Files
accounted/extensions/general/mcp-server
Jakob WennbergandClaude Fable 5 e33cc2428d feat(plugin): official Claude Code plugin with marketplace and seven workflow skills (#1088)
Ships an installable Claude Code plugin (/plugin marketplace add
erp-mafia/accounted) that bundles the MCP connection (OAuth, zero-key)
with seven short workflow skills following the Swedish bookkeeping
rhythm: start, bookkeep, check, month-close, vat, payroll, year-end.

Wrappers are deliberately thin: they ground in the agent briefing and
Accounted:// resources, load server-side workflow skills and regulatory
atoms via gnubok_load_skill at need, and stage every write for user
approval. No knowledge is duplicated into the plugin.

A vitest cross-checks every skill slug, atom id, resource URI, and tool
name the wrappers reference against the MCP server source, so a server
rename fails CI instead of a user's chat session.

Assessment and follow-ups in dev_docs/claude_plugin.md (local, dev_docs
is unpublished by design).

Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-07-21 12:59:57 +02:00
..
2026-07-15 15:53:15 +02:00
2026-07-15 15:53:15 +02:00

Accounted MCP server

JSON-RPC 2.0 server exposing the Accounted bookkeeping engine to MCP clients (Claude Desktop, Claude Code, etc.). Endpoint: /api/extensions/ext/mcp-server/mcp. OAuth and stdio bridge live alongside the API surface: see app/api/mcp-oauth/ and packages/gnubok-mcp/.

Tool authoring contract

Enforced by tests in __tests__/: these are not style preferences, they're guard rails.

  1. additionalProperties: false on every inputSchema. Guarded by strict-schemas.test.ts. Forces clear rejections on hallucinated fields instead of silent ignores.
  2. Descriptions ≤ 280 chars. Guarded by output-schema.test.ts. No Args: / Returns: / Examples: prose: those belong in JSON Schema. Use agent-native hints ("Use to…", "Call X first", "HIGH risk").
  3. Staged-operation envelope for write tools: outputSchema: STAGED_OPERATION_SCHEMA (server.ts). Fields: staged, risk_level, actor, message, preview, period_status?, next?. The staged: true boolean is the explicit completion signal; agents must not infer completion from prose. Do NOT introduce a parallel { success, shouldContinue, output } envelope.
  4. period_status threading: any tool that ties to a fiscal-period-bound date (categorize, mark paid, create voucher, correct/reverse entry, approve supplier invoice) passes dateForPeriodCheck to stagePendingOperation. Response then includes period_status: { period_id, status: open|locked|closed, lock_date } so widgets and agents disable writes without round-trips.
  5. Scope mapping: every new tool needs an entry in lib/auth/api-keys.ts TOOL_SCOPE_MAP. Missing entries default to deny.
  6. Tests for new write tools: add staging-gate coverage to __tests__/voucher-tools.test.ts (or a sibling) plus executor coverage to lib/pending-operations/__tests__/voucher-executors.test.ts if the tool stages a new operation_type.

Determinism / cache stability

Tool definitions (name, description, inputSchema, outputSchema, annotations) are declared as static object literals at module load: no timestamps, no UUIDs, no Date/Math.random in the definition layer. This makes the tools/list JSON payload byte-stable across requests, which lets agent-side prompt caches stay warm. Do not introduce per-request non-determinism into the definitions block. Anything time-bound or random belongs inside execute().

For internal Anthropic API usage (today only extensions/general/invoice-inbox/lib/extract-invoice-fields.ts): annotate stable prefixes with cache_control: { type: 'ephemeral' } and log usage.cache_read_input_tokens for hit-ratio observability. The 1h TTL from the agent-native API plan (item 10) requires the direct Anthropic API; Accounted's Bedrock path defaults to a shorter TTL.

Payload-size watchdog

payload-size.bench.test.ts enforces a tools/list JSON payload ceiling (currently 36,000 tokens, bumped from 32,000 when top-level Tool.title landed on all tools for Claude Connectors Directory readiness). If the test fires, the right answer is rarely "raise the ceiling". Instead, trim descriptions or leverage gnubok_search_tools (already deployed; tool definitions can defer to it for discovery rather than enumerating in tools/list).

Where things live

  • server.ts: the tools array + JSON-RPC dispatcher
  • tool-result.ts: withNext(), toToolError() response helpers
  • resources/: read-only Accounted:// URIs (active company, period, recent activity, capabilities, attention items, voucher gaps, chart of accounts, VAT treatments)
  • widgets/: inline HTML widgets (receipt-matcher, vat-review)
  • prompts/: slash-command-style prompts
  • skills/: domain-knowledge skill bodies served via gnubok_load_skill
  • __tests__/: strictness guards + per-tool coverage