Search / ai.runx/runx
protogridR0· no sign-inThe governed runtime for agent skills. Search the catalog and inspect a skill before running it.
v1.0.0 · active · repository · website · descriptor JSON · versions
{
"mcpServers": {
"runx": {
"type": "http",
"url": "https://api.runx.ai/mcp"
}
}
}claude mcp add --transport http runx https://api.runx.ai/mcp[mcp_servers.runx]
url = "https://api.runx.ai/mcp"
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"runx": {
"type": "remote",
"url": "https://api.runx.ai/mcp",
"enabled": true
}
}
}{
"mcpServers": {
"runx": {
"type": "http",
"url": "https://api.runx.ai/mcp"
}
},
"deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=runx&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vYXBpLnJ1bnguYWkvbWNwIn0%3D"
}{
"servers": {
"runx": {
"type": "http",
"url": "https://api.runx.ai/mcp"
}
}
}{
"mcpServers": {
"runx": {
"httpUrl": "https://api.runx.ai/mcp"
}
}
}extensions:
"runx":
enabled: true
name: "runx"
type: streamable_http
uri: "https://api.runx.ai/mcp"
timeout: 300
protocol.modernnewest supported version is 2025-11-25; 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.annotations2 of 2 tools declare readOnlyHint or destructiveHinttools.directory_hintsevery tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHinttools.token_costabout 350 tokens to load every tooltools.api_dumptools are not a one-to-one API dumpstability.changes4 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 packageget_skillchangedannotationssearch_skillschangedannotationsget_skillchangedtitlesearch_skillschangedtitleFull history: list_changes · trend: quality JSON.
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-91% ~updated-43d-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://api.runx.ai/mcp streamable-http | none | yes | 91% | 347 ms | 2025-11-25 | 2026-10-20 |
get_skillread-only | Read one runx skill in full before running it: its manifest, the authority it asks for, its publisher and trust signals, and the exact command to install and run it through the runx CLI. Everything needed to decide whether to trust a skill arrives in this one call. |
search_skillsread-only | Find runx skills by what they do. Returns each match with its skill id, owner, description, latest version, and trust tier, so a caller can pick one and then read it in full with get_skill. |
Schemas: list_tools.
{
"name": "ai.runx/runx",
"icons": [
{
"src": "https://runx.ai/assets/logo/runx-symbol-192.png",
"sizes": [
"192x192"
],
"mimeType": "image/png"
},
{
"src": "https://runx.ai/assets/logo/runx-symbol-512.png",
"sizes": [
"512x512"
],
"mimeType": "image/png"
}
],
"title": "runx",
"$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
"remotes": [
{
"url": "https://api.runx.ai/mcp",
"type": "streamable-http"
}
],
"version": "1.0.0",
"repository": {
"id": "1207981219",
"url": "https://github.com/runxhq/runx",
"source": "github"
},
"websiteUrl": "https://runx.ai",
"description": "The governed runtime for agent skills. Search the catalog and inspect a skill before running it."
}