Skip to main content

MCP Integration

Model Context Protocol (MCP) is an open standard that enables agents to interact with external tools, resources, and prompts in a standardized way. Instead of custom integrations for each service, MCP provides a universal protocol that works everywhere.

What is MCP?

MCP provides a unified interface for three types of capabilities:

CapabilityDescriptionExamples
ToolsActions agents can performAPI calls, calculations, file operations
ResourcesData agents can readFiles, databases, APIs
PromptsPre-defined prompt templatesCode review, analysis, summarization

How MCP Works

Agent needs to act --> Calls MCP tool via standard protocol --> MCP server translates to native API --> Results returned in standard format

The agent does not need to know the details of each external service. It speaks MCP, and the MCP server handles the translation.

Built-in MCP Tools

MeetLoyd includes several built-in tools available to all agents:

ToolDescription
CalculatorMathematical operations (add, subtract, multiply, divide, power, sqrt)
Current TimeGet current date and time in any timezone
HTTP RequestMake HTTP requests (GET, POST, PUT, DELETE, PATCH)
MemoryStore and retrieve persistent data across conversations
RandomGenerate random numbers, UUIDs, or pick from choices
JSONParse, stringify, query, and transform JSON data

Assigning Tools to Agents

Tools are assigned to agents through authorization grants. When you grant a permission, the associated MCP tools become available to the agent automatically.

  1. Go to the Authorization page
  2. Select an agent and resource
  3. Pick a permission template (e.g., "Contributor")
  4. Click Grant -- the agent immediately gets access to the corresponding tools

Or use the Agent Wizard when creating or editing an agent -- the "Access & Permissions" step configures grants visually.

info

Tools are managed through authorization grants, not a direct tools array on the agent. This ensures consistent security enforcement.

Best Practices

Use Specific Tools

Assign purpose-built tools (CRM lookup, email send) rather than generic ones (HTTP request). Specific tools have better input validation and security constraints.

Limit Tool Scope

Restrict filesystem access to specific directories. Use read-only mode for databases. The principle of least privilege applies to agents too.

Secure Secrets

Never hardcode API keys or tokens. Use the secrets system so credentials are encrypted at rest and injected securely at runtime.

Validate Inputs

Define strict input schemas with required fields, types, and bounds. This prevents agents from sending invalid or dangerous data to external services.


Next: Explore Integrations for pre-built connections to popular services.