Search / dev.llmlatency/llm-latency-tracker
protogridR0· no sign-inMeasured latency, time to first token and uptime for ~45 AI inference APIs, by region.
v1.1.0 · active · repository · website · descriptor JSON · versions
{
"mcpServers": {
"llm-latency-tracker": {
"type": "http",
"url": "https://llmlatency.dev/mcp"
}
}
}claude mcp add --transport http llm-latency-tracker https://llmlatency.dev/mcp[mcp_servers.llm-latency-tracker]
url = "https://llmlatency.dev/mcp"
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"llm-latency-tracker": {
"type": "remote",
"url": "https://llmlatency.dev/mcp",
"enabled": true
}
}
}{
"mcpServers": {
"llm-latency-tracker": {
"type": "http",
"url": "https://llmlatency.dev/mcp"
}
},
"deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=llm-latency-tracker&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vbGxtbGF0ZW5jeS5kZXYvbWNwIn0%3D"
}{
"servers": {
"llm-latency-tracker": {
"type": "http",
"url": "https://llmlatency.dev/mcp"
}
}
}{
"mcpServers": {
"llm-latency-tracker": {
"httpUrl": "https://llmlatency.dev/mcp"
}
}
}extensions:
"llm-latency-tracker":
enabled: true
name: "llm-latency-tracker"
type: streamable_http
uri: "https://llmlatency.dev/mcp"
timeout: 300
protocol.modernnewest supported version is 2025-06-18; 2026-07-28 not supported, older versions are deprecated until 2027-07-28protocol.statelessonly applies to 2026-07-28 serversprotocol.transportstreamable HTTPprotocol.list_ttlonly applies to 2026-07-28 serversauth.prm, auth.as_metadata, auth.cimdno remote uses OAuthauth.secret_in_urlno templated URLtools.descriptionsevery tool has a descriptiontools.description_lengthdescriptions are concisetools.schemasevery tool has an object input schematools.annotationsno tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky onestools.directory_hintsno tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: get_model_deprecations (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_ai_api_latency (readOnlyHint, destructiveHint, idempotentHint, openWorldHint)tools.token_costabout 169 tokens to load every tooltools.api_dumptools are not a one-to-one API dumpstability.changesno tool changes in 30 daysstability.rug_pullno tool changed its meaning under the same namedeps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI packageNo tool definition changes recorded. A server's first observation is its baseline; later probes record what changes.
Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.
+repository +dns-namespace +website +reachable +uptime-99% ~updated-64d-ago
Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.
| remote | auth | reachable | uptime 30d | p50 | protocol | last ok |
|---|---|---|---|---|---|---|
https://llmlatency.dev/mcp streamable-http | none | yes | 99% | 290 ms | 2025-06-18 | 2026-10-20 |
get_ai_api_latency | Measured latency (TTFB p50/p95) and uptime rankings of AI inference API providers by region, from llmlatency.dev. |
get_model_deprecations | AI model deprecation calendar: announced and shutdown dates, replacement models, and how many days of migration notice each provider actually gives (median/min/max). Every entry is verified against the provider own deprecation page. |
Schemas: list_tools.
{
"name": "dev.llmlatency/llm-latency-tracker",
"title": "LLM Latency Tracker",
"$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
"remotes": [
{
"url": "https://llmlatency.dev/mcp",
"type": "streamable-http"
}
],
"version": "1.1.0",
"repository": {
"url": "https://github.com/mazamaka/llm-latency-tracker",
"source": "github"
},
"websiteUrl": "https://llmlatency.dev",
"description": "Measured latency, time to first token and uptime for ~45 AI inference APIs, by region."
}