taru (notoofly/taru) is an MCP server listed on the M8ven Trust Index. It scores 68 out of 100, grade C. It declares 60 tools. The publisher has proved control of what we score (Verified Publisher). It is connected through the M8ven GitHub App, so the listing is re-checked on every push.

C
Caution
68/100

taru

Open-Source Self-Hosted Autonomous Software Engineering Platform. Plan, develop, review, test, and manage software projects using AI agents with a Git-native workflow.

Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

Code Verified⚡ Live Monitored

every push re-verified

Who stands behind it

gmail.com (@notoofly) · Verified Publisher

Source: github_code

Install from

The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.

// key findings
🚨
Known vulnerabilities in dependencies: 1 critical, 8 high
Affects packages this MCP installs at runtime. Upgrade or remove the affected dependency.
🔐
You'll be asked for 2 credentials: BETTER_AUTH_SECRET, OPENAI_API_KEY
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
Are you the publisher? Confirm or correct these findings.
// known CVEs in dependencies1 critical8 high3 low

Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.

criticalbetter-auth@1.4.21GHSA-pw9m-5jxm-xr6h

Better Auth: OAuth refresh-token replay via missing client authentication on oidc-provider and mcp plugins

highbetter-auth@1.4.21GHSA-392p-2q2v-4372

Better Auth: OAuth refresh-token rotation forks the token family on concurrent redemption

highbetter-auth@1.4.21GHSA-7w99-5wm4-3g79

@better-auth/oauth-provider's OAuth authorization-code grant allows concurrent redemption when two token requests race the find-then-delete primitive

highbetter-auth@1.4.21GHSA-86j7-9j95-vpqj

Better Auth has stored XSS in the auth-server origin via javascript: redirect_uri in oidc-provider and mcp

highbetter-auth@1.4.21GHSA-9h47-pqcx-hjr4

Better Auth has insecure cryptographic defaults in oidcProvider: alg=none advertised and plain PKCE accepted by default

Depend on this server? Get alerted when its CVEs change.Watch this server free →
// environment variables
To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.
🔐 secretBETTER_AUTH_SECRET
configLOG_LEVEL
🔐 secretOPENAI_API_KEY
configORIGIN
Deployment configuration, supplied by whoever hosts the server. Users are not asked for these.
deployDATABASE_URL
// quality suggestions

Dependencies

57 runtime dependencies (8 dev), 3 flagged: @playwright/test, @vitest/browser-playwright, playwright

Tool annotations

No tools have read-only/destructive annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

60/60 tools missing one or more hints — container_inspect (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); container_logs (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); container_stats (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +57 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

Tool test coverage

Only 5/60 tools referenced in tests (8%)

Write tests that reference each tool by name so every tool has at least one test.

Production dependencies are patched

1 critical, 8 high severity in production deps — better-auth@1.4.21 (critical), better-auth@1.4.21 (high)

Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.

// embed badge in your README
[![M8ven Verified](https://m8ven.ai/badge/mcp/notoofly/taru?variant=verified)](https://m8ven.ai/mcp/notoofly/taru)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: c8d47fbd226e8de1aa938496663c92cbd42883c8
code hash: ae7166398d63de76f81f400f0466f66c49ef8814f5bee30d53753b0e361a7ba9
view raw JSON →
Check MCPs from inside your assistant
Tool Check · MCP

Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.

https://m8ven.ai/api/mcp/tool-check
check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern
How to add it →Free · no account needed · works in any MCP client