MCP.Market

ShareGrokBots MCP server

online · 100% uptime
by legacyinmotion·io.github.legacyinmotion/sharegrokbots·v1.0.0

Search shared Grok Bots by what they do. Credit the creator. No prompt text.

B75/100grade B
What users say
No reviews yet
Be the first
Safety scan
B75/100

full report

Adoption
New

0 stars

Reviews

Write one

Nobody has reviewed ShareGrokBots yet.

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

ShareGrokBots tools (7, 1 write)

write = sends, deletes, buys or posts
  • get_botFree

    Fetch one public listing by slug. Credits the creator X post and carries the listing's `votes` and `adds`. ShareGrokBots does not test, score, or review the bots it lists. Never returns prompt text.

  • latestFree

    Newest public listings, newest first. Each carries its `votes` and `adds`. ShareGrokBots does not test, score, or review the bots it lists.

  • list_categoriesFree

    List the categories used to file listings, grouped as market or trades. Old slugs appear under aliases.

  • most_votedFree

    Listings the community voted up, most votes first. Votes come from signed-in members, one per person per bot.

  • my_listingsFree

    List the member's submissions with status, votes, and adds. ShareGrokBots does not test, score, or review the bots it lists. Prompt text is never returned.

  • search_botsFree

    Search public ShareGrokBots listings by text and optional category. Returns name, credit, live bot link, and the community signal: `votes` from signed-in members and `adds` from people who opened the bot through its listing. ShareGrokBots does not test, score, or review the bots it lists. Never returns prompt text.

  • submit_botwrite actionFree

    Submit a public Grok bot page to the directory. Requires the creator X handle and the source X post URL. ShareGrokBots does not test, score, or review the bots it lists. Prompt text is never stored or returned.

Public scan report

scanner v0.1.10 · 2026-10-30 · same rubric, same numbers if you re-run it

1 high
  • –Code scanremote-only server, no package to scann/a
  • Live reliabilityremote reachable in 713ms20/20
  • Tool poisoning7 tool descriptions checked15/15
  • Auth qualityopen endpoint exposes 1 write-action tools with no auth3/15
  • Maintenancelast push 60 days ago12/15
  • Maintainer identityregistry namespace matches repository owner6/10

Findings (1)

  • highWrite-action tools reachable without authenticationauth.open-write
Overall 75/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How ShareGrokBots compares

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

Safety score
75/100
higher than 45% of 4,461 AI and agents servers
Tools
7
the typical AI and agents server has 6
Tools that change things
14%
typical: 0%. Fewer write tools means less an agent can break
Uptime
100%
of our recent checks; the typical remote AI and agents server answers 100%
Response time
126 ms
faster than 80% of 2,334 AI and agents servers

What its tools let an agent do: 6 read · 1 change

Install ShareGrokBots in Claude Code, Cursor or VS Code

claude mcp add --transport http sharegrokbots https://mcp.sharegrokbots.com/mcp
Add to Cursor

What the publisher says

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

ShareGrokBots examples

ShareGrokBots is a public directory of Grok Bot builds, each credited to the X creator who shared it. Listings are run on a standard task and marked verified or not yet verified; the site does not store or show prompt text.

This repo is working code against the public surfaces: JSON API, feeds, and the MCP host. Nothing here talks to a private product repo.

Public API (v1, additive-only)

v1 is additive-only. New fields and endpoints may appear; existing fields are never removed, renamed, or repurposed within v1. Ignore fields you do not recognize. Follow a next cursor when a response includes one. Breaking changes ship at /api/v2 and are announced on status with at least 90 days of deprecation notice.

GET on the MCP host returns 405. POST with JSON-RPC is the protocol. /llms.txt is coming.

Captured responses: examples/curl.md. Cursor pagination of verified rows: examples/node/list-verified.mjs.

MCP one-liner

grok mcp add --transport http sharegrokbots https://mcp.sharegrokbots.com/mcp

The host exposes searchbots, getbot, listcategories, latest, and verifiedrecent. A Node client is in examples/node/mcp-client.mjs. Wiring the same host into a Grok Bot is in examples/grok-bot/. Browser WebMCP is noted in examples/webmcp/.

Cursor / Grok Bot plugin

This repo is the Cursor Marketplace / Grok Bot Settings plugin for the same host. Manifest: .cursor-plugin/plugin.json. MCP config: mcp.json.

grok mcp add --transport http sharegrokbots https://mcp.sharegrokbots.com/mcp

Five read-only tools:

  • search_bots: Search public ShareGrokBots listings by text and optional category. Returns name, credit, live bot link, our verdict, and verified. verified is authoritative; verdict is a display object and may say Not yet verified. Never returns prompt text.
  • get_bot: Fetch one public listing by slug. Credits the creator X post. verified is authoritative; verdict is a display object and may say Not yet verified. Never returns prompt text.
  • list_categories: List the categories used to file listings, grouped as market or trades. Old slugs appear under aliases.
  • latest: Newest public listings, verified first then pending, newest first within each group. verified is authoritative; verdict is a display object and may say Not yet verified.
  • verified_recent: Listings verified within the last N days, newest verdict first.

Connect: https://sharegrokbots.com/connect

Not affiliated with xAI. Grok is a trademark of xAI.

Credit law

If you reuse listing data, credit the creator's @handle and source post, link the live x.ai/bot URL, and never republish prompts. Verdicts are ShareGrokBots'. Unverified listings are third-party links, not an endorsement.

Run

npm install
npm run smoke

npm run smoke hits only public endpoints.

License

MIT. Copyright 2026 LegacyForgeAI LLC.

Not affiliated with xAI. Grok is a trademark of xAI.

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

ShareGrokBots: common questions

Is ShareGrokBots MCP server safe?
Mostly: it is graded B (75/100). Read the ShareGrokBots safety report
How do I install ShareGrokBots?
It runs remotely at mcp.sharegrokbots.com. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
Does ShareGrokBots need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is ShareGrokBots maintained?
The last commit was 67 days ago (2026-08-30). The latest release is v1.0.0.
Is ShareGrokBots up?
100% of our last 28 checks got an answer. We check remote servers about four times a day.
What can I use instead of ShareGrokBots?
Servers from other publishers that do the same job: PaperBanana MCP server, Agent-Native Analytics MCP server and Image MCP server.
How does ShareGrokBots compare with other AI and agents MCP servers?
safety score 75/100 (higher than 45% of 4,461 AI and agents servers); tools 7 (the typical AI and agents server has 6); tools that change things 14% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to ShareGrokBots

Same job from other publishers: the closest match first, then the best rated.

  • PaperBanana
    Generate academic diagrams and statistical plots from text using multi-agent AI.
    A
  • Agent-Native Analytics
    Agent-Native Amplitude/Mixpanel - connect data sources, prompt for charts
    A
  • Image
    AI image generation and editing with prompt optimization and quality presets
    B
  • Mnemoverse Memory
    Hosted agent memory that learns from outcomes, with shared rooms. No key: mcp.mnemoverse.com/mcp
    A
  • llmtrim
    MCP server and proxy that compresses LLM prompts, tool output, and replies to cut token cost.
    A