Agent Gateway
MCP gateway that aggregates multiple downstream MCP servers behind a single interface, exposing just 3 tools (~2k tokens) instead of loading all server tools upfront (5k-50k+ tokens). Built with FastMCP 2.0, provides on-demand tool discovery through list_servers, get_server_tools, and execute_tool. Features per-agent access control via configurable policy rules with wildcard patterns and deny-before-allow precedence, hot configuration reload, transparent proxying to stdio and HTTP MCP servers with OAuth support, comprehensive audit logging, and performance metrics tracking.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-28.
Scan details: Circle-IR · 2026-09-28 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- monitoring
- Source
- PulseMCP
- Repository
- github.com/roddutra/agent-mcp-gateway
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve Agent Gateway from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp --scope user for --scope project to commit it to .mcp.json.