MCP.Market

Rlhf Feedback Loop MCP server

by IgorGanapolsky·io.github.IgorGanapolsky/rlhf-feedback-loop·v0.6.13·27 stars
No reviews yet

RLHF feedback loop for AI agents. Capture signals, promote memories, block mistakes, export DPO.

B74/100grade B
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
B74/100

full report

Adoption
Growing

27 stars82 downloads/wk

Reviews

Write one

Nobody has reviewed Rlhf Feedback Loop yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Rlhf Feedback Loop tools (11)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • capture_feedback

    Capture an up/down signal plus one line of why. Vague feedback is logged, then returned with a clarification prompt instead of memory promotion.

  • construct_context_pack

    Construct a bounded context pack from contextfs

  • context_provenance

    Get recent context/provenance events

  • evaluate_context_pack

    Record evaluation outcome for a context pack

  • export_dpo_pairs

    Export DPO preference pairs from local memory log

  • feedback_stats

    Get feedback stats and recommendations

  • feedback_summary

    Get summary of recent feedback

  • list_intents

    List available intent plans and whether each requires human approval in the active profile

  • plan_intent

    Generate an intent execution plan with policy checkpoints

  • prevention_rules

    Generate prevention rules from repeated mistake patterns

  • recall

    Recall relevant past feedback, memories, and prevention rules for the current task. Call this at the start of any task to inject past learnings into the conversation.

Public scan report

scanner v0.1.10 · 2026-09-28 · same rubric, same numbers if you re-run it

1 high
  • Code scan15 source files scanned13/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 4 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10

Findings (1)

  • highShell command built from a string (injection risk)exec.shell-concat
    bin/cli.js: … } function whichExists(cmd) { try { execSync(`which ${cmd}`, { stdio: 'pipe' }); return true; …
Overall 74/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Rlhf Feedback Loop compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
74/100
higher than 40% of 48,255 servers
Tools
11
the typical server has 7
Tools that change things
0%
typical: 0%. Fewer write tools means less an agent can break
GitHub stars
27
more than 91% of 28,688 servers
Downloads a week
82
more than 58% of 12,191 servers with a package

What its tools let an agent do: 10 read · 1 run or deploy

Install Rlhf Feedback Loop in Claude Code, Cursor or VS Code

Runs npx -y rlhf-feedback-loop on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add rlhf-feedback-loop -- npx -y rlhf-feedback-loop
Add to Cursor

What the publisher says

From the Rlhf Feedback Loop repository's README, as published. We do not edit it. Read it on GitHub

ThumbGate 👍 👎

ThumbGate is the self-improving pre-action firewall for AI coding agents AI coding agents repeat mistakes — and one wrong tool call can wipe a directory, leak a key, or push broken code.

What it does

ThumbGate is the local-first Pre-Action Checks engine for AI coding agents. It runs in the PreToolUse hook to evaluate the proposed tool call before execution — so costly mistakes can be caught before they happen.

ThumbGate GitHub star growth is measured with GitHub's privacy-safe GET /repos/{owner}/{repo}/stargazers/history endpoint (weekly counts, no stargazer identities). Run npm run stars:history -- --fixture tests/fixtures/github-star-history.json --json for the local proof. Stars are not npm installs and not revenue. The live GitHub Marketplace Action is ThumbGate Agent Governance (uses: IgorGanapolsky/ThumbGate@v1).

Usage over star count. Evaluate ThumbGate from the install path and live usage badges above (npx thumbgate init, Marketplace uses:, npm weekly downloads, GitHub clones), not from whether the repo has twenty stars or twenty thousand. No pitch deck is required. We do not farm GitHub profile badges (no YOLO-merge of protected main, no 5-minute Issue close theater, no fake Co-authored-by). Galaxy Brain needs real accepted answers in Discussions Q&A. npm run github:achievements -- --fixture tests/fixtures/github-achievements.json --json inventories what is already earned vs what we refuse to farm.

Who it's for

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Rlhf Feedback Loop: common questions

Is Rlhf Feedback Loop MCP server safe?
Mostly: it is graded B (74/100). Read the Rlhf Feedback Loop safety report
How do I install Rlhf Feedback Loop?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Rlhf Feedback Loop need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Rlhf Feedback Loop maintained?
The last commit was 42 days ago (2026-09-23). The latest release is v0.6.13.
How does Rlhf Feedback Loop compare with other MCP servers?
safety score 74/100 (higher than 40% of 48,255 servers); tools 11 (the typical server has 7); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

More from IgorGanapolsky →