com.einvoicegoblin/counterfoil
Registry code: cd20992fff10c0f0
Stateless MCP endpoint at POST /mcp. Protocol 2026-07-28 uses MCP-Protocol-Version, Mcp-Method, and Mcp-Name headers. Legacy initialize also works for 2025-11-25, 2025-06-18, and 2025-03-26. No session. No authentication. Tools: get_rule, search_rules, explain_error, and check_invoice. The first three return the stored statement, the plain reading, the fix, and the source URL. check_invoice reads a UBL slice and returns the terms it writes, the field-map gaps, and one stored BR-DE-15 note when buyer reference BT-10 is absent. evaluation stays false. The body is not stored. The same reading is…
- endpoint
- https://einvoicegoblin.com/mcp
- protocol
- streamable-http ·2025-06-18
- authentication
- none observed
- public key
- none — nobody has proven they own this listing · is it yours? claim it
- karma
- 0 · newcomer
- Is com.einvoicegoblin/counterfoil live?
- Yes — it answered the hub's last check (checked 2h ago). It answered 100% of checks over the last 30 days.
- Is com.einvoicegoblin/counterfoil free to use?
- Yes — the hub reached it with no key and no payment.
- What tools does com.einvoicegoblin/counterfoil have?
- 4 tools: explain_error, check_invoice, get_rule, search_rules.
- Is com.einvoicegoblin/counterfoil safe to connect?
- The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.
90 days 100%· all time 100%
last good check
of 4 tools
- unknown → live
Calls placed through this hub's router, from its own receipts. Every caller and every payer counts the same; the chain total is counted from three payers.
through this hub
successful
what callers paid
Access was read off the card rather than seen on the wire: inferred: the handshake, the tool list and a call without arguments went through with no key and no payment asked; no tool was run
Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.
explain_error unknown 2h ago
Read a stored rule named in a rule id or a validator message. Returns the stored statement, plain reading, fix, and source URL when a stored rule matches. Does not check an invoice.
{ "type": "object", "required": [ "text" ], "properties": { "text": { "type": "string", "maxLength": 8000, "minLength": 1, "description": "A rule id such as BR-01, or a validator message that quotes one." } }, "additionalProperties": false }arguments 15 linescheck_invoice unknown 2h ago
Read a UBL Invoice XML slice of at most 60000 characters. Returns the business terms that slice writes, the field-map gaps, and one stored note when BR-DE-15 finds no non-empty buyer reference (BT-10). evaluation is false: no Schematron runs. The result does not say the invoice passed. The XML is not stored. A larger file is the raw body of POST /v1/invoices/check, up to 1048576 bytes.
{ "type": "object", "required": [ "xml" ], "properties": { "xml": { "type": "string", "maxLength": 60000, "description": "UBL Invoice XML. At most 60000 characters." } }, "additionalProperties": false }arguments 14 linesget_rule unknown never probed
Read one stored EU e-invoice rule by id. Returns the stored statement, context, test, plain reading, fix, and source URL. Does not check an invoice.
{ "type": "object", "required": [ "id" ], "properties": { "id": { "type": "string", "pattern": "^[A-Za-z0-9-]+$", "maxLength": 40, "description": "A stored rule id, such as BR-01 or BR-IC-05." } }, "additionalProperties": false }arguments 15 linessearch_rules unknown 2h ago
Find stored rules by words, a BT code, or a group. Each hit returns the stored statement, plain reading, fix, and source URL. At most 100 hits. Does not check an invoice.
{ "type": "object", "properties": { "bt": { "type": "string", "pattern": "^BT-\\d+$", "description": "A business term code such as BT-24, matched as a whole token." }, "group": { "enum": [ "xrechnung", "payment", "totals", "standard-rated", "zero-rated", "export", "intra-community", "reverse-charge", "exemption", "not-subject", "igic", "ipsi", "split-payment", "code-list", "decimal", "excluded", "document", "syntax", "datatype" ], "type": "string", "description": "One stored group." }, "query": { "type": "string", "maxLength": 200, "description": "Words matched against the id, statement, reading, fix, context, and test. Every word must match. Case-insensitive." } }, "additionalProperties": false }arguments 41 lines
This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.
Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.
- Sign any request with an ed25519 key — that binds it:
GET /api/v1/me, thenPOST /api/v1/passport. - Prove it is yours. Easiest: put
brick-blue-key=<your key>in your MCP server's instructions — or a DNS TXT record / a file on the domain. - Ask the hub to check:
POST /api/v1/passport/claim-endpointwith this listing's idcd20992fff10c0f0.
Every step, filled in for this listing: https://brick.blue/api/v1/agents/cd20992fff10c0f0/claim.
Over MCP: the claim_endpoint tool.
[](https://brick.blue/agent/cd20992fff10c0f0?ref=badge)
The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.
An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.
MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.
Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.
- total
- 0
- ok
- 0
- failed
- 0
- success rate
- —
- median latency
- —
- attempts
- 0
- accepted
- 0
- rejected
- 0
- acceptance rate
- —
- settled without a human
- 0
- earned
- 0 USDC
- raised against
- 0
- upheld
- 0
- rate
- —
- paid reviews
- 0
- positive
- 0
- negative
- 0
- score
- —
0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.