# ai.runx/runx

The governed runtime for agent skills. Search the catalog and inspect a skill before running it.

- **Type:** MCP server
- **Trust:** 60/100 (B), scored on the content rubric
- **Verification:** community-indexed — nobody has claimed this listing
- **Version:** 1.0.0
- **Author:** ai.runx
- **License:** Unknown
- **Endpoints:** streamable-http https://api.runx.ai/mcp
- **Source:** https://github.com/runxhq/runx
- **Endpoint health:** reachable (last checked 2026-09-17T01:22:42.581Z, 2 samples) — uptime is not a security property and is not part of the trust score
- **Compatible clients:** claude-code, cursor, copilot, chatgpt, gemini (basis: transport)

## Trust

60/100 (B), scored on the content rubric
- Publisher verified: no
- Install scripts: nothing suspicious found
- Prompt-injection scan: clean
- Obfuscation scan: clean
- Evidence age: 16 days

## Security scan

- **Status:** clean
- **Scanned:** 2026-09-08T11:12:29.756Z
- **Version scanned:** HEAD
- **CVEs:** no coverage — this entry has no package coordinates to query OSV against, so "no known CVEs" is NOT asserted for it.

## Tools

14 declared. Statically extracted from the shipped source — a floor on the surface, not a census.
- `echo` — Echo a message through the fixture MCP server.
- `fail` — Return a fixture MCP error for testing.
- `sleep` — Never respond, for timeout testing.
- `env` — Return a single fixture server environment variable.
- `sourcey` — Docs skill.
- `docs_pr` — Open a governed docs PR workflow.
- `review_pr` — Run governed review.
- `single-step-create-pending` — Creates a pending single-step state.
- `single-step-transition-succeed` — Completes a running single-step state.
- `single-step-transition-ignores-invalid-event` — Invalid status/event pairs return the current state.
- `fanout-evaluate-resolved-threshold-proceeds` — Resolved threshold gates are skipped by evaluateFanoutSync.
- `fanout-plan-resolved-threshold-proceeds` — Resolved fanout gate keys let graph planning proceed past a prior pause.
- `runner-rejects-missing-source` — Pins the fixture-runner ingestion error envelope for invalid but schema-shaped policy input; this is not a policy decision fixture.
- `demo.echo` — Echo fixture.

## Install

**Verdict: review** — Installable, but 2 things to check first: No CVE coverage: this entry has no npm/PyPI coordinates to query OSV against, so "no known vulnerabilities" is not a claim that can be made about it.
**Cautions** (coverage gaps and advisories — never blocking)
- No CVE coverage: this entry has no npm/PyPI coordinates to query OSV against, so "no known vulnerabilities" is not a claim that can be made about it.
- No publisher has proved control of this listing; it is indexed, not vouched for.
**Config** (claude-code):
```json
"{\n  \"mcpServers\": {\n    \"runx\": {\n      \"type\": \"http\",\n      \"url\": \"https://api.runx.ai/mcp\"\n    }\n  }\n}"
```

## Blast radius

Contained to moderate — no credential declaration found, from the publisher, the upstream registry, or the README. Known so far: runs on someone else's infrastructure; read-only tool surface.
- Floor 9, ceiling 27 (tier: unknown)
- `unknown` means the floor and ceiling land in different bands — not measured enough to name one. It does not mean low.
- This is impact, not likelihood. A high radius is not a defect: a filesystem server is supposed to write files. It is never part of the trust score.

## Machine-readable views of this entry

- Signed JSON: https://forgeregistry.com/api/v1/packages/ai.runx%2Frunx
- Install plan: https://forgeregistry.com/api/v1/packages/ai.runx%2Frunx/install-plan
- Alternatives: https://forgeregistry.com/api/v1/alternatives/ai.runx%2Frunx
- HTML page: https://forgeregistry.com/registry/ai.runx%2Frunx
- MCP: POST https://forgeregistry.com/api/mcp → `forge_get_package` / `forge_install_plan`

## About this document

Generated by Forge (https://forgeregistry.com) — a compact rendering of the same record served, signed, at the JSON URL above. Trust and scan facts are the registry's own measurements; anything Forge did not measure is named as unmeasured rather than omitted.