Tuskira AI Agent Gateway
Open-source, self-hosted gateway in front of MCP tool servers and LLM APIs: authenticates every call, injects credentials, scopes tools per agent profile and logs it all.
Tags
Description
One Go binary with three planes: MCP (:8080), REST API and admin console (:8081) and an LLM proxy (:8082) for Claude (direct or via AWS Bedrock), OpenAI and Gemini with your own keys. It authenticates each request, injects per-request credentials, scopes tools per agent profile and records every MCP tool call and LLM request; the console includes a catalog of ready-made MCP servers, LLM logs and (with the optional ClickHouse analytics profile) access logs and session timelines. Needs PostgreSQL; ships Docker Compose and Kubernetes manifests. Works with Claude Code, Cursor, VS Code, Codex CLI and any MCP or provider-SDK client. Pre-1.0 alpha (v0.6.1 on 2026-10-22); macOS and Linux, Windows via WSL2 untested. No Tuskira account needed. Note: the demo stack stores request/response bodies unless you turn capture off.
Agent access
Related
- Docker MCP Gateway: Docker's open-source MCP gateway (the docker mcp CLI plugin behind MCP Toolkit): one endpoint that runs MCP servers in isolated containers and injects credentials.
- ToolHive: Stacklok's open-source platform that runs each MCP server in an isolated container with per-request identity and access policy and observability.
- Arcade: Actions runtime for enterprise AI agents: agent authorization, agent-optimized tools (MCP servers) and governance, plus an open-source MCP framework.
- Claude Code: Anthropic's agentic coding tool that reads your codebase, edits files, runs commands and integrates with dev tools; available in terminal, IDE, desktop and browser.
- OpenAI Codex CLI: OpenAI's lightweight open-source coding agent that runs in your terminal.
Sources
Machine-readable
- JSON
- Markdown
- Source file on GitHub (edit via pull request)