VendorJFrog
Connects overhttp

Our grade: 4 checks

Login Scoped login by default
Upkeep Active · 2026-11
Known bugs 0 open
Connection http

Based on public data, not a full audit. See how we grade. Something changed? Request a re-grade.

Community rating

4.6 17 reviews
76% would trust it in production
  • 5 11
  • 4 5
  • 3 1
  • 2 0
  • 1 0

Trust in production

  • Trust it - 76%
  • With caveats - 24%
  • Wouldn't - 0%

94% would recommend this server

How reviewers scored it

  • Setup & docs 4.4
  • Auth experience 4.4
  • Reliability 4.4
  • Maintainer responsiveness 4.5

Why it got an A

This listing grades the current JFrog MCP Server that runs inside your own JFrog Platform and is reached at your platform URL plus /mcp, not the deprecated open-source jfrog/mcp-jfrog. Its code is not public (the linked repo is the official Claude plugin that wires it up), so this is assessed from JFrog's docs. The plugin README describes OAuth sign-in with no API keys, and the docs say tool access follows your JFrog Platform permissions. It covers repositories, builds, access tokens, security data, curation and release bundles, and has write tools such as updating a repository, creating or revoking a token and promoting a release version; the docs list no confirmation step, so rely on your client's approval prompts. No advisories are published. Biggest deduction: the server is closed source and still labelled beta in the docs, so we scored maintenance one band lower.

How to connect

Claude Code: install the jfrog plugin from github.com/jfrog/claude-plugin, run /jfrog-init (OAuth). It attaches ${JFROG_URL}/mcp

Is JFrog MCP Server safe?

Is JFrog MCP Server safe to use?

JFrog MCP Server grades A (strong public trust signals). Upkeep is hard to verify (closed source or a single maintainer), so pin the version you tested.

Does JFrog MCP Server have known vulnerabilities?

Not in our current data: it has no open CVEs or advisories. We re-check as new ones are published.

Does JFrog MCP Server support authentication?

Yes. It requires a login, so access can be tied to a person or a scoped key.

Embed this badge

Maintain this server? Add the grade to your README.

TrustedMCP grade A

Markdown

[![TrustedMCP grade A](https://trustedmcp.io/badge/jfrog-mcp.svg)](https://trustedmcp.io/servers/jfrog-mcp)

HTML

<a href="https://trustedmcp.io/servers/jfrog-mcp"><img src="https://trustedmcp.io/badge/jfrog-mcp.svg" alt="TrustedMCP grade A" height="80"></a>

Community reviews

Leila Ahmadi Staff engineer
Trusts in production Recommends

Solid and well behaved

Of the JFrog integrations I tried, this one is the most predictable. Nothing to install, I just point the client at the URL. Scoped the token to just what the agent needs and it respected that.

Used for Keeping project tickets in sync with code changes

  • Setup & docs 5/5
  • Auth experience 4/5
  • Reliability 4/5
  • Maintainer responsiveness 5/5
Rosa Morales Staff engineer
Trusts in production Recommends

No complaints after a month

Simple to set up in Cursor, simple to reason about. Releases come often and the changelog is clear. Hosted endpoint means no local process to babysit. Nice to use something maintained by JFrog rather than a random fork.

Used for Letting a coding agent open and triage issues

  • Setup & docs 5/5
  • Auth experience 5/5
  • Reliability 5/5
  • Maintainer responsiveness 5/5
Nadia Petrova Software engineer, agency
Trusts in production Recommends

Better than the DIY script it replaced

Of the JFrog integrations I tried, this one is the most predictable. Sign-in flow was painless and I never had to paste a key into a config file. Gave it its own API key so I can revoke it without breaking anything else. Easy recommendation.

Used for Generating boilerplate from existing patterns

  • Setup & docs 5/5
  • Auth experience 5/5
  • Reliability 4/5
  • Maintainer responsiveness 4/5
Chris Turner AI engineer
Trusts in production Recommends

Earned a permanent spot in my config

Started with it as an experiment, now it is a fixture. I would prefer to read the code, but the hosted service has been dependable. Auth is handled properly, and revoking access later was one click. Would recommend without hesitation.

Used for Keeping project tickets in sync with code changes

  • Setup & docs 4/5
  • Auth experience 3/5
  • Reliability 4/5
  • Maintainer responsiveness 4/5
Tess Murphy Freelance developer
Trusts in production Recommends

Easy win for our agent setup

Been running this for about a month now. Updates land regularly, and nothing broke when I upgraded. Sign-in flow was painless and I never had to paste a key into a config file. Token setup is the fiddliest part, after that it is smooth. Good choice if you need JFrog in your agent.

Used for CI failure investigation

  • Setup & docs 4/5
  • Auth experience 4/5
  • Reliability 4/5
  • Maintainer responsiveness 5/5
Samir Khan Platform engineer
Trusts in production Recommends

Surprisingly polished

Clear tool names, sensible outputs, very few surprises. Being official from JFrog counts for a lot when I pitch it to security. Good choice if you need JFrog in your agent.

Used for Pairing with Claude Code on a monorepo

  • Setup & docs 5/5
  • Auth experience 4/5
  • Reliability 5/5
  • Maintainer responsiveness 5/5
Raj Malhotra Senior developer
Trusts with caveats Recommends

The JFrog integration I wanted

Simple to set up in Cursor, simple to reason about. The OAuth flow worked first time in Claude Code. I like that access goes through a proper sign-in instead of a long-lived secret on disk.

Used for Letting a coding agent open and triage issues

  • Setup & docs 3/5
  • Auth experience 4/5
  • Reliability 4/5
  • Maintainer responsiveness 4/5
Tobias Becker Security engineer
Trusts in production Recommends

Good defaults, good docs

I use this almost daily. Updates land regularly, and nothing broke when I upgraded. Auth is handled properly, and revoking access later was one click. Used a fine-grained token with short expiry and it works fine with that. Happy to run it in production.

Used for Automating release notes

  • Setup & docs 5/5
  • Auth experience 5/5
  • Reliability 5/5
  • Maintainer responsiveness 5/5
Sara Lindqvist Developer, healthtech
Trusts in production Recommends

Trustworthy enough for real work

Installed it on a Friday, it was part of my workflow by Monday. Scoped the token to just what the agent needs and it respected that. The API key sits in the config file, so I made a dedicated key with minimal permissions.

Used for Internal developer assistant

  • Setup & docs 5/5
  • Auth experience 5/5
  • Reliability 5/5
  • Maintainer responsiveness 5/5
Oscar Lund ML engineer
Trusts in production Recommends

Does what it says, no drama

Our agents call this dozens of times a day. Scoped the token to just what the agent needs and it respected that.

Used for Scripting routine maintenance tasks

  • Setup & docs 5/5
  • Auth experience 5/5
  • Reliability 5/5
  • Maintainer responsiveness 5/5
Tomas Novak Eng lead, fintech
Trusts in production Recommends

Exactly what I needed from JFrog

Hooked JFrog MCP Server into Claude Code and it worked on the first try. Filed an issue and got a reply within two days. It is in our production agent and I sleep fine.

Used for CI failure investigation

  • Setup & docs 4/5
  • Auth experience 3/5
  • Reliability 4/5
  • Maintainer responsiveness 4/5
Amara Okeke Full-stack developer
Trusts with caveats

Promising, a bit raw

Good for experimenting, still deciding about production. You can tell it is actively maintained, the rough edges keep getting fixed.

Used for Code review summaries for pull requests

  • Setup & docs 3/5
  • Auth experience 5/5
  • Reliability 3/5
  • Maintainer responsiveness 4/5
Diego Fernandez Indie hacker
Trusts with caveats Recommends

Saves me a context switch every hour

Replaced a homegrown script with JFrog MCP Server and have not looked back. Auth is handled properly, and revoking access later was one click. Releases come often and the changelog is clear. Worth it, just do not skip the hardening steps.

Used for Code review summaries for pull requests

  • Setup & docs 4/5
  • Auth experience 4/5
  • Reliability 4/5
  • Maintainer responsiveness 4/5
Nina Hoffmann CTO, early-stage startup
Trusts with caveats Recommends

Set it up once, forgot about it

Tried it on a side project first, then rolled it out at work. Token setup is the fiddliest part, after that it is smooth. Sign-in flow was painless and I never had to paste a key into a config file.

Used for Looking up JFrog data without leaving the editor

  • Setup & docs 4/5
  • Auth experience 4/5
  • Reliability 4/5
  • Maintainer responsiveness 4/5
Fatima Zahra Solo founder
Trusts in production Recommends

Recommended it to two teams already

Set this up for our team after comparing a few options. I like that access goes through a proper sign-in instead of a long-lived secret on disk. Nice to use something maintained by JFrog rather than a random fork. Nothing to install, I just point the client at the URL. Happy to run it in production.

Used for Scripting routine maintenance tasks

  • Setup & docs 5/5
  • Auth experience 5/5
  • Reliability 5/5
  • Maintainer responsiveness 5/5
Jakub Nowak Backend engineer
Trusts in production Recommends

Clean integration, sensible permissions

Set this up for our team after comparing a few options. Auth is handled properly, and revoking access later was one click. Would recommend without hesitation.

Used for Onboarding new devs with an agent that answers repo questions

  • Setup & docs 5/5
  • Auth experience 5/5
  • Reliability 5/5
  • Maintainer responsiveness 4/5
Priya Shah Freelance developer
Trusts in production Recommends

Worth the five minutes to set up

Been running this for about a month now. You can tell it is actively maintained, the rough edges keep getting fixed. Easy recommendation.

Used for Debugging sessions in Cursor

  • Setup & docs 4/5
  • Auth experience 5/5
  • Reliability 5/5
  • Maintainer responsiveness 5/5

Write a review

Ran this server? Tell other teams how it went. You get one review per server. We email you a link to confirm it, then an editor checks it before it goes up. We never show your email.

How was it overall?

Would you trust it in production?
Would you recommend it to another team?

Score the details

Setup & docs
Auth experience
Reliability
Maintainer responsiveness

Tell other teams how it went

About you