Server data from the Official MCP Registry
MCP-first control plane for ProAgentStore agents and private instances.
MCP-first control plane for ProAgentStore agents and private instances.
Remote endpoints: streamable-http: https://mcp.proagentstore.online/mcp
This MCP server for ProAgentStore has reasonable authentication controls and proper token handling via environment variables, but exhibits moderate security concerns. The server makes extensive external API calls (GitHub, Cloudflare AI, internal APIs) with proper auth token scoping, but several code quality issues and input validation gaps are present. The primary concerns are unvalidated file path handling in GitHub operations, broad exception handling without logging, and potential information disclosure in error messages. Permissions are appropriate for the stated purpose of managing AI agents. Supply chain analysis found 7 known vulnerabilities in dependencies (1 critical, 2 high severity).
5 files analyzed · 15 issues found
Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.
This plugin requests these system permissions. Most are normal for its category.
Available as Local & Remote
This plugin can run on your machine or connect to a hosted endpoint. during install.
From the project's GitHub README.
Marketplace for server-powered AI agents. Creators build agent templates, clients subscribe and run them on their own data.
Store: https://proagentstore.online API: https://api.proagentstore.online MCP: https://mcp.proagentstore.online/mcp Console: https://proagentstore.online/console/ GitHub: https://github.com/ProAgentStore Free pair: https://freeagentstore.online
platform/
├── packages/sdk/ Internal TypeScript SDK for agents
├── packages/cli/ @proagentstore/cli — init, check, publish, local runner
├── packages/browser-runner/ Internal Playwright runner bundled into the CLI
├── workers/api/ Hono API worker (auth, agents, instances, keys, analytics)
├── workers/host/ Marketing site + console + widget
├── workers/mcp/ MCP server for Codex, Claude Code, Cursor, and VS Code
├── store/ Source HTML for all pages
├── skills/ Open Agent Skills source files
├── plugins/ Codex and Claude plugin wrappers
├── agents/ 5 flagship agents (site-monitor, lead-qualifier, etc.)
└── templates/ Agent scaffolding (worker, cron, api)
| Type | Template | What it does |
|---|---|---|
| Agent | worker | Full AI: conversation, memory, knowledge base, 10 tools, Workers AI |
| Worker | cron | Scheduled tasks: daily digests, monitoring, batch processing |
| Tool | api | Stateless endpoint: transform, generate, analyze |
# Try any published agent — no sign-up needed
curl -X POST https://api.proagentstore.online/v1/public/agents/chatbot/try \
-H "Content-Type: application/json" \
-d '{"message":"Hello!"}'
npx @proagentstore/cli init my-agent --template worker
cd my-agent
pnpm install && pnpm dev
npx @proagentstore/cli publish
import { initPro } from '@proagentstore/sdk'
const agent = initPro({ agentId: 'your-id', token: 'your-token' })
const { response } = await agent.chat('Hello!')
<script src="https://proagentstore.online/widget.js"
data-agent="chatbot" data-theme="dark"></script>
codex mcp add proagentstore --url https://mcp.proagentstore.online/mcp
codex mcp list
# If the server shows "Not logged in":
codex mcp login proagentstore
claude mcp add --transport http proagentstore https://mcp.proagentstore.online/mcp
claude mcp list
npx mcp-remote https://mcp.proagentstore.online/mcp
MCP has two runtime modes:
chat_with_agent calls the public trial endpoint. Use it for discovery and smoke tests.subscribe_agent creates your private instance, then chat_with_instance runs that instance with your own state, knowledge, and caller-provided AI credentials.Typical user run:
list_agents -> subscribe_agent -> my_instances -> add_instance_knowledge -> chat_with_instance
The expected response when user-owned AI credentials are missing is:
Add your Cloudflare Workers AI account ID and API token before running this agent.
That means the instance runtime path is working and correctly refusing to bill the platform AI account. See MCP Instance Runtime for the full tool map, live test record, and OAuth troubleshooting.
The full MCP-first developer surface is documented at:
Browser-capable agents use PAGS as the control-plane brain and a local runner as the tool executor. Users install one public package, @proagentstore/cli; the Playwright runner is bundled into it.
npm install -g @proagentstore/cli
pags runner start --port 49171 --token "$PAGS_RUNNER_TOKEN" --instance-id "$PAGS_INSTANCE_ID"
pags runner status --token "$PAGS_RUNNER_TOKEN" --instance-id "$PAGS_INSTANCE_ID"
pags runner task --type echo --input '{"ok":true}' --token "$PAGS_RUNNER_TOKEN" --instance-id "$PAGS_INSTANCE_ID"
When exposing the runner through a tunnel, start it with a token and instance binding, then register only the tunnel URL plus token with PAGS. Runtime registration is instance-scoped: PAGS stores the endpoint and encrypted runner token, then MCP/API proxy task calls to the runner with X-PAGS-Instance-Id.
pags runner register "$PAGS_INSTANCE_ID" \
--endpoint-url "$PAGS_RUNNER_ENDPOINT" \
--runner-token "$PAGS_RUNNER_TOKEN" \
--pags-token "$PAGS_TOKEN" \
--probe
pags runner runtime "$PAGS_INSTANCE_ID" --pags-token "$PAGS_TOKEN" --probe
pags runner run "$PAGS_INSTANCE_ID" --type echo --input '{"ok":true}' --pags-token "$PAGS_TOKEN"
subscribe_agent -> register_instance_runtime -> instance_runtime_status(probe: true) -> run_instance_task -> approve_instance_task -> instance_task_events
The browser runtime MCP tools are register_instance_runtime, instance_runtime_status, unregister_instance_runtime, run_instance_task, approve_instance_task, cancel_instance_task, and instance_task_events.
ProAgentStore publishes skills through platform-specific plugin marketplaces so users can find them from both Codex and Claude Code.
Codex:
codex plugin marketplace add ProAgentStore/platform
Claude Code:
/plugin marketplace add ProAgentStore/platform
/plugin install proagentstore@proagentstore
/reload-plugins
See Skill Publishing for the publishing layout, marketplace files, and dual Codex/Claude release checklist.
Public discovery pages:
| Agent | Type | Description |
|---|---|---|
| site-monitor | Worker | Hourly URL change detection + webhook alerts |
| lead-qualifier | Agent | AI lead scoring from webhook submissions |
| content-pipeline | Worker | Daily AI content generation to R2 |
| competitor-intel | Worker | Daily competitor tracking + AI briefings |
| support-escalator | Agent | Ticket triage + auto-response + daily summary |
| Store | URL | Product |
|---|---|---|
| FreeAppStore | freeappstore.online | PWA apps |
| FreeGameStore | freegamestore.online | Browser games |
| FreeWebStore | freewebstore.online | AI-built sites |
| FreeAgentStore | freeagentstore.online | Browser AI tools |
| ProAppStore | proappstore.online | Paid apps |
| ProAgentStore | proagentstore.online | Server AI agents |
MIT
Be the first to review this server!
by Modelcontextprotocol · Developer Tools
Web content fetching and conversion for efficient LLM usage
by Toleno · Developer Tools
Toleno Network MCP Server — Manage your Toleno mining account with Claude AI using natural language.
by mcp-marketplace · Developer Tools
Create, build, and publish Python MCP servers to PyPI — conversationally.