mcp-context-forge and mcp-gateway

These are competitors offering similar gateway functionality—both provide centralized MCP orchestration and management layers, though IBM's tool emphasizes multi-protocol support (MCP, A2A, REST/gRPC) and registry capabilities while Lasso focuses on plugin-based extensibility for agent development.

mcp-context-forge
73
Verified
mcp-gateway
43
Emerging
Maintenance 25/25
Adoption 10/25
Maturity 15/25
Community 23/25
Maintenance 10/25
Adoption 10/25
Maturity 9/25
Community 14/25
Stars: 3,393
Forks: 570
Downloads:
Commits (30d): 228
Language: Python
License: Apache-2.0
Stars: 352
Forks: 28
Downloads:
Commits (30d): 0
Language: Python
License: MIT
No Package No Dependents
No Package No Dependents

About mcp-context-forge

IBM/mcp-context-forge

An AI Gateway, registry, and proxy that sits in front of any MCP, A2A, or REST/gRPC APIs, exposing a unified endpoint with centralized discovery, guardrails and management. Optimizes Agent & Tool calling, and supports plugins.

Implements gRPC-to-MCP translation via server reflection and REST-to-MCP adaptation with automatic JSON Schema extraction, while providing OpenTelemetry-based observability across multiple backends (Phoenix, Jaeger, Zipkin). Runs as a native MCP server with 40+ plugins for protocol extensibility, Redis-backed caching for multi-cluster deployments, and built-in auth, rate-limiting, and retry policies across federated tool, agent, and API gateways.

About mcp-gateway

lasso-security/mcp-gateway

A plugin-based gateway that orchestrates other MCPs and allows developers to build upon it enterprise-grade agents.

Supports pluggable security guardrails (basic token masking, PII detection via Presidio, and advanced policy enforcement via Lasso) that intercept and sanitize MCP requests/responses before reaching LLMs. Exposes `get_metadata` and `run_tool` endpoints to provide unified discovery and execution across proxied MCPs, while optionally scanning server reputation via Lasso Security's API. Integrates with Cursor and Claude Desktop through standard `mcp.json` configuration, with Docker support for containerized deployment.

Scores updated daily from GitHub, PyPI, and npm data. How scores work