Skip to main content
Glama
sevdesk-mcp

sevdesk-mcp

by joosthel

Call any sevDesk API operation

sevdesk_call
Destructive

Executes a sevDesk API operation from the catalogue by operationId, handling path, query, and body parameters with dry-run and read-only safeguards.

Instructions

Execute any operation from the catalogue. Path parameters are taken from params by name; remaining params entries become query parameters. Nested objects are encoded in sevDesk's bracket syntax (a[b]=c). Mutating operations are refused when the server runs with SEVDESK_READ_ONLY=true, and are only described (not sent) when SEVDESK_DRY_RUN=true or dryRun is passed. Operations with a preventSendBy query parameter (the *GetPdf reads) default it to true so a read does not mark the document as sent. GETs that change state (sendByWithRender, enshrine flags, preventSendBy=false) count as writes. Booking operations (bookVoucher, bookInvoice, bookCreditNote, their resetToOpen and resetToDraft, createPrivateTransactionRule) and writes that set a transaction status or move a voucher out of draft or mark it paid (updateCheckAccountTransaction, updateVoucher, voucherFactorySaveVoucher) are refused unless SEVDESK_ALLOW_BOOKING=true; prefer sevdesk_link_transaction for vouchers. Can call DELETE operations, which are irreversible. ⚠️ This tool can change data in sevDesk.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "operationId": "<operationId>"
    },
    "name": "sevdesk_call"
  }
}

Input Schema

NameRequiredDescriptionDefault
bodyNoJSON request body, for POST/PUT operations.
dryRunNoDescribe the request that would be sent instead of sending it.
paramsNoPath and query parameters, keyed by parameter name.
operationIdYesExact operationId from sevdesk_list_operations.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A4.3/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Substantially exceeds the annotations: it explains SEVDESK_READ_ONLY and SEVDESK_DRY_RUN gating, the dryRun override, the preventSendBy auto-default for *GetPdf reads, that some GETs mutate state, the SEVDESK_ALLOW_BOOKING gate with an enumerated list of gated operations, and that DELETEs are irreversible. These are exactly the operational hazards an agent needs before dispatching an arbitrary endpoint.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads the dispatch mechanism, then layers behavioral constraints in a single dense paragraph with no filler. The closing warning sentence largely restates destructiveHint=true, which is the one mildly redundant element.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an open-world catch-all dispatcher with no output schema, the definition covers encoding rules, environment gates, read-versus-write classification, booking restrictions, and irreversibility. An agent has everything needed to decide whether to call it and how to shape the request.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds real semantic meaning: params entries are matched against path parameters by name, leftovers become query parameters, and nested objects use bracket encoding (a[b]=c). Only dryRun and body semantics are left entirely to the schema, which already documents them.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: execute any operation from the catalogue, with the operationId sourced from sevdesk_list_operations. That makes the generic-dispatcher nature clear, though it does not explicitly contrast itself with sibling wrappers such as sevdesk_create_invoice or sevdesk_get_voucher, which an agent would still have to infer.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives explicit routing guidance for one case ('prefer sevdesk_link_transaction for vouchers') and clear conditions under which calls are refused (read-only mode, booking gate). It does not say when to prefer the dedicated siblings over this generic escape hatch, so the when-not guidance is partial rather than complete.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.