Score breakdown
Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.
Why it matters
Useful for teams that want to standardize LLM routing, metrics and provider access without wiring every app to every vendor separately. It matters most when the gateway is treated as sensitive infrastructure, not just a convenience proxy.
Where this stands now
Inference Gateway — a self-hosted OpenAI-compatible router that can expose MCP tools only when enabled ranks #7 of 10 tracked AI Gateway items by composite score (7.8 against a section median of 7.9). The section currently carries 6 Gold, 4 Silver. Signal extremes versus the section: novelty at the 30th percentile.
Who should use it
Who should skip it
Move on from Inference Gateway — a self-hosted OpenAI-compatible router that can expose MCP tools only when enabled if the licensing terms, language support, or platform requirements do not fit your project.
About this signal
Inference Gateway — a self-hosted OpenAI-compatible router that can expose MCP tools only when enabled is tracked by RepoRadar as a developer tool in the AI Gateway section. First seen —; the source record was last checked on 2026-09-06. The current verdict is 'try now' with a Gold tier and moderate setup difficulty. Inference Gateway — a self-hosted OpenAI-compatible router that can expose MCP tools only when enabled leads on workflow potential (8.9) and maturity (8.7); its lowest signal is setup ease (6.4), so factor that in before investing setup time. This page summarizes the public evidence on the linked source page and states where additional review is still needed.
How this item is evaluated
The Inference Gateway — a self-hosted OpenAI-compatible router that can expose MCP tools only when enabled record combines a 7.8/10 composite score with separate popularity (100.0), risk (conditional), and setup (moderate) signals. See the scoring methodology for the current weights and evidence definitions.
Questions worth asking before you adopt this
Putting this into practice? Read How to vet an AI agent or MCP server before you wire it in for the checklist behind this score.
Risk explanation
Provider API keys and routing policy live at the gateway boundary. A bad deployment can centralize access to multiple paid or sensitive model providers; Provider-native proxying can forward requests beyond the standardized API surface. Restrict credentials and network exposure before use; MCP middleware lets model calls reach configured tools when enabled. Keep MCP_ENABLED and MCP_EXPOSE off until each tool server is reviewed; Telemetry and audio endpoints are opt-in according to the README, but production deployments still need normal retention, access-control and data-handling review.