SoloFlow

SoloFlow

Grok Agent Store

Category
Visit Server

README

Grok Agent Store

Agent-only vertical skill marketplace powered exclusively by the xAI Grok API.

Buyer agents discover skills, register for credits, invoke Grok-backed tools, and receive signed receipts. Humans set the operator secrets; agents do the commerce.

🤖 Agent: start here

Master index: https://grok-agent-store.manhatton31.workers.dev/discovery.json

MCP:     https://grok-agent-store.manhatton31.workers.dev/mcp
Skills:  https://grok-agent-store.manhatton31.workers.dev/skills.json
Card:    https://grok-agent-store.manhatton31.workers.dev/.well-known/agent.json
llms:    https://grok-agent-store.manhatton31.workers.dev/llms.txt
server:  https://grok-agent-store.manhatton31.workers.dev/server.json

First call:

curl -s https://grok-agent-store.manhatton31.workers.dev/v1/invoke \
  -H "content-type: application/json" \
  -d '{"skill_id":"register_agent","input":{"name":"my-buyer"}}'

What agents get

Endpoint Purpose
GET /discovery.json Master discovery index
GET /skills.json Skill graph (prices, schemas)
GET /.well-known/agent.json A2A-style agent card
GET /server.json Official MCP Registry format
GET /mcp.json Client config snippet
GET /openapi.json OpenAPI 3.1
GET /llms.txt / /ai.txt / /AGENTS.md Machine instructions
GET /robots.txt / /sitemap.xml Crawler surfaces
POST /v1/invoke REST skill invoke
POST /mcp MCP Streamable HTTP

Skills (MVP)

Skill Credits Auth
list_skills / get_skill / quote 0 No
register_agent 0 (+ bonus) No
balance 0 Yes
skill_match 5 Yes
agent_brief 10 Yes
structured_extract 15 Yes
code_review 25 Yes

Quickstart (local)

cd grok-agent-store
npm install
# put your key in .dev.vars (gitignored pattern below)
npx wrangler dev

.dev.vars:

XAI_API_KEY=xai-...
PUBLIC_BASE_URL=http://127.0.0.1:8787
GROK_MODEL=grok-4
SIGNUP_BONUS_CREDITS=100

Agent flow

# 1) Register
curl -s http://127.0.0.1:8787/v1/invoke \
  -H "content-type: application/json" \
  -d '{"skill_id":"register_agent","input":{"name":"demo-buyer"}}'

# 2) Use a paid skill (paste api_key)
curl -s http://127.0.0.1:8787/v1/invoke \
  -H "content-type: application/json" \
  -H "Authorization: Bearer gas_..." \
  -d '{"skill_id":"agent_brief","input":{"goal":"Launch an agent marketplace"}}'

MCP clients

Point Streamable HTTP MCP at https://<your-host>/mcp and send:

Authorization: Bearer gas_...

Live deploy (current)

Public base: https://grok-agent-store.manhatton31.workers.dev

Surface URL
Skill graph https://grok-agent-store.manhatton31.workers.dev/skills.json
Agent card https://grok-agent-store.manhatton31.workers.dev/.well-known/agent.json
OpenAPI https://grok-agent-store.manhatton31.workers.dev/openapi.json
llms.txt https://grok-agent-store.manhatton31.workers.dev/llms.txt
REST invoke POST https://grok-agent-store.manhatton31.workers.dev/v1/invoke
MCP https://grok-agent-store.manhatton31.workers.dev/mcp

This was launched with wrangler deploy --temporary (preview account). Claim the account within 60 minutes or the deploy can expire:

https://dash.cloudflare.com/claim-preview?claimToken=6ByjulVj7W-mC6i6KWid0OqyEomj8Wt5lZoUDSbWI1s

Required operator step: Grok secret

Paid skills need your xAI key:

npx wrangler secret put XAI_API_KEY --temporary
# paste key from https://console.x.ai

Until this is set, /health shows "grok_configured": false and Grok tools return an error.

Deploy (Cloudflare Workers, permanent)

npx wrangler login
npx wrangler kv namespace create STORE
# paste id into wrangler.jsonc
npx wrangler secret put XAI_API_KEY
# set PUBLIC_BASE_URL in wrangler.jsonc to your workers.dev URL
npx wrangler deploy

After deploy, agents find you via:

  • https://<worker>.workers.dev/skills.json
  • https://<worker>.workers.dev/.well-known/agent.json
  • https://<worker>.workers.dev/llms.txt
  • MCP: https://<worker>.workers.dev/mcp

Optional: custom domain

npx wrangler domains add your-domain.com

Update PUBLIC_BASE_URL to the custom domain.

Architecture

  • Code — auth, metering, discovery, receipts (deterministic, free)
  • Grok — only LLM for paid skills (api.x.ai)
  • KV — agent balances + receipts
  • Durable Object — MCP session state (GrokAgentStore)

Roadmap

  1. Vertical MCP + credits + discovery (this MVP)
  2. x402 pay-per-call without prepaid accounts
  3. Job marketplace (hire multi-step workflows with escrow)
  4. Seller-listed third-party skills

License

MIT

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured