MCP Gateway

Agentic tools. Enterprise governance.

Standardize tool calling and context integration across autonomous AI agents. Securely bridge any LLM with internal databases, APIs, and microservices via the Model Context Protocol with sub-millisecond dispatch.

Connect your first toolExplore MCP architecture
mcp · tool execution

Agent Tool Orchestration

Active MCP Serverpostgres-mcp-prod (Port 8443)
Connected AgentLangGraph · Financial Analyst Loop
Tool Invokedexecute_sql_query (Read-Only Replica)
Execution Latency18.4 ms (Zero-Copy Rust Pipe)
Credential IsolationDatabase Password Injected Server-Side
Audit Span StatusBound to x-nr-request-id (22-Col Spend)
Open ProtocolZero Secret LeakOTLP Traced
Tool execution dispatch
< 1 ms

High-speed asynchronous Rust proxy

Protocol standard
MCP 1.0

Universal JSON-RPC context protocol

Credential leakage risk
Zero

Server-side token injection & filtering

Model compatibility
160+ Models

Automatic schema and format translation

Execution Pipeline

Secure tool proxying for autonomous agent workflows

Agents dispatch tool requests via standard MCP endpoints. nRouter validates authorization, injects enterprise secrets securely, executes the tool, and streams telemetry back to your observability pipeline.

Model Context Protocol Execution Lifecycle

  1. Agent Instruction

    Tool Call Request

    Autonomous agent initiates an MCP tool call (database query, API fetch, or document index).

  2. MCP Gateway Proxy

    Protocol Validation

    nRouter validates JSON-RPC schema, verifies virtual key permissions, and checks tool authorization.

  3. Credential Hygiene

    Header Sanitization

    Sensitive tokens and environment variables are stripped or injected server-side before execution.

  4. Sandboxed Execution

    Telemetry & Settle

    Tool response is recorded in OTLP spans with execution latency, token cost, and return payload.

Agent Architecture

Decouple tools from models with centralized governance

Tool Security

Protect backend infrastructure from unpredictable agent loops

Autonomous agent loops can execute hundreds of tool calls per second. nRouter MCP Gateway enforces concurrency limits, read-only guarantees, timeout ceilings, and parameter validation on every single tool execution.

  • Strict parameter schema validation prevents malformed SQL or API requests
  • Timeout circuit breakers abort runaway agent loops before database starvation
  • Centralized credential vault eliminates hardcoded API keys in agent scripts
  • Full OTLP tracing visualizes multi-step agent reasoning and tool executions
governance · tool fleet

Connected Enterprise MCP Tools

mcp-analytics-dbRead-Only (500ms Timeout)
mcp-github-pr-botScoped to repo:core-app
mcp-slack-notifierApproval Required on #general
mcp-bash-runnerBlocked by Org Policy
Scoped PermissionsCircuit BreakersAudit Logged
Full MCP gateway technical specification — schemas, security & transport
Standardized Model Context Protocol (MCP)
Native support for the open standard for AI tools and context servers. Connect your AI agents to Postgres, GitHub, Slack, filesystem, and custom internal APIs without custom glue code.
Credential sanitization & isolation
Agents never hold raw database passwords, internal API tokens, or secrets. nRouter MCP Gateway injects authentication tokens server-side and strips sensitive headers from outgoing and incoming payloads.
Cross-model protocol translation
Seamlessly translate tool calls between OpenAI function calling format, Anthropic tool use schemas, and native MCP JSON-RPC, allowing you to swap model backends without rewriting agent tools.
Tool call observability & OTLP spans
Every tool invocation is tracked with execution latency, payload size, return code, and error messages, bound directly to the parent LLM inference span via unified x-nr-request-id.
Fine-grained tool permissions per virtual key
Restrict which tools an agent or user can invoke. Define read-only vs mutating tool scopes, disallow dangerous shell execution, and enforce approval gates on sensitive actions.
High-concurrency Rust proxy core
Built inside the nRouter high-performance Rust proxy engine. Dispatches thousands of concurrent tool calls with negligible latency overhead (<1ms proxy routing).
Common questions

Frequently asked questions about the MCP gateway

What is the Model Context Protocol (MCP)?

Model Context Protocol (MCP) is an open industry standard that enables AI models and autonomous agents to securely connect to external tools, databases, repositories, and context sources with a standardized protocol.

How does nRouter MCP Gateway secure agent tool calls?

The nRouter MCP Gateway sits between your LLM agent and your external tools. It enforces virtual key authentication, validates tool schemas, sanitizes headers, prevents arbitrary code execution, and logs every tool action to your audit trail.

Can I use MCP with models that do not natively support it?

Yes. The nRouter Gateway automatically bridges and translates standard OpenAI tool-calling and Anthropic tool-use formats into standardized MCP JSON-RPC messages, enabling tool usage across all 160+ supported models.

Which agent frameworks are supported?

nRouter MCP Gateway works out of the box with LangChain, LlamaIndex, CrewAI, AutoGen, Microsoft Semantic Kernel, and native Python / TypeScript MCP client libraries.

Does tool execution incur token charges?

Tool execution through the MCP Gateway does not incur additional per-token markup. You only pay for standard LLM inference tokens consumed by the model before and after the tool invocation.

Where can I host my MCP servers?

You can host MCP servers in your own private VPC (AWS, Azure, GCP), behind Cloudflare Tunnels, or connect to publicly available enterprise MCP servers via mTLS and Bearer authentication.

Empower Your Agents

Supercharge autonomous AI agents with the MCP Gateway

Connect your AI agents to enterprise data and tools with standardized security, credential isolation, and comprehensive observability.

Get started for freeExplore MCP documentation