# Bonsai MCP MCP Server > **Bonsai MCP MCP Server** is a hosted, multitenant Model Context Protocol (MCP) server run by **MewCP** (https://mewcp.com), giving AI agents managed access to Bonsai MCP. > > MewCP takes care of all MCP infrastructure for you — credential storage, OAuth flows, > token refresh, and production-grade auto-scaling — so your AI agents can connect to > third-party services and run freely without you managing any MCP server yourself. > > Server page: https://mewcp.com/mcp/bonsai-mcp > MewCP docs: https://docs.mewcp.com > Full catalog: https://mewcp.com/llms.txt --- ## About Bonsai brings freelance business operations into one workspace, covering client management, proposals, contracts, project tracking, time tracking, invoicing, and payments. Create estimates, manage retainers, track expenses, monitor outstanding invoices, and review business finances from a unified dashboard. --- ## Details - Server ID: `bonsai-mcp` - Version: 0.1.0 - Tools: 51 - Authentication: OAuth, managed by MewCP - Transport: http --- ## Access The gateway URL below serves your **entire MewCP toolset**, not this server on its own. Pasting a config snippet is not enough — Bonsai MCP has to be in the toolset first. In order: 1. Add Bonsai MCP to your toolset at https://mewcp.com/mcp/bonsai-mcp 2. Connect your Bonsai MCP account (OAuth); MewCP stores the credential and attaches it to each call 3. Copy your MewCP API key from the dashboard (Developer) 4. Configure your client with the snippet for it below Once connected, an agent does **not** see this server's tools as top-level tools. It sees four meta-tools and reaches everything through them: - `search(query)` — find tools by keyword across the toolset - `get_schema(tools)` — full description and arguments for the tools you picked - `list_accounts(provider)` — only when one app has several connected accounts - `call_tool(server_maskedId, tool_name, args)` — execute So the list below is what `search` can return for this server, not a set of callable tool names on their own. --- ## Tools (51) Descriptions are truncated to 160 characters; call `get_schema` for the full text and the argument schema. Where a tool is annotated, its type is shown — treat `destructive` as irreversible. - `get_task` _(read)_ — Fetch a single task from Bonsai by its UUID. Returns the full task including pre-resolved `assignee_member_name`, `due_date`/`start_date`,… - `list_tasks` _(read)_ — List tasks in the user's current company, paginated, ordered by creation date (newest first). Supports filtering by `title` (free-text search,… - `list_subtasks` _(read)_ — List a parent task's subtasks (its child tasks), paginated, ordered by the manual subtask order. Each subtask carries the same summary fields as `list_tasks`… - `list_task_statuses` _(read)_ — List the caller's company task statuses, paginated. A task status is a board column a task can occupy (e.g. "To Do" / "In Progress" / "Done", plus any custom… - `create_task` _(write)_ — Create a task in the user's current company. Supports `title` (required), optional `project_id`, `deal_id` (put the task on a deal — resolve via `list_deals`;… - `update_task` _(write)_ — Update an existing task in the user's current company. Requires `uuid` (resolve via `list_tasks`, `get_task`, or `list_subtasks`); every other field is… - `destroy_task` _(destructive)_ — Soft-delete a task in Bonsai by its UUID. The task is removed from every subsequent read; archived tasks can be deleted directly. Returns the deleted task's… - `list_time_entries` _(read)_ — List time entries in the user's current company, paginated, newest first. Each entry exposes `key`, `seconds`, `formatted_time`, `date`, `notes`, `rate`,… - `create_time_entry` _(write)_ — Log a time entry in the user's current company. Only `seconds` (duration) and `date` (YYYY-MM-DD) are required. Attach the entry to work with `project_id`… - `update_time_entry` _(write)_ — Update an existing time entry in the user's current company. Requires `key` (resolve via `list_time_entries`); every other field is optional and only the ones… - `list_projects` _(read)_ — List projects in the user's current company, paginated, ordered by creation date (newest first). Defaults to active projects; pass `status` to retrieve… - `create_project` _(write)_ — Create a project for an existing company. Requires `title`, `company_id` (the company the project is for — resolve via `list_companies`), and `billing_type`… - `update_project` _(write)_ — Update an existing project in the user's current company. Requires `id` (resolve via `list_projects`); every other field is optional and only the ones supplied… - `destroy_project_budget` _(destructive)_ — Stop tracking a project's budget. The budget and its cycles are removed, and the project reads back with `budget: null` on `list_projects`. The project itself,… - `list_team_members` _(read)_ — List team members (company member entities) in the user's current company, paginated. Each entry exposes `company_member_id`, the value to pass as… - `list_board_groups` _(read)_ — List the caller's company board groups, paginated. A board group is a pipeline stage on a Deal board and a Project Group on a Project board (see… - `list_company_tags` _(read)_ — List the caller's company tags as a single flat collection across every tag type, paginated. A company tag is a reusable label attached to Bonsai records. Each… - `list_deals` _(read)_ — List deals in the user's current company, paginated. Each entry exposes `id`, `title`, `deal_number`, `deal_value` (nullable decimal string), `currency`,… - `list_invoices` _(read)_ — List invoices in the user's current company, paginated, newest first. Each entry exposes `id`, `invoice_number` (nullable until numbered; a sequential string… - `list_companies` _(read)_ — List CRM companies in the user's current company, paginated. Use this to find an existing company — by `name` free-text search — before deciding whether to… - `get_company` _(read)_ — Fetch a single CRM company by its id, in the same shape `list_companies` returns per row. Use it when you already hold a company id — from `list_companies`, a… - `list_company_activities` _(read)_ — List what happened with a CRM company, newest first: its own events plus the events of every contact on it, merged into one stream — documents, invoices,… - `list_contacts` _(read)_ — List CRM contacts in the user's account, paginated. Each entry exposes `id`, `name`, `email`, `job_title`, `phone_number`, `created_at`, `archived_at` (null… - `list_contact_activities` _(read)_ — List what happened with one CRM contact, newest first: its own events — documents, invoices, emails, meetings, deals it was assigned to, form submissions,… - `create_company` _(write)_ — Create a CRM company in the user's current account. Supports `name` (required), optional `default_contact_id` (resolve via `list_contacts`; `null` for none),… - `create_contact` _(write)_ — Create a CRM contact in the user's account. Requires `name` and `email`. Optional `job_title` and `phone_number` (pass `null` to leave unset), and `company_id`… - `create_invoice` _(write)_ — Create an invoice for a client company in the user's current company. Requires `company_id` (the company being billed — resolve via `list_companies`),… - `update_invoice` _(write)_ — Partially update an existing invoice in the user's current company. Requires `id` (the invoice — use the `id` from a prior `create_invoice` call or resolve via… - `stop_invoice_recurrence` _(destructive)_ — End a recurring or subscription invoice series, so no further invoices are issued and a subscription stops charging the card the client has on file — the same… - `destroy_invoice` _(destructive)_ — Delete a draft invoice, or cancel one that is scheduled or has been sent; either way it stops appearing in `list_invoices`. Its `status` decides which: a… - `create_invoice_item` _(write)_ — Add a single line item to an existing invoice; the invoice total is recomputed. Requires `invoice_id` (the invoice to bill on — use the `id` returned by a… - `update_invoice_item` _(write)_ — Update the supplied fields of a single line item on an invoice; the invoice total is recomputed. Requires `invoice_id` (the invoice — use the `id` from a prior… - `destroy_invoice_item` _(destructive)_ — Remove a single line item from an invoice; any linked time entries are unbilled and the invoice total is recomputed. Requires `invoice_id` (the invoice — use… - `update_company` _(write)_ — Update an existing CRM company in the user's current account. Requires `id` (resolve via `list_companies`); every other field is optional and only the ones… - `update_contact` _(write)_ — Update an existing CRM contact in the user's account. Requires `id` (resolve via `list_contacts`); every other field is optional and only the ones supplied are… - `list_comments` _(read)_ — List the comments on a task or a deal, paginated, newest first. Provide exactly one parent — `task_id` (a task UUID) or `deal_id` (a deal id). By default only… - `create_comment` _(write)_ — Post a user-authored comment on a task or a deal. Provide exactly one parent — `task_id` (a task UUID) or `deal_id` (a deal id) — and a `body`. The comment is… - `list_notes` _(read)_ — List notes in the user's current company, paginated, ordered by when each note was written (newest first) — not by `date`, so a note backdated to last year… - `create_note` _(write)_ — Write a note in the user's current company. Only `content` is required, and it is Markdown — Bonsai stores it as rich text, so headings, bold/italic, bullet,… - `get_note` _(read)_ — Fetch a single note by its id, including what it says — the body a list response always leaves out, so read a note here whenever you need it. The body comes… - `update_note` _(write)_ — Rewrite an existing note in the user's current company. Requires `id` (resolve via `list_notes`); `content_html`, `title`, `date` and `visibility` are all… - `destroy_note` _(destructive)_ — Delete a note by its id. The note stops appearing in every subsequent read, and there is no way to restore it, so confirm with the user before calling this.… - `create_note_link` _(write)_ — Attach a note that already exists to a client company, a project or a contact — use this to file a standalone note under a record after the fact, or to add a… - `destroy_note_link` _(destructive)_ — Detach one record from a note, so the note stops appearing under that company, project or contact. The note itself is untouched — detaching its last record… - `list_templates` _(read)_ — List the templates the user can start a new document from, paginated: the account's own saved templates first (`source` "own"), then Bonsai's library (`source`… - `list_template_categories` _(read)_ — List the names `list_templates` accepts in its `category` and `industry` filters, paginated, categories first. Each entry is a `name` plus its `kind` —… - `list_docs` _(read)_ — List the user's documents — proposals, contracts, quotes and the like — in the current company, paginated, newest first. Templates are not documents and never… - `get_doc` _(read)_ — Fetch a single document by its id — the `id` that `list_docs` or `create_doc` returned — in the shape `list_docs` uses, plus its `pricing_table`. Read it again… - `create_doc` _(write)_ — Create a draft document — a proposal, contract, quote and the like — from a template in the user's current company. Nothing is sent: the draft waits in Bonsai… - `set_doc_pricing_table` _(destructive)_ — Replace the whole pricing table on a draft document and return it with the totals Bonsai computed, plus `warnings`. Requires `doc_id` (from `list_docs`,… - `list_tax_rates` _(read)_ — List the taxes the account charges, such as a sales tax or VAT, ordered by name and paginated. This is where a tax name turns into the id a pricing table row… --- ## Connect Gateway URL: https://gateway.mewcp.com/personal/mcp Every request carries one header: Authorization: Bearer Replace `API_KEY` with your own key from the dashboard (Developer). ## Apps ### Claude Desktop Mac & Windows app - macOS: `~/Library/Application Support/Claude/claude_desktop_config.json` - Windows: `%APPDATA%\Claude\claude_desktop_config.json` ```json { "mcpServers": { "mewcp": { "command": "npx", "args": [ "-y", "mcp-remote@latest", "https://gateway.mewcp.com/personal/mcp", "--header", "Authorization:${AUTH_HEADER}" ], "env": { "AUTH_HEADER": "Bearer API_KEY" } } } } ``` Already have an "mcpServers" section in your config? Just add the server entry inside it. 1. Open Claude Desktop → Settings → Developer → "Edit Config" 2. Paste the snippet inside the outer { } of the config file (merge with your existing "mcpServers" section if you have one) 3. Save the file, then quit Claude Desktop completely and reopen it 4. Start a new conversation — your tool will be available ### VS Code Copilot / Cline - Command Palette → "MCP: Open User Configuration" (opens mcp.json). For one project only, use .vscode/mcp.json instead. ```json { "mcp.servers": { "mewcp": { "type": "http", "url": "https://gateway.mewcp.com/personal/mcp", "headers": { "Authorization": "Bearer API_KEY" } } } } ``` Already have a "servers" section in your mcp.json? Just add the server entry inside it. 1. Open VS Code → Command Palette (Cmd+Shift+P / Ctrl+Shift+P) 2. Run "MCP: Open User Configuration" to open your mcp.json 3. Paste the snippet and save 4. Start the server when prompted (or from the MCP servers view) and use it in Copilot Chat ### Cursor AI-first editor - macOS: `~/.cursor/mcp.json` - Windows: `%USERPROFILE%\.cursor\mcp.json` ```json { "mcpServers": { "mewcp": { "url": "https://gateway.mewcp.com/personal/mcp", "headers": { "Authorization": "Bearer API_KEY" } } } } ``` Already have an "mcpServers" section in your mcp.json? Just add the server entry inside it. 1. Open Cursor → Settings → Cursor Settings → MCP 2. Click "Add new global MCP server" 3. Paste the snippet and save 4. Restart Cursor ### Codex OpenAI's CLI agent - Add the snippet to your Codex MCP config or your standard MCP config file for the CLI tool you use. ```json { "mcpServers": { "mewcp": { "type": "http", "url": "https://gateway.mewcp.com/personal/mcp", "headers": { "Authorization": "Bearer API_KEY" } } } } ``` Codex generally reads a standard MCP server block, so you can add this alongside your other configured servers. 1. Open your Codex MCP config or project-level config file 2. Paste the MewCP server block inside the config JSON/TOML structure your tool expects 3. Save the file and restart Codex 4. Verify the tool is available inside a fresh session ### Claude Code Anthropic's CLI agent - ~/.claude.json (user scope) or .mcp.json in your project root — create it if it doesn't exist. Or skip the file and use the CLI command below. ```json { "mcpServers": { "mewcp": { "type": "http", "url": "https://gateway.mewcp.com/personal/mcp", "headers": { "Authorization": "Bearer API_KEY" } } } } ``` Already have an "mcpServers" section in your config? Just add the server entry inside it. 1. Open ~/.claude.json (or .mcp.json in your project root) in a text editor 2. Paste the snippet inside the outer { } (merge with your existing "mcpServers" section if you have one) 3. Save the file and start (or restart) Claude Code 4. Or skip the file entirely and run the CLI command below instead ### OpenCode Open-source terminal agent - ~/.config/opencode/opencode.json (global) or opencode.json in your project root — create it if it doesn't exist. ```json { "$schema": "https://opencode.ai/config.json", "mcp": { "mewcp": { "type": "remote", "url": "https://gateway.mewcp.com/personal/mcp", "enabled": true, "headers": { "Authorization": "Bearer API_KEY" } } } } ``` Already have an "mcp" section in your opencode.json? Just add the server entry inside it. 1. Open ~/.config/opencode/opencode.json (or opencode.json in your project root) in a text editor 2. Paste the snippet inside the outer { } (merge with your existing "mcp" section if you have one) 3. Save the file and start (or restart) OpenCode ### OpenClaw Self-hosted agent gateway - ~/.openclaw/openclaw.json — create it if it doesn't exist. ```json { "mcp": { "servers": { "mewcp": { "transport": "streamable-http", "url": "https://gateway.mewcp.com/personal/mcp", "enabled": true, "headers": { "Authorization": "Bearer API_KEY" } } } } } ``` Already have an "mcp" section in your openclaw.json? Just add the server entry inside "servers". 1. Open ~/.openclaw/openclaw.json in a text editor 2. Paste the snippet inside the outer { } (merge with your existing "mcp" section if you have one) 3. Save the file and restart OpenClaw ### Antigravity Google's agentic IDE - ~/.gemini/config/mcp_config.json (global) or .agents/mcp_config.json (workspace-local) — create it if it doesn't exist. ```json { "mcpServers": { "mewcp": { "serverUrl": "https://gateway.mewcp.com/personal/mcp", "headers": { "Authorization": "Bearer API_KEY" } } } } ``` Already have an "mcpServers" section in your config? Just add the server entry inside it. Remote servers must use the "serverUrl" field — the legacy "url"/"httpUrl" fields aren't supported. 1. In the editor's agent side panel, click "…" → "MCP Servers" → "Manage MCP Servers" → "View raw config" (Antigravity CLI: type /mcp instead to open the Interactive MCP Manager) 2. Paste the snippet inside the outer { } (merge with your existing "mcpServers" section if you have one) 3. Save the file — the server connects automatically ### Hermes Nous Research's CLI agent - config.yaml in your Hermes config directory (~/.hermes) — add this under a top-level "mcp_servers:" key. ```yaml mcp_servers: mewcp: url: "https://gateway.mewcp.com/personal/mcp" headers: Authorization: "Bearer API_KEY" ``` Already have an "mcp_servers" section in your config.yaml? Just add the server entry inside it. 1. Open config.yaml in your Hermes config directory 2. Paste the snippet under the top-level "mcp_servers:" key (merge with existing entries if you have any) 3. Save the file, then run /reload-mcp in Hermes (or start a fresh session) 4. Ask Hermes "Tell me which MCP-backed tools are available right now" to confirm it connected ### DeepSeek Harness DeepSeek's agent harness - cordis.yml in your DSH project — or the patch file you mount plugins from. ```yaml - id: mcp-mewcp name: '@deepseek-ai/dsh-mcp-client' config: serverName: mewcp transport: streamable-http url: https://gateway.mewcp.com/personal/mcp headers: Authorization: "Bearer API_KEY" ``` One plugin instance = one MCP server. Add this entry to your plugin list; don't nest it inside another entry. 1. Open cordis.yml (or your patch file) in your DSH project 2. Paste the entry into your plugin list, keeping the leading dash and indentation 3. Restart DSH (or let HMR reload) — tools register as mcp__mewcp__ 4. Verify with: dsh web --dump-config | grep -A3 mcp ## SDKs ### Python fastmcp client ```python import asyncio from fastmcp import Client from fastmcp.client.transports import StreamableHttpTransport SERVER_URL = "https://gateway.mewcp.com/personal/mcp" API_KEY = "API_KEY" transport = StreamableHttpTransport( url=SERVER_URL, headers={ "Authorization": f"Bearer {API_KEY}", } ) async def main(): client = Client(transport) async with client: tools = await client.list_tools() print(tools) asyncio.run(main()) ``` 1. Install fastmcp: pip install fastmcp 2. Copy the snippet into your project 3. Replace API_KEY with your key from the dashboard 4. Run your script ### TypeScript MCP SDK ```typescript import { Client } from "@modelcontextprotocol/sdk/client/index.js"; import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp.js"; const SERVER_URL = "https://gateway.mewcp.com/personal/mcp"; const API_KEY = "API_KEY"; const transport = new StreamableHTTPClientTransport(new URL(SERVER_URL), { requestInit: { headers: { Authorization: `Bearer ${API_KEY}`, }, }, }); const client = new Client({ name: "mewcp-client", version: "1.0.0" }); await client.connect(transport); const tools = await client.listTools(); console.log(tools.tools.map((t) => t.name)); ``` 1. Install: npm install @modelcontextprotocol/sdk 2. Copy the snippet into your project 3. Replace API_KEY with your key from the dashboard 4. Run with Node 18+ as an ES module (e.g. npx tsx script.ts)