
AgentToolWorks MCP server
Which servers in the official MCP registry are AgentToolWorks's own, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-15
- Registry namecom.agenttoolworks/invoiceforgeverified in the MCP registry
The registry name sits under agenttoolworks.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-15
- Tools5
- Server calls itselfinvoiceforge
- Server version0.1.0
- Protocol version2025-06-18
On 2026-10-15 the server answered initialize and tools/list without a sign-in. First answer in 824 ms.
- Whether its tools do the product's job has not been judged yet.
- Checked on 3 of the 7 days it takes to judge reliability.
Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.
- INITE MCP scoreafter a weeka score needs 7 daily checks: 3 so far
- Answeredmeasuring3 of the 7 daily checks it takes to print a share
- Median first answer675 ms
- Space in an agent's context≈ 1,736 tokensthe definitions of all its tools (5), which an agent carries on every turn
- Tool definitionsB · 83 of 100
- Typed results0 of 5 toolsdeclared outputSchema: results come typed, read once
- Not saying whether it only reads or can destroy: 5 of 5
What an agent can do with it
- not sure · confirm a company is registered in French or UK registries
- not sure · check EU VAT numbers against the VIES system
- not sure · screen people and companies against sanctions lists
Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?
Worth a look
None of the five warning signs in these definitions.
A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (30%), doing the product's job (25%), definitions (20%), context (10%) and use (15%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →
generate_invoiceTurns invoice data into a compliant UBL 2.1 XML document following the EN 16931 semantic model, with totals and the VAT breakdown computed for you. Choose the plain EN 16931 profile or the Peppol BIS Billing 3.0 customization. The…
validate_invoiceChecks invoice data against a documented subset of the EN 16931 business rules: mandatory fields, code lists, VAT category consistency and the arithmetic that most often gets invoices rejected. Accepts incomplete or malformed data on…
extract_invoiceReads an incoming UBL or CII (Factur-X) invoice XML and returns the data as structured JSON, listing any field the document did not contain rather than guessing it. Use it to ingest supplier invoices before booking them. Costs 1 credit.
describe_coverageReturns the exact EN 16931 rules this server checks, the syntaxes it can produce and read, and the things it deliberately does not do, such as transmitting invoices over Peppol or acting as a French accredited platform. Light read: costs…
get_usageReturns your current plan, remaining credit balance and call volume over the last 30 days. Free to call.
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"invoiceforge": {
"type": "http",
"url": "https://invoiceforge.agenttoolworks.com/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http agenttoolworks https://invoiceforge.agenttoolworks.com/mcpclaude.ai, ChatGPT and other clients: add https://invoiceforge.agenttoolworks.com/mcp as a custom connector in the settings.
- com.agenttoolworks/jobsradaranswers, 4 toolsverified in the MCP registry
- com.agenttoolworks/storecataloganswers, 5 toolsverified in the MCP registry
- com.agenttoolworks/verifydesknot asked yetverified in the MCP registry
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.
Cookies
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.