MCP Observatory
4m ago Tracked 59,459 Last 4m ago 24h 2,459
npm JavaScript analyzed 3.2.28

harness-mcp-v2

v3.2.28
npm

Give AI agents full access to the Harness.io platform — manage pipelines, deployments, cloud costs, chaos engineering, feature flags, SEI, and 125+ resource types through 11 MCP tools

maintainer
thisrohangupta
licence
MIT
first seen
2026-06-03
last seen
2026-09-17
releases · 30d
8
short id
risk 2/100 · heuristic grade
A minimal inferred analyzer v33 (current)
  • capability exposure inferred + 10
  • supply-chain attested + 6
  • trust mitigators mixed − 14

attested inferred mixed

The A–E grade is our heuristic synthesis — a "review this" prompt, not a verdict. Each factor is tagged by what backs it: attested (a verifiable record), reported (a third party's claim), or inferred (our own heuristic, e.g. permissions). See methodology.

grade last moved 1w ago · see ecosystem CVEs →

risk trajectory 12 movements
  • A · 7 → A · 2
  • B · 19 → A · 7
  • B · 34 → B · 19
  • C · 39 → B · 34
  • B · 33 → C · 39
  • C · 40 → B · 33
  • C · 45 → C · 40
  • B · 33 → C · 45
  • B · 28 → B · 33
  • B · 30 → B · 28
  • C · 42 → B · 30
  • C · 45 → C · 42
capability exposure grade factor +10
Inferred surface — each links to servers holding it:
vulnerabilities 0 CVEs

No known CVEs for this server.

tool safety 1 findings · grade factor +0
  1. low dangerous code

    env-secret-flows-to-network-js: A process environment value reaches a network call. Review whether it is a credential leaving the process; the ordinary API-wrapper shape (read a ke

skills & danger signals npm-tarball
prompt-surface shipped agent-instruction files + hidden-content / dangerous-code findings — quoted from the analyzed source

analyzed v3.2.28 · analyzer v33 · 18h ago

danger signals3

  • suspicious endpoint docs.datadoghq.com (telemetry) package/build/registry/toolsets/chaos-descriptions.js :338 datadoghq.eu", "ap1.datadoghq.com"; see https://docs.datadoghq.com/getting_started/site/), datadogCredentialsSecretName (REQUIRED on Kubernetes — name of k8s secret containing "dd-api-key" and "dd-app
  • suspicious endpoint docs.datadoghq.com (telemetry) package/build/registry/toolsets/chaos.js :1083 te/region identifier. Valid values (per https://docs.datadoghq.com/getting_started/site/): \"datadoghq.com\" (US1), \"us3.datadoghq.com\" (US3), \"us5.datadoghq.com\" (US5), \"datadoghq.eu\" (EU1), \"
  • suspicious endpoint 1.2.3.4 package/build/registry/toolsets/gitops.js :908 " {list:{elements:[{cluster:'staging', url:'https://1.2.3.4'}, {cluster:'prod', url:'https://2.3.4.5'}]}}\n" +
other grade factors evidence elsewhere
embed badge readme-ready
live risk-grade badge preview [![MCP Observatory risk grade](https://mcpobservatory.com/servers/npm:harness-mcp-v2/badge.svg)](https://mcpobservatory.com/servers/npm:harness-mcp-v2/security)

Heuristic, inferred signals — false positives (legitimately powerful tools, forks, language ports) are expected. Treat each as "review this", not a verdict. See the ecosystem-wide picture on the security hub, or the fleet security of thisrohangupta.