← Index

OpenRouter

io.github.tsilva/mcp-openrouter·v1.1.8·Other

MCP server providing access to 300+ AI models via OpenRouter

Trust verdict · v1 advisory · method
NOT YET SCREENEDno verdict on file

Verdict not yet evaluated for this tool. The semantic screen takes adversarial cases first; coverage rolls out as the corpus expands (15/150 labels to graduation). The deterministic conformance probe is built but has not yet run on the public corpus, so a recorded verdict here is REVIEW or UNVERIFIED, never a clearing ALLOW. Until a verdict is recorded, an agent should treat this tool as not-yet-cleared and fall back to its own checks. Method: the eval, four-state verdict, honest limits.

Own this server? Screen its description →

Environment variables
OPENROUTER_API_KEY
requiredsecret

OpenRouter API key used to authenticate tool requests.

DEFAULT_TEXT_MODEL

Default model slug for chat tool calls when no model is provided.

DEFAULT_IMAGE_MODEL

Default model slug for image generation tool calls.

DEFAULT_CODE_MODEL

Default model slug for code-oriented tasks.

DEFAULT_VISION_MODEL

Default model slug for vision-capable tool calls.

DEFAULT_EMBEDDING_MODEL

Default model slug for embedding tool calls when no model is provided.

MCP quality score · maturity, not trust · methodology
freshness
24
completeness
15
installability
25
documentation
15
stability
10
Alternatives in Other