MCP server for minia2a.uk — discover and call 1,600+ x402 pay-per-call APIs with USDC payments.
Nothing to run from here
SEF e-fakture (Srbija) is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
96/100
trust score
14
tools declared
local
runs on your machine
—
calls last 7d
What it does
Serbian SEF e-invoicing from Claude: drafts, approval before sending, status, cancel and storno.
Quickstart
Install it the way its author documents:
1. Download sef-mcp.mcpb and open it in Claude Desktop or another client that installs MCP bundles (.mcpb)
2. Its sha256 is 7e364c605b209cf5916f2c83388be03921c665f66bad8434a397f2e428b3a8fb
The full guide: https://github.com/janko-vrbnjak/sef-mcp/releases/download/v0.4.0/sef-mcp.mcpb
Publishernot claimed
JVAll 1 server
janko-vrbnjak1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts SEF e-fakture (Srbija) as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Install it the way its author documents:
1. Download sef-mcp.mcpb and open it in Claude Desktop or another client that installs MCP bundles (.mcpb)
2. Its sha256 is 7e364c605b209cf5916f2c83388be03921c665f66bad8434a397f2e428b3a8fb
The full guide: https://github.com/janko-vrbnjak/sef-mcp/releases/download/v0.4.0/sef-mcp.mcpb
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
Shows environment (demo/prod), safety switches and profile summary. Makes no network calls.
No parameter schema on file.
Creates or updates the seller (your company) in the local profile, so no JSON has to be edited by hand.
No parameter schema on file.
Adds a customer to the local profile (or replaces the one with the same id). Same preview → confirm flow as
No parameter schema on file.
Calls a harmless read-only SEF endpoint to confirm the API key and environment work.
No parameter schema on file.
Lists customers defined in the local profile (id, name, PIB, defaults).
No parameter schema on file.
Returns SEF's official list of VAT exemption reason codes (e.g. PDV-RS-33).
No parameter schema on file.
Returns SEF's list of accepted unit codes (e.g. H87 piece, HUR hour, MON month).
No parameter schema on file.
Builds a UBL 2.1 invoice locally from the profile and the given lines, stores it as a draft and returns
No parameter schema on file.
Returns a stored draft's summary, optionally with the full XML.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| draftId | string | yes | — |
| includeXml | boolean | no | — |
Uploads a previously drafted invoice to SEF. Requires the draftId and the approvalCode the user approved.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| draftId | string | yes | — |
| approvalCode | string | yes | — |
| executeValidation | boolean | no | Default false (as the SEF portal). true only on the user's explicit request; SEF says the option is not in operation yet. |
Returns a sales invoice and its status from SEF by SEF invoiceId.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| invoiceId | integer | yes | — |
Lists SEF sales invoice ids by status within a date range. For New, Draft and Mistake the range filters
| Parameter | Type | Required | Notes |
|---|---|---|---|
| status | string | yes | SEF status, e.g. New, Draft, Mistake, Sent, Approved, Rejected, Cancelled, Storno |
| dateFrom | string | yes | ISO date-time |
| dateTo | string | yes | ISO date-time |
Cancels a sales invoice on SEF. SEF allows this only for status Draft, New or Sending error;
| Parameter | Type | Required | Notes |
|---|---|---|---|
| invoiceId | integer | yes | — |
| comment | string | yes | — |
Reverses (storno) a sales invoice on SEF. SEF allows this only for status Sent, Accepted or Rejected.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| invoiceId | integer | yes | — |
| comment | string | yes | — |
| stornoNumber | string | no | — |
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install SEF e-fakture (Srbija) or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 96 / 100
Release 0.4.0 · scanned 7 Nov 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score96
Findings4 threat · 1 capability
Capabilitymoderate
Coveragesource
Verificationrepo
Surface digeste77d635847480e307489b0ad8c00326a484f625c5e8ffcbe9dfae4e2f6f90ae2
Score vectorthreat 100 → client 96
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (14 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| sef_check_setup | no tags | |
| sef_setup_company | state-write | state-write: declares readOnlyHint: false |
| sef_add_customer | state-write | state-write: declares readOnlyHint: false |
| sef_ping | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| sef_list_customers | no tags | |
| sef_list_vat_exemption_reasons | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| sef_list_unit_measures | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| sef_draft_invoice | state-write | state-write: declares readOnlyHint: false |
| sef_get_draft | no tags | |
| sef_send_invoice | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| sef_get_invoice | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| sef_list_invoice_ids | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| sef_cancel_invoice | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| sef_storno_invoice | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
flow-1
Untrusted input can drive an external action even though no sensitive source is exposed.
Supply chain and provenance
Integrityfirst-seen
Surface digeste77d635847480e30
Scanned2026-11-07
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
It installs from its repository rather than from a versioned package, so the command cannot be pinned to a release. The history below is for reading; the current release on file is 0.4.0.
0.4.0
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish SEF e-fakture (Srbija) can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.