dacixSAFE
Remote MCP server for dacix.store — the store where AI agents shop. 19 tools: buy agent templates, web search & crawl, SEO audit, Romanian company data, city info.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Remote MCP server for dacix.store — a machine-first marketplace where AI agents buy agent templates and pay-per-call data services, with Stripe checkout and automatic fulfillment.
- Endpoint:
https://dacix.store/mcp(streamable HTTP, no auth needed to connect) - Registry: published in the official MCP registry as
store.dacix/store - Docs: OpenAPI · llms.txt · agents.json
Configuration
Add DACIX to any MCP client that supports streamable HTTP (Claude Desktop, Cursor, Windsurf, ...):
{
"mcpServers": {
"dacix": {
"type": "http",
"url": "https://dacix.store/mcp"
}
}
}Claude Code one-liner:
claude mcp add --transport http dacix https://dacix.store/mcp
No connection parameters needed — your agent creates its own account with the store_register tool and receives an API key plus 25 free credits.
Tools
- store_catalog: List everything for sale at dacix.store — agent templates (portable JSON agent definitions) and API credit packs. No auth needed.
- store_register: Create a DACIX account and get an API key (
dacix_sk_...) plus 25 free trial credits. - store_account: Check your account — credit balance and owned templates.
- store_buy: Buy a product — returns a Stripe checkout URL; fulfillment is automatic after payment.
- store_order_status: Check an order's status after payment (pending → paid).
- store_download_template: Download a purchased agent template (full JSON: system prompt, tools, schemas).
- web_crawl: Fetch any public web page server-side and get clean readable text back. 5 credits.
- web_search: Search the web via DuckDuckGo — structured results with titles, URLs, and snippets. 5 credits.
- web_fetch: Fetch a page w
51279f79990aOBSERVED · 2026-10-14Trust audit
SAFEgrade B · trust 87/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | NA |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (3)
streamable-http
Gates applied: no_behavioural_pass, no_license.
51279f79990afull audit observations/trust-audit/mcp-server/ionasrobert__dacix-mcp.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-14 | 51279f79990a | SAFE | B | 87 | first audit |
Questions
What is the dacix MCP server?
Remote MCP server for dacix.store — the store where AI agents shop. 19 tools: buy agent templates, web search & crawl, SEO audit, Romanian company data, city info.
Is dacix safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (87/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does dacix need?
No credential environment variables were found in its source, so it appears to need none.
How does dacix run?
It speaks streamable-http, so it runs as a service you connect to over the network.
How current is this page?
The grade is for one exact copy of the source (51279f79990a), read on 2026-10-14. The repository is watched and re-audited when it changes.