What is the Model Context Protocol?

2 min read Updated

An open standard by Anthropic defining how AI agents connect to external tools and data sources. MCP provides a universal interface for discovering and invoking capabilities — tools (actions), resources (data), and prompts (interaction patterns) — across any compatible agent framework.

WHY IT MATTERS

Before MCP, every framework had its own tool integration — custom APIs, incompatible formats. MCP standardises this with a universal protocol that any agent can speak.

Three primitives define the protocol: tools (executable actions an agent can perform), resources (read-only data providing context), and prompts (reusable interaction templates). Together they cover the full surface area of agent-to-system interaction.

MCP is rapidly becoming the standard for agent tool access. Claude, Cursor, Windsurf, VS Code Copilot, and most major agent frameworks now support it natively — meaning any MCP-compatible tool is automatically available to any MCP-compatible agent.

See model context protocol (mcp) working in your own stack — route your MCP servers through PolicyLayer and every tool call is checked against policy before it runs.

GOVERN YOUR MCP SERVERS →

Enforced before the call runs. Nothing to install.

HOW POLICYLAYER USES THIS

PolicyLayer is a hosted MCP gateway that sits transparently between any MCP client and server. Rather than modifying agent code or server implementations, you point the client at PolicyLayer instead of the server. PolicyLayer evaluates every tool call against YAML-defined policies — enforcing allow/deny decisions, argument constraints, and rate limits — then forwards approved calls to the upstream server. No code changes needed, fail-closed by default.

IN THE CATALOGUE

PolicyLayer continuously scans the MCP ecosystem and classifies every tool it finds by risk category.

43,000+ MCP servers known to the catalogue
220,000+ tools scanned and risk-classified
9,300+ servers with published scan reports

FREQUENTLY ASKED QUESTIONS

Why does MCP matter for policy enforcement?
MCP standardises how agents access tools. Because every tool call flows through a single protocol, a proxy like PolicyLayer can enforce policies on all tool calls uniformly — regardless of which agent framework or MCP server is being used.
MCP vs. direct API integration?
MCP provides discovery, schema negotiation, and context management on top of API access. It is a higher-level protocol that makes tool integration more robust — and critically, it creates a single chokepoint where policies can be enforced via an MCP proxy.
Who supports MCP?
Anthropic (Claude), Cursor, Windsurf, VS Code Copilot, and growing support from LangChain, OpenAI Agents SDK, and other tool developers. The ecosystem is expanding rapidly.

FURTHER READING

Take your agents live. Without losing control.

Route your MCP traffic through PolicyLayer. Every tool call is checked against your policy before it runs: allow, deny, or require approval. Per-identity grants. Full audit log. Live in minutes.

Instant setup, no code required.

43,000+ MCP servers and 220,000+ tools scanned and risk-classified.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.