mcp-portico

mcp-portico

MCP Portico is an MCP server that turns OpenAPI descriptions or inspected backend source code into policy-controlled MCP connections, exposing multiple backend systems with tenant isolation and credential security.

Category
Visit Server

README

MCP Portico

A generic, multi-tenant MCP frontend for HTTP APIs.

CI License: Apache-2.0 Node

MCP Portico turns OpenAPI descriptions or inspected backend source code into policy-controlled MCP connections. One deployment can expose multiple backend systems while isolating tenants, credentials, catalogs, and runtime sessions.

Status: Phase 1 (foundation) complete. This repository is a fresh implementation following the implementation plan.

Why MCP Portico

  • The catalog is the gate - operations are compiled from OpenAPI/Swagger or AI-analyzed backend metadata into a validated catalog. Only catalog-gated operations can run, keyed by stable operation ID.
  • One deployment, many backends - a backend registry and tenant-scoped connections isolate URLs, credentials, and policies.
  • A fixed MCP toolset - discovery, description, and gated execution instead of arbitrary method/path input.
  • An operator CLI - catalog import/validate/diff, registry validation, connection testing, and usage analysis.

Architecture

flowchart LR
    OA["OpenAPI / Swagger 2.0-3.2"] --> IM["Import adapters"]
    REPO["Backend repository"] --> AI["AI analysis skill"]
    AI --> OA2["Generated OpenAPI + policy overlay"]
    OA2 --> IM
    IM --> IR["Normalized API model"]
    POL["Policy overlay"] --> COMP["Catalog compiler"]
    IR --> COMP
    COMP --> CAT["Validated catalog v2"]
    CAT --> REG["Backend & connection registry"]
    SEC["Secret resolver"] --> REG
    IDP["Portico identity provider"] --> RT["Tenant-aware runtime"]
    REG --> RT
    RT --> MCP["Fixed MCP toolset"]
    MCP --> UP["Authorized upstream APIs"]

Authentication at two layers

flowchart LR
    CLIENT["MCP client"] -->|"Portico API key"| AUTH["IdentityProvider"]
    AUTH --> RT["MCP Portico runtime"]
    RT -->|"Connection auth"| CONN["UpstreamAuthProvider"]
    CONN --> BACKEND["Backend API"]

Client credentials and upstream credentials are never shared. Secrets are stored as environment references, and nothing secret appears in logs, telemetry, or MCP responses.

Quick start

# Prerequisites: Node.js >= 22 and pnpm 11
pnpm install
pnpm ci:check   # typecheck, format, tests, sweeps, build, smoke
pnpm serve      # Phase 1 health server on http://127.0.0.1:3000

mcp-portico --help and mcp-portico serve are available after pnpm build.

Planned interface

mcp-portico serve
mcp-portico catalog import <openapi-file>
mcp-portico catalog validate <catalog-file>
mcp-portico catalog diff <old-catalog> <new-catalog>
mcp-portico registry validate <registry-file>
mcp-portico connection test <connection-id>

What's next

The implementation plan defines seven phases: catalog v2 and the deterministic compiler (2), tenant registry and authentication (3), OpenAPI importers (4), the operation runtime (5), the AI backend-analysis skill (6), and the inspector plus clean cutover (7).

Contributing

See CONTRIBUTING.md for setup and verification requirements, SECURITY.md for the security policy, and docs/deprecation-inventory.md for the legacy module removal map.

License

Apache-2.0. See LICENSE.

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured