Jaz AI
Mirrors help center content from Intercom for reference.
Provides tools for converting data from MYOB to Jaz accounting.
Provides tools for converting data from QuickBooks to Jaz accounting.
Provides tools for converting data from Sage to Jaz accounting.
Provides tools for converting data from Xero to Jaz accounting.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Jaz AIshow me the balance sheet for Q3 2024"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Jaz AI · Agent stack for the ledger
The complete agent surface for Jaz accounting. 284 MCP tools, 6 skills, 16 IFRS recipes, 13 calculators, 12 close playbooks. Designed for any agent: Claude, GPT, Gemini, Copilot, Cursor. Hyper token economics, one-shot discovery, structured errors that an LLM can recover from.
Also fully compatible with Juan Accounting (same API surface).
Contents
Install · 30 seconds
Your agent | Install |
Claude Code |
|
Claude Desktop | Install the |
Cursor / Windsurf | Add the stdio MCP config (below) |
VS Code (incl. GitHub Copilot) | Add the VS Code MCP config (below) to |
Gemini CLI |
|
OpenAI Codex CLI / Agents SDK | Add the stdio MCP config (below) |
OpenAI Responses API | Hosted HTTP MCP only (see Responses API note) |
npm (CLI) |
|
Stdio MCP config (Claude Desktop, Cursor, Windsurf, OpenAI Codex CLI / Agents SDK, any host that runs MCP servers as local processes):
{
"mcpServers": {
"jaz": {
"command": "npx",
"args": ["-y", "jaz-clio@5.5.0", "mcp"],
"env": { "JAZ_API_KEY": "jk-your-api-key" }
}
}
}VS Code MCP config (.vscode/mcp.json — workspace-scoped — used by VS Code itself and the GitHub Copilot Chat extension):
{
"servers": {
"jaz": {
"command": "npx",
"args": ["-y", "jaz-clio@5.5.0", "mcp"],
"env": { "JAZ_API_KEY": "jk-your-api-key" }
}
}
}Pin jaz-clio@5.5.0 for stability, or jaz-clio@latest for auto-updates. Multi-org: comma-separated keys, e.g. "JAZ_API_KEY": "jk-aaa,jk-bbb". Personal access tokens (pat_...) also work for multi-org.
OpenAI Responses API
The Responses API only accepts HTTP MCP (no stdio). To use Jaz from a Responses API tool, host the MCP server behind HTTP and point at it:
{
"type": "mcp",
"server_label": "jaz",
"server_url": "https://your-hosted-jaz-mcp/",
"require_approval": "never"
}A managed hosted endpoint isn't published yet; use the OpenAI Codex CLI / Agents SDK path above for stdio in the meantime.
Just want skills (no MCP, any agent on the Agent Skills standard):
npx jaz-clio init # auto-detects your tool
npx jaz-clio init --platform cursor
npx jaz-clio init --no-rules # skills only, skip the agent-rules file
npx jaz-clio init --check # report drift between installed agent-rules version and currentSkills install to .agents/skills/ (Agent Skills standard, used by Cursor, Copilot, Codex, Antigravity, Windsurf, Goose, Roo Code, Junie, Amp, and more) or .claude/skills/ (Claude Code).
init also writes a one-page jaz-agent-rules.md block to the path your platform reads on workspace open, so any agent (Claude / GPT / Gemini / Copilot / Cursor) starts every session with the meta-tool discovery flow, the 6 API gotchas, and the recipe-engine carve-out (no double-posting on fx-reval).
The block is wrapped in version-stamped markers (<!-- BEGIN jaz-agent-rules vX.Y.Z --> / <!-- END jaz-agent-rules -->), so re-running init updates only the Jaz block — your own rules above and below stay untouched. Run clio init --check to report drift between your installed version and the current package version (exit 1 = drift, exit 0 = current).
Platform | Rules file path |
Claude Code |
|
Codex / Antigravity / Goose |
|
GitHub Copilot |
|
Cursor |
|
Windsurf |
|
Gemini CLI |
|
What you get
284 MCP tools covering every Jaz endpoint. Each tool description disambiguates against similar tools, lists enum values inline, and flags idempotency. The LLM picks right on the first call.
6 skills with the production-grade rules and playbooks any agent needs:
Skill | What it teaches an agent |
jaz-api | 141 production rules, every endpoint, error catalog, field aliases, response shapes |
jaz-cli | The |
jaz-conversion | Xero / QuickBooks / Sage / MYOB / Excel migration, CoA mapping, FX, clearing accounts, TB verification |
jaz-jobs | 12 close playbooks (month-end / quarter-end / year-end / bank-recon / GST-VAT / payment-run / credit-control / supplier-recon / audit-prep / FA-review / statutory-filing) + Singapore Form C-S |
jaz-recipes | 16 IFRS recipes (loans, IFRS 16 leases, depreciation, FX reval, ECL, IAS 37 provisions, asset disposal, etc.) + 13 calculators |
jaz-practice | Multi-client practitioner workspace, engagement scaffolding, per-client config |
3 meta-tools (
search_tools,describe_tools,execute_tool) for deferred discovery so the full catalog never has to load into context.OpenAPI spec at
spec/openapi.yamlsynced weekly from the source.Help center mirror at
help-center-mirror/synced weekly from Intercom.Structured-search DSL for natural-feeling queries (
status:unpaid amount:>500 contact:Acme).
Three layers
The stack is one binary plus markdown skills, exposed through three layers that compose. The default agent setup is Skills + MCP. The CLI is the same binary as the MCP server with a different transport flag.
Layer | What it is | Use it alone when |
Skills | Domain knowledge as markdown (154 API rules, 16 recipes, 12 jobs, conversion playbooks, practitioner workflows). The agent reads these at session start. | Your AI tool reads markdown but cannot call binaries (e.g., a Custom GPT with no actions). |
CLI ( | A | You're scripting CI / running offline calculators / a human is at the terminal. |
MCP server ( | The same binary in MCP mode: 284 Jaz tools as agent-callable functions with structured envelopes. | This is the default for any agent (Claude / GPT / Gemini / Copilot / Cursor) that takes accounting actions. |
Skills layer on top of either. Most installs (Claude Code plugin, Claude Desktop MCPB, Cursor + MCP, Gemini extension) load Skills + MCP together.
Quick start
Once installed, skills load automatically when an agent works with Jaz. Describe what you need:
Close the books for Acme for January. Bank-recon DBS Current first.
Then file GST for Q1.Or call the CLI directly:
clio invoices list --json
clio calc loan --principal 100000 --rate 6 --term 60 --json
clio jobs month-end --period 2025-01 --jsonOr via MCP from any agent:
search_tools("anomalous bills")
→ download_export at rank 1
execute_tool("download_export", { exportType: "analysis-anomalous-bills" })
→ { fileName, fileUrl }Token economics + speed
Built so any LLM sees the right tool fast and calls it once.
What | How |
MCP delivery | 3 meta-tools (~600 tokens) instead of 284 (~78KB). LLM searches into the catalog only when needed. |
OpenAI Responses API | Native deferred tool_search with namespace bundles. ~78% token reduction over a static tool list. |
Anthropic delivery | Tool list cached via prompt-cache breakpoints (5-min TTL). System blocks cached. ~5KB/request savings after v5.4.4 cleanup. |
Discovery ranker | In-memory, no network round-trip. Scans tool name + description + searchHint + namespace. |
Disambiguation | Every tricky pair ( |
Median tool call | Subsecond for read tools; bounded by the Jaz API + network. |
Errors are structured | 422 responses carry field-level details so the LLM can self-correct without human input. |
For AI agents
Skills load automatically from
.claude/skills/,.agents/skills/, the Claude Code marketplace, the Gemini CLI extension, or the Claude Desktop MCPB.Discovery is one-shot. 68 canonical-query lock-in tests guarantee the right tool at rank 1 for the queries that matter.
Disambiguation is explicit. Tools that look similar carry "USE THIS, not X" preambles. No more guessing.
Errors are structured. Server validation failures return field-level details so the agent can self-correct.
Multi-org is native. Comma-separated keys (
jk-aaa,jk-bbb) or PATs unlock cross-org tools (list_organizations, per-callorg_id).OpenAPI spec at
spec/openapi.yamlfor code-gen pipelines and custom SDKs.CONTEXT.md captures runtime rules-of-engagement (bootstrap with
clio context --json, search before create, mutate as draft first, never echo API keys).
For accountants
Set up the firm workspace once, then run period work conversationally:
clio practice init --firm-name "My Firm"
clio practice onboard --name "Acme Pte Ltd" --fy-end 12-31 --gst quarterly
clio practice create-engagement acme-pte-ltd --type monthly-close --period 2026-03Or describe it to any agent:
Onboard Beta Pte Ltd, FY June, GST quarterly. Close March for Acme.
Each engagement template names the exact Jaz tools, recipes, and calculators to invoke. The agent loads CLIENT.md automatically before touching the books: FY end, GST scheme, COA mapping, banks, recurring accruals.
13 calculators (clio calc loan / depreciation / lease / ecl / fx-reval / provision / fixed-deposit / asset-disposal / prepaid-expense / deferred-revenue / accrued-expense / leave-accrual / dividend), 12 job blueprints (clio jobs month-end / quarter-end / year-end / bank-recon / document-collection / gst-vat / payment-run / credit-control / supplier-recon / audit-prep / fa-review / statutory-filing), all with --json for structured blueprint output.
Reference
CLAUDE.md · architecture, source structure, version-bump procedure, contributor guide
CONTEXT.md · runtime rules-of-engagement for agents using the stack
CHANGELOG.md · release notes
Skills source · all 6 skills (jaz-api / jaz-cli / jaz-conversion / jaz-jobs / jaz-recipes / jaz-practice)
OpenAPI spec · full HTTP surface, synced weekly
README-cli.md · npm-package README, full CLI command catalog
help.jaz.ai · Jaz product help center
CLI surface: 55 command groups across the
cliobinary
jaz-api
Reference | Lines | Content |
| 525 | 154 rules: auth, IDs, dates, FX, payments, field aliases, response shapes |
| 2342 | Request/response examples for every core endpoint |
| 860 | Error catalog with root causes and fixes |
| 678 | Intuitive name → actual field name mapping |
| 769 | Filter fields, sort fields, operators for 28 search endpoints |
| 759 | Complete endpoint catalog (80+), enums, limits |
| 140 | Resource creation order (currencies → CoA → transactions) |
| 248 | Business context per feature |
jaz-recipes (16 IFRS recipes + 13 calculators)
Reference | Content |
| 16 recipes in 4 tiers, building blocks, calculator index |
| Capsules, schedulers, manual journals, FA, tracking tags, nano classifiers |
| Annual insurance/rent paid upfront, monthly scheduler recognition |
| Upfront customer payment, monthly revenue recognition |
| Month-end accrual + reversal cycle using dual schedulers |
| Loan disbursement, amortization table, monthly installments |
| ROU asset + lease liability unwinding (IFRS 16) |
| DDB/150DB with switch-to-SL logic |
| Placement, compound interest accrual, maturity (IFRS 9) |
| Like IFRS 16 but depreciate over useful life |
| Sale/scrap/write-off with gain/loss (IAS 16) |
| Non-AR/AP FX revaluation with Day 1 reversal (IAS 21) |
| ECL simplified approach provision matrix (IFRS 9) |
| Leave (scheduler) + bonus (manual) accruals (IAS 19) |
| PV recognition + monthly discount unwinding (IAS 37) |
| Declaration + payment (two manual journals) |
| Mirrored invoices/bills across two entities |
| CIP accumulation → FA transfer on completion |
jaz-jobs (12 close playbooks + Singapore Form C-S)
Reference | Content |
| 12 jobs + SG tax computation, CLI commands, wizard workflow |
| Shared concepts: accounting periods, lock dates, period verification |
| 5 phases, ~18 steps. Foundation for all period closes. |
| Monthly + quarterly extras (GST/VAT, ECL, bonus accruals) |
| Quarterly + annual extras (true-ups, dividends, CYE rollover) |
| Match, categorize, resolve unreconciled items |
| 5-phase cascade matcher (1:1, N:1, 1:N, N:M) |
| Local + cloud (Dropbox / Drive / OneDrive) doc capture |
| Tax ledger review, discrepancy check, filing summary |
| Select bills by due date, process payments |
| AR aging review, overdue chase list, bad debt |
| AP vs supplier statement reconciliation |
| Compile reports, schedules, reconciliations for auditor |
| Fixed asset register review, disposal/write-off |
| 10 files: SG CIT framework, Form C-S fields, wizard, data extraction, add-backs, capital allowances, IFRS 16 tax adj, enhanced deductions, exemptions, loss carry-forward |
jaz-conversion
Reference | Content |
| Conversion domain knowledge, clearing account pattern, FX handling |
| CoA, contact, and tax code mapping rules |
| Full conversion (all transactions FY + FY-1) |
| Quick conversion (opening balances at FYE) |
| Supported file formats and detection heuristics |
| Platform-specific quirks (Sage 300, Xero rounding) |
| Trial balance comparison and verification checklist |
| Excel/CSV structure analysis and smart detection |
Troubleshooting
command not found: clio
Node.js is not installed, or npm's global bin directory is not on PATH.
node --version # Need v18+. If missing, install LTS from https://nodejs.org
npm install -g jaz-clio
npm config get prefix # e.g. /usr/local or ~/.nvm/versions/node/v22.x.x
export PATH="$(npm config get prefix)/bin:$PATH" # Add to ~/.bashrc or ~/.zshrcAuth error / 401 Unauthorized
Missing or invalid API key. Keys expire if regenerated in the Jaz app.
clio auth whoami
clio auth add <your-api-key> # Get from Settings > API in Jaz
clio auth list # Confirm the right org is activeIf you use env vars, set JAZ_API_KEY in the current shell or your MCP config's env block.
MCP not connecting
The config path is wrong, the command is wrong, or the server crashes on startup.
npx jaz-clio mcp # Smoke-test the server (Ctrl+C to stop)
claude mcp list # Confirm Claude Code sees "jaz"
claude mcp add jaz -- npx jaz-clio mcpFor Cursor / VS Code / Windsurf, validate the JSON and pin the API key:
{
"command": "npx",
"args": ["-y", "jaz-clio@5.5.0", "mcp"],
"env": { "JAZ_API_KEY": "jk-your-api-key" }
}Pin
JAZ_API_KEYin MCP config rather than relying on the active CLI profile. MCP servers cache credentials at startup soclio auth switchwon't take effect until restart. For multi-org, use comma-separated keys.
Skills not loading
Files are in the wrong path, or your tool doesn't auto-discover from there.
ls .claude/skills/ # Claude Code
ls .agents/skills/ # Agent Skills standard (Cursor, Copilot, etc.)
npx jaz-clio init # Re-install with auto-detectionEach skill folder must contain SKILL.md plus its reference files. Manual copies often miss subdirectories.
EACCES permission denied on npm install
npm's global directory needs elevated permissions on macOS/Linux without nvm.
# Option A — nvm (recommended)
curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.40.3/install.sh | bash
nvm install --lts && npm install -g jaz-clio
# Option B — fix npm permissions
mkdir -p ~/.npm-global && npm config set prefix ~/.npm-global
export PATH="$HOME/.npm-global/bin:$PATH" # Add to ~/.bashrc or ~/.zshrc
npm install -g jaz-clioStale data after org switch
You ran clio auth switch but the MCP server still uses the previous org (it cached auth at startup).
# In Claude Code: remove and re-add
claude mcp remove jaz && claude mcp add jaz -- npx jaz-clio mcp
# In Cursor / VS Code: restart the editor or reload MCP serversOr use multi-org mode and skip restarts: comma-separated keys (jk-aaa,jk-bbb) and switch orgs in conversation.
Privacy & security
Runs entirely on your machine. API calls go directly from your machine to the Jaz API over HTTPS. No telemetry. The API key lives locally in ~/.config/jaz-clio/credentials.json.
Full policy: jaz.ai/legal. Vulnerability disclosure: SECURITY.md.
Support
Help center: help.jaz.ai
Email: api-support@jaz.ai
License
MIT · Copyright (c) 2026 Tinvio / Jaz · Clio is a registered trademark of Tinvio.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/teamtinvio/jaz-ai'
If you have feedback or need assistance with the MCP directory API, please join our Discord server