, a third compiles reports, all orchestrated through Vinkius with zero configuration overhead.
What you can do
- Open Issues — List all open security vulnerabilities (CVEs, leaked secrets, cloud misconfigs, SAST findings) ordered by priority
- Repository Scanning — View all connected code repositories and their scanning status across GitHub, GitLab, Bitbucket
- Cloud Asset Monitoring — List cloud infrastructure assets from AWS, GCP, and Azure being monitored for misconfigurations
- Container Security — Monitor container images and registries for known vulnerabilities
- Compliance Tracking — Get ISO 27001 and SOC2 compliance overviews for audit preparation
- Export Issues — Bulk export all security findings for reporting and analysis
- Webhook Management — List configured webhooks for Slack, Jira, and other integrations
The Aikido Security MCP Server exposes 16 tools through the Vinkius. Connect it to CrewAI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.
How to Connect Aikido Security to CrewAI via MCP
Follow these steps to integrate the Aikido Security MCP Server with CrewAI.
Install CrewAI
Run pip install crewai
Replace the token
Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com
Customize the agent
Adjust the role, goal, and backstory to fit your use case
Run the crew
Run python crew.py. CrewAI auto-discovers 16 tools from Aikido Security
Why Use CrewAI with the Aikido Security MCP Server
CrewAI Multi-Agent Orchestration Framework provides unique advantages when paired with Aikido Security through the Model Context Protocol.
Multi-agent collaboration lets you decompose complex workflows into specialized roles, one agent researches, another analyzes, a third generates reports, each with access to MCP tools
CrewAI's native MCP integration requires zero adapter code: pass Vinkius Edge URL directly in the `mcps` parameter and agents auto-discover every available tool at runtime
Built-in task delegation and shared memory mean agents can pass context between steps without manual state management, enabling multi-hop reasoning across tool calls
Sequential and hierarchical crew patterns map naturally to real-world workflows: enumerate subdomains → analyze DNS history → check WHOIS records → compile findings into actionable reports
Aikido Security + CrewAI Use Cases
Practical scenarios where CrewAI combined with the Aikido Security MCP Server delivers measurable value.
Automated multi-step research: a reconnaissance agent queries Aikido Security for raw data, then a second analyst agent cross-references findings and flags anomalies. all without human handoff
Scheduled intelligence reports: set up a crew that periodically queries Aikido Security, analyzes trends over time, and generates executive briefings in markdown or PDF format
Multi-source enrichment pipelines: chain Aikido Security tools with other MCP servers in the same crew, letting agents correlate data across multiple providers in a single workflow
Compliance and audit automation: a compliance agent queries Aikido Security against predefined policy rules, generates deviation reports, and routes findings to the appropriate team
Aikido Security MCP Tools for CrewAI (16)
These 16 tools become available when you connect Aikido Security to CrewAI via MCP:
export_all_issues
This provides a comprehensive snapshot of your organization's security posture. Use this for compliance reporting, audit preparation, or bulk analysis of vulnerabilities. Export all security issues from Aikido
get_iso_compliance
Shows which controls are passing, failing, or need attention. Use this for compliance monitoring, audit preparation, and security posture reporting. This endpoint is available on all paid Aikido plans. Get ISO 27001 compliance overview for your organization
get_issue_group
The issue group ID can be obtained from list_open_issues. Each issue group represents a category of related vulnerabilities (e.g., the same CVE across multiple repositories). Use this to deep-dive into a specific security finding before deciding on remediation steps. Get detailed information about a specific security issue group
get_soc2_compliance
Shows which trust service criteria are met and which need remediation. Use this for SOC2 audit preparation and compliance monitoring. This endpoint is available on all paid Aikido plans. Get SOC2 compliance overview for your organization
get_workspace
Use this to verify your workspace setup and check for any configuration errors. Get workspace information and configuration
list_apps
Shows which apps have active protection and their configuration status. Use this to verify your web applications are properly secured against common attacks (SQL injection, XSS, etc.). List all web applications protected by Aikido firewall
list_cloud_assets
You can paginate through results and optionally search by text or sort by name, asset type, region, etc. Use this to understand your cloud attack surface and identify misconfigurations or vulnerabilities. List cloud infrastructure assets monitored by Aikido
list_code_repositories
This includes repositories connected from GitHub, GitLab, Bitbucket, etc. Use this to discover which repositories are being monitored for vulnerabilities and security issues. List all active code repositories connected to Aikido
list_connected_clouds
Shows which cloud environments are being monitored for security misconfigurations and vulnerabilities. Use this to verify cloud integrations are properly configured. List all cloud accounts connected to Aikido
list_containers
This includes Docker images from registries like Docker Hub, ECR, GCR, etc. Use this to monitor container security and identify vulnerable base images or dependencies. List all container images and repositories scanned by Aikido
list_custom_rules
Custom rules allow you to define organization-specific security checks beyond the default scanner. Use this to audit your custom rule coverage and ensure your security policies are properly enforced. List all custom SAST scanning rules in Aikido
list_open_issues
Issues include vulnerabilities from code scanning, container scanning, cloud security, SAST, IaC, DAST, and more. You can optionally filter by issue type (open_source, leaked_secret, cloud, sast, iac, docker_container, etc.), by team ID, or by repository. Supports pagination with page and per_page parameters. Use this to get a comprehensive view of your organization's security posture and prioritize remediation efforts. List all open security issues (vulnerabilities) in your Aikido account
list_teams
Teams are used to organize repositories, assign issues, and manage security workflows. Use this to understand how your organization structures its security responsibilities. List all teams in your Aikido organization
list_users
Shows user roles, permissions, and access levels. Use this to audit user access and ensure proper security team membership. List all users in your Aikido organization
list_virtual_machines
Use this to understand your VM attack surface and identify security gaps. List all virtual machines monitored by Aikido
list_webhooks
Webhooks are used to send security event notifications to external systems (Slack, Jira, etc.). Use this to verify integrations are properly configured and troubleshoot notification delivery. List all configured webhooks in Aikido
Example Prompts for Aikido Security in CrewAI
Ready-to-use prompts you can give your CrewAI agent to start working with Aikido Security immediately.
"Show me all critical and high severity open security issues, grouped by type."
"What's our current ISO 27001 compliance status?"
"List all our connected cloud accounts and any misconfigurations found in the last 7 days."
Troubleshooting Aikido Security MCP Server with CrewAI
Common issues when connecting Aikido Security to CrewAI through the Vinkius, and how to resolve them.
MCP tools not discovered
Agent not using tools
Timeout errors
Rate limiting or 429 errors
Aikido Security + CrewAI FAQ
Common questions about integrating Aikido Security MCP Server with CrewAI.
How does CrewAI discover and connect to MCP tools?
tools/list method. This means tools are always fresh and reflect the server's current capabilities. No tool schemas need to be hardcoded.Can different agents in the same crew use different MCP servers?
mcps list, so you can assign specific servers to specific roles. For example, a reconnaissance agent might use a domain intelligence server while an analysis agent uses a vulnerability database server.What happens when an MCP tool call fails during a crew run?
Can CrewAI agents call multiple MCP tools in parallel?
process=Process.parallel, each calling different MCP tools concurrently. This is ideal for workflows where separate data sources need to be queried simultaneously.Can I run CrewAI crews on a schedule (cron)?
crew.kickoff() method runs synchronously by default, making it straightforward to integrate into existing pipelines.Connect Aikido Security with your favorite client
Step-by-step setup guides for every MCP-compatible client and framework:
Anthropic's native desktop app for Claude with built-in MCP support.
AI-first code editor with integrated LLM-powered coding assistance.
GitHub Copilot in VS Code with Agent mode and MCP support.
Purpose-built IDE for agentic AI coding workflows.
Autonomous AI coding agent that runs inside VS Code.
Anthropic's agentic CLI for terminal-first development.
Python SDK for building production-grade OpenAI agent workflows.
Google's framework for building production AI agents.
Type-safe agent development for Python with first-class MCP support.
TypeScript toolkit for building AI-powered web applications.
TypeScript-native agent framework for modern web stacks.
Python framework for orchestrating collaborative AI agent crews.
Leading Python framework for composable LLM applications.
Data-aware AI agent framework for structured and unstructured sources.
Microsoft's framework for multi-agent collaborative conversations.
Connect Aikido Security to CrewAI
Get your token, paste the configuration, and start using 16 tools in under 2 minutes. No API key management needed.