Runlayer MCP Server for CrewAI 27 tools — connect in under 2 minutes
Connect your CrewAI agents to Runlayer through the Vinkius — pass the Edge URL in the `mcps` parameter and every Runlayer 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="Runlayer Specialist",
goal="Help users interact with Runlayer effectively",
backstory=(
"You are an expert at leveraging Runlayer 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 Runlayer "
"and summarize their capabilities."
),
agent=agent,
expected_output=(
"A detailed summary of 27 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 Runlayer MCP Server
What you can do
Connect AI agents to the Runlayer Enterprise Control Plane for comprehensive MCP ecosystem management:
When paired with CrewAI, Runlayer becomes a first-class tool in your multi-agent workflows. Each agent in the crew can call Runlayer tools autonomously — one agent queries data, another analyzes results, a third compiles reports — all orchestrated through the Vinkius with zero configuration overhead.
- Manage MCP Servers — register, inspect, update, and remove serverless MCP endpoints
- Manage Skills — create, assign, and version reusable agent capabilities
- Manage Agents — onboard AI agents (Claude, Cursor, VS Code, custom) with proper security guardrails
- Enforce Policies — define and audit security policies governing MCP access and agent permissions
- Audit Everything — retrieve complete audit trails of all MCP, skill, agent, and policy operations
- Manage API Keys — create, rotate, and revoke organization and personal API keys
- Run Security Scans — discover shadow AI, unauthorized MCP servers, and policy violations across your organization
- Monitor Organization Health — review member activity, server inventory, and security posture
The Runlayer MCP Server exposes 27 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 Runlayer to CrewAI via MCP
Follow these steps to integrate the Runlayer 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 27 tools from Runlayer
Why Use CrewAI with the Runlayer MCP Server
CrewAI Multi-Agent Orchestration Framework provides unique advantages when paired with Runlayer 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 the 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
Runlayer + CrewAI Use Cases
Practical scenarios where CrewAI combined with the Runlayer MCP Server delivers measurable value.
Automated multi-step research: a reconnaissance agent queries Runlayer 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 Runlayer, analyzes trends over time, and generates executive briefings in markdown or PDF format
Multi-source enrichment pipelines: chain Runlayer 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 Runlayer against predefined policy rules, generates deviation reports, and routes findings to the appropriate team
Runlayer MCP Tools for CrewAI (27)
These 27 tools become available when you connect Runlayer to CrewAI via MCP:
create_agent
Requires agent name and type (claude_desktop, cursor, vs_code, custom). Optionally assign MCP servers, skills, and policies during registration. Returns the created agent details. Use this to onboard new AI agents to your enterprise control plane with proper security guardrails. Register a new AI agent in Runlayer
create_api_key
Returns the key value (shown only once) and metadata. Use this to create keys for integrations, CI/CD pipelines, or service accounts. Store the key value securely immediately after creation. Create a new API key for your Runlayer organization
create_mcp_server
Requires server name and connection details (URL, authentication method). Optionally assign skills, agents, and policies during registration. Returns the created server details including the new UUID. Use this to onboard new MCP servers to your enterprise control plane. Register a new MCP server in Runlayer
create_policy
Requires policy name and rule definitions. Returns the created policy. Use this to enforce security standards, restrict access to sensitive MCP servers, or define audit requirements. Create a new security or access policy in Runlayer
create_skill
Requires skill name and description. Optionally define input/output schemas and initial MCP server assignments. Returns the created skill details. Use this to codify reusable agent capabilities for consistent use across your organization. Register a new skill (agent capability) in Runlayer
delete_agent
This disconnects the agent from all MCP servers and removes policy assignments. Requires the agent ID. Confirm with the user before proceeding. Remove an AI agent from Runlayer
delete_mcp_server
This action disconnects all associated agents and removes policy assignments. Requires the server UUID. Confirm with the user before proceeding. Remove an MCP server from Runlayer
delete_policy
All resources previously governed by this policy will no longer be subject to its rules. Requires the policy ID. Confirm with the user before proceeding. Remove a security or access policy from Runlayer
delete_skill
Does not delete the underlying MCP server tools. Requires the skill ID. Confirm with the user before proceeding. Remove a skill from Runlayer
get_agent
Requires the agent ID from list_agents results. Use this to review agent configuration, audit access patterns, or troubleshoot connectivity. Get detailed information about a specific AI agent
get_audit_logs
Returns timestamps, actor identities, action types, affected resources, and outcomes. Use this for compliance reporting, security investigations, or operational troubleshooting. Get audit logs for your Runlayer organization
get_mcp_server
Requires the server UUID from list_mcp_servers results. Use this to review server configuration, verify security compliance, or troubleshoot connectivity issues. Get detailed information about a specific MCP server
get_organization
Use this to verify your organization configuration or get an overview of your MCP ecosystem. Get your Runlayer organization details
get_scan_results
Requires the scan ID from run_mcp_sweep_scan results. Use this to review shadow AI discoveries, identify policy violations, or generate compliance reports. Get results from an MCP sweep scan
get_skill
Requires the skill ID from list_skills results. Use this to review skill configuration or understand capability dependencies. Get detailed information about a specific skill
list_agents
Returns agent names, IDs, types (Claude Desktop, Cursor, custom), assigned MCP servers, active skills, policy compliance status, and last activity timestamps. Use this to understand your agent ecosystem and verify which agents have access to which MCP servers. List all AI agents registered in your Runlayer organization
list_api_keys
Use this to audit key inventory, identify unused keys, or prepare for key rotation. List all API keys for your Runlayer organization
list_mcp_servers
Returns server names, UUIDs, status (active, inactive, blocked), assigned skills, connected agents, policy associations, and last activity timestamps. Use this as the first step to understand your MCP server inventory before managing individual servers, applying policies, or reviewing security posture. List all registered MCP servers in your Runlayer organization
list_members
Use this to audit access, review role assignments, or identify inactive accounts. List all members of your Runlayer organization
list_policies
Returns policy names, descriptions, enforcement status, affected resources, and violation counts. Use this to review your security posture before creating or modifying policies. List all security and access policies in your Runlayer organization
list_skills
Returns skill names, descriptions, associated MCP servers, usage counts, and version information. Use this to discover available capabilities before assigning them to agents or MCP servers. List all skills registered in your Runlayer organization
revoke_api_key
This action cannot be undone. Requires the key ID. Use this for compromised keys, unused keys, or during security incidents. Revoke an API key immediately
run_mcp_sweep_scan
Returns a scan ID which can be used with get_scan_results to retrieve findings. Use this for security assessments, compliance audits, or shadow AI detection. Run an MCP sweep scan to discover shadow AI across your organization
update_agent
Only pass the fields you want to change. Requires the agent ID. Use this to update agent assignments or modify metadata. Update an existing AI agent configuration
update_mcp_server
Only pass the fields you want to change. Requires the server UUID. Use this to update server endpoints, rotate credentials, or modify policy assignments. Update an existing MCP server configuration
update_policy
Only pass the fields you want to change. Requires the policy ID. Use this to refine security requirements, update access controls, or modify audit rules. Update an existing security or access policy
update_skill
Only pass the fields you want to change. Requires the skill ID. Use this to refine skill definitions or update documentation. Update an existing skill configuration
Example Prompts for Runlayer in CrewAI
Ready-to-use prompts you can give your CrewAI agent to start working with Runlayer immediately.
"Show me all MCP servers registered in our organization and their security status"
"Run a shadow AI discovery scan across our organization and show me the findings"
"Create a new policy that restricts MCP server access to only approved developers"
Troubleshooting Runlayer MCP Server with CrewAI
Common issues when connecting Runlayer 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
Runlayer + CrewAI FAQ
Common questions about integrating Runlayer 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 Runlayer 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 Runlayer to CrewAI
Get your token, paste the configuration, and start using 27 tools in under 2 minutes. No API key management needed.