Aiterm MCP vs Next AI Draw IO
A side-by-side look at the Aiterm MCP and Next AI Draw IO MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Aiterm MCP for developer tools work as a local process; choose Next AI Draw IO for developer tools as a local process. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose Aiterm MCP when
- You need dedicated capabilities in the Developer Tools domain.
- You prefer a local stdio subprocess transport.
- You want tools like
diagnostics, pty_open, pty_send.
Choose Next AI Draw IO when
- You need dedicated capabilities in the Developer Tools domain.
- You prefer a local stdio subprocess transport.
- Its auth model fits you: API key required.
- You want tools like
get_drawing_guide, get_shape_library, start_session.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Developer Tools | Developer Tools |
| Quality signal | 64/100 · Good | 72/100 · Great |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | Not declared | API key required |
| Pricing | Not declared | BYOK (pay the provider) |
| Required env vars | None listed | None listed |
| Verified owner | Community listing | Community listing |
| GitHub stars | 6 | 36,373 |
| Directory activity | 1 views 0 installs 0 upvotes | 2 views 0 installs 0 upvotes |
| Tools | 18 | 16 |
| Full listing | View Aiterm MCP | View Next AI Draw IO |
Tools & capabilities
Aiterm MCP tools 18
diagnosticsFactory 向け read-only 診断。安全な状態語彙だけを機械可読 JSON で返す（PTY 内容・認証情報・path・環境値は返さない）。2つ目のtextは親配送hook（Claude Code・Cursor）の登録状態で、caller_status が setup_required なら呼出元からのagent送信は拒否される。aiterm-setup を実行する。pty_openローカル永続端末（POSIXはtmux、Windows nativeはpsmux 3.3.8以上）を1個開き、session_id を返す。backend server常駐ゆえ本サーバや クライアントが再起動してもセッションは生存する。リモート操作は専用ツールにせず、開いた端末の中で pty_send(session_id, "ssh host") と打って入る。pty_sendセッションへテキストを送る。通常PTYへは送信のみ（出力は pty_read で取得）。agent session（launcher起動）への送信はこのtoolだけで行い、子の状態はAitermが送る時点で見て振り分ける。子のturnが実行中なら各harness標準の操作で現在のturnへ差し込み（mode=agent_steer）、完了は差し込み後の作業の終わりに元の依頼への1回だけ届く。新しいevent_cursorと配送は作らない。それ以外は新しいturnとしてdispatchし（mode=agent_dispatch）、TUI の ready gate と submit 分離を通して即返り、receipt の event_cursor を返す。dispatch した子は投げっぱなしでよい＝親はここで待たない。Codex親とClaude Code親にはAitermが回答本文を自動配送する。parent_deliveryがある場合はwait起動も通常の回答回収も不要。親は作業を続けるかターンを終える。Cursor親にはparent_deliveryとwait_processが付く。作業を続ければ次のツール返りに回答が差し込まれ、ターンを終える前にwait_processを背景で起動するとidle中の完了でも起きられる。ポーリングとpty_read(agent_transcript:true)は不要。その他の親では、完了通知をreceiptの `wait_process.executable` と `wait_process.args` をそのまま親のターンを塞がない別プロセスAPIへ渡して受け、PowerShell 7のStart-Processだけは `windows_start_process_argument_list` を単一文字列として渡す。exit を完了通知として扱う（exit 0=done / 3=timeout（既定600秒・未完了） / 4=closed / 7=error（harnessの記録でturnがAPIエラー等で打ち切られた。結果は無い）。receiptのoutcomeが正で、done以外は未完了。ポーリング不要）。`wait_command` は人間向け互換表示でありprocess境界へ使わない。foreground実行で親のターンを塞がない。自動配送以外の結果回収は pty_read(agent_transcript:true)、Claude の durable turn は claude_turn を使う。require_agent:true はagent登録が無いsessionへ打鍵せず、AGENT_SESSION_REQUIREDで未送信を返す。preface はagent sessionへの送信で本文の前に置く1行。Claude Codeの席では貼り付けの印なしで入れ、本文だけを貼る（前置きが貼り付けの包みの外へ出る）。他のharnessでは前置き・空行・本文を1つで貼る。force:true は非Claude agent sessionへの手動介入用の素送信。aiterm相関付きClaudeの承認UIはclaude_approvalを使う。pty_readセッションの出力をトークン削減して読む（既定は前回読取位置からの増分）。削減: 制御文字除去 / 反復圧縮 / head+tail 折りたたみ＋復元ヒント＋メタ併記。agent_transcript:true は agent session の直近完了ターンの最終 assistant メッセージを公開されたharness記録から平文で返す。回答が空で終わったターンは誤りにせず、空のtextとanswer_empty:trueを返す。長い回答が screen tail で切れた時の回収用。pty_key制御キーを送る（C-c, C-d, Enter, Tab, Up, Down... の別名に対応）。acceptedは入力受付であり処理中断/会話維持の確認ではない。aiterm相関付きClaudeではC-cだけを許可し、承認UIはclaude_approvalで操作する。pty_closeセッションを閉じ、ログ／読取位置を破棄する。同じsession_idへの再試行は安全で、closed／already_closedのstructured receiptを返す。pty_list握っているセッション一覧（名前 / 現在の前面コマンド / attach 状態 / サイズ / agent 情報）。pty_observe指定sessionの存在、paneとharnessの生存、状態と理由、native process identity、画面変化とCPU活動を構造化して観測する。画面本文と生argvは返さない。agent_approvalCodexの現在の承認をinspectし、digestへ束縛した単発許可または拒否をrespondする。恒久許可は選ばない。Claudeは既存claude_approvalを使う。未知dialogはblockedのtyped errorで返す。claude_turnaiterm相関付きClaude sessionのdurable operationを構造化issue／recoverするmachine-caller専用面。pending／unknown／completedを人間向けerror文字列の解析なしで返し、Observer固有ロジックは持たない。claude_approvalaiterm相関付きClaudeのactive turn中に表示された権限確認UIを、turn相関を保ったまま検査・応答する専用面。inspectで画面digestと安全な単発Yes/Noだけを取得し、respondは同じoperation・同じdigestが現在も表示中の場合だけ送信する。agent_auth各harnessの公式CLI認証を開始・確認・取消する。CLIごとのコマンドと認証URL/codeの抽出はAitermが所有し、資格情報は各CLIだけが保存する。waitingのURL/codeを人へ表示し、input_requiredなら同じsessionのpty_send／pty_keyで公式画面へ入力する。authenticatedは認証の結果であり、agent_launchの起動準備完了とは別。remoteは他toolと同じ標準対応。startは公式の状態が認証済みなら何も起こさずauthenticatedを返す。relogin:trueを付けると、認証済みに見えても公式ログインを開始する（別のアカウントへ入り直す時、ログインの期限切れを状態から見抜けない時）。Aitermは資格情報を消さず、置き換えは公式CLIが行う。Codexの公式ログインは、始めた時点で元のログインを消す（途中でcancelしても戻らない）。- +6 more on the listing page
Next AI Draw IO tools 16
get_drawing_guideReturn the drawing guide: XML format, layout, edge routing, style and editing rules. start_session already returns it; call this only if the guide is no longer in your context. With topic, returns a short XML reference for tables, layers or groups.get_shape_libraryGet the style syntax and shape names of a draw.io icon library. Call this BEFORE drawing with cloud, network or other icon shapes, and use the exact names it returns; never guess them. Libraries: - Cloud: aws4, azure2, gcp2, alibaba_cloud, openstack, salesforce - Networking: cisco19, network, kubernetes, vvd, rack - Business: bpmn, lean_mapping - General: flowchart, basic, arrows2, infographic, sitemap - UI/Mockups: android, material_design - Enterprise: citrix, sap, mscae, atlassian - Engineering: fluidpower, electrical, pid, cabinets, floorplan - Icons: webiconsstart_sessionStart a new diagram session, or continue a saved one with session_id, and open the browser for real-time preview. Starts an embedded server and opens a browser window with draw.io. The browser will show diagram updates as they happen. The result includes the drawing guide; follow it when drawing.list_saved_diagramsList the diagrams saved by earlier sessions (auto-save files), newest first, with their pages. Continue one with start_session session_id=<id>; the file path also works with load_diagram.create_new_diagramCreate a NEW diagram, REPLACING the whole document: every page and any unsaved user changes (the previous state stays in History). To add a tab use add_page; to change cells use edit_diagram. Before using icon shapes (AWS, Azure, GCP, Kubernetes, Cisco...), call get_shape_library first. Follow the drawing guide returned by start_session (call get_drawing_guide if it is no longer in your context). Pass screenshot: true on the last call of a complex diagram to check the result. Accepted xml: 1) Only the mxCell elements of one page (recommended). The server adds <mxfile>, <mxGraphModel>, <root> and the root cells "0" and "1": <mxCell id="2" value="Shape" style="rounded=1;" x="40" y="40" w="120" h="60"/> 2) A bare <mxGraphModel> with <root> (one page). 3) A full <mxfile> with one or more <diagram> pages. Every page's <root> must start with <mxCell id="0"/><mxCell id="1" parent="0"/>. Rules: cells are siblings (never nested), ids are unique per page and start from "2", parent only for shapes inside a container, no XML comments, and shapes stay within x 0 to 800 and y 0 to 600. A style used by several cells is defined once with <mxStyle name="..." value="..."/> before the cells and used by name (see the drawing guide); html=1 and whiteSpace=wrap are added automatically. To clear the canvas to one blank page, send only the two root cells <mxCell id="0"/><mxCell id="1" parent="0"/>; the previous diagram stays in History.load_diagramLoad a .drawio diagram into the current session, REPLACING the entire diagram (all pages). To change an existing file, load it here, edit with edit_diagram, then export_diagram to the same path; never rewrite the file by hand. Provide ONE of two mutually exclusive sources: 'path' (the server reads the file from disk — you do NOT need to read the file yourself or pass its XML through create_new_diagram) or 'xml' (the raw file content you already have — from another tool, a repository read, or an API response — so no temporary file needs to be written first). Both accept plain XML and draw.io's compressed save format. .drawio.svg (Editable SVG, the format export_diagram writes) is accepted too; .png files (also draw.io's editable PNG) and plain .svg files cannot be loaded. After loading from 'path' (or from compressed 'xml'), call get_diagram before edit_diagram — you haven't seen the file's cell IDs yet. Plain-XML 'xml' content you supplied yourself is already known and can be edited immediately.edit_diagramEdit a specific page in the current diagram by ID-based operations (update/add/delete cells). All-or-nothing: if any operation fails, nothing is applied and every failure is listed. Freshness: the server remembers the last diagram state you have seen, and rejects this call only if the user edited the diagram in the browser since then. You do NOT need to call get_diagram before every edit: a rejected call changes nothing and includes the current XML of the page, so you can rebuild your operations and retry. Call get_diagram first only when you don't know the current diagram content (cell IDs, structure) — e.g. the diagram wasn't created in this conversation, or you're unsure your memory of it is accurate. Multi-page targeting: - page_id / page_name / page_index are optional; when all omitted, the FIRST page is targeted - Use list_pages to discover what pages exist Operations: - add: Add a new cell. Provide cell_id (new unique id within the page) and new_xml. One cell per operation. - update: Replace an existing cell by its id. Provide cell_id and complete new_xml. - delete: Remove a cell by its id. Only cell_id is needed. Its children and connected edges are deleted too, so give only a container's id. For add/update, new_xml is the complete mxCell (inside its <object> wrapper when it has custom data, see the drawing guide) in the compact form (a shape with x, y, w, h; an edge with source and target). No XML comments. Every " inside new_xml must be escaped as \" in the JSON. Example - Add a rectangle on the default (first) page: {"operations": [{"operation": "add", "cell_id": "rect-1", "new_xml": "<mxCell id=\"rect-1\" value=\"Hello\" style=\"rounded=1;\" x=\"100\" y=\"100\" w=\"120\" h=\"60\"/>"}]} Example - Delete a cell on the default page: {"operations": [{"operation": "delete", "cell_id": "rect-1"}]}get_diagramGet the current diagram XML (fetches latest from browser, including user's manual edits). Call this when you don't know the current diagram content (cell IDs, pages, structure) — e.g. before editing a diagram you didn't create in this conversation, or after edit_diagram was rejected because the user changed the diagram in the browser. Returns the full <mxfile> by default. If a page selector is provided, returns just that page's <mxGraphModel> embedded in a one-page <mxfile> wrapper.get_selectionReturn the cells the user has selected in the preview: their ids and labels, for edges the source and target ids, for shapes the position and size, and the page they are on. Call this when the user refers to what they selected ("this box", "these arrows", "the selected shapes"), then act on the ids with edit_diagram. Says when nothing is selected. Needs the preview tab to be open.screenshot_diagramRender the diagram in the preview and return it as a PNG image, so you can see your own result. Call this once after drawing or heavily editing a complex diagram, then fix overlaps and edges that cross shapes. Without a page selector it shows the page on screen; with one it renders that page without changing what the user sees. Needs the preview tab to be open.export_diagramExport the current diagram to a file. Supports .drawio (XML), .png, .svg, and .drawio.svg (an SVG with the diagram embedded, which draw.io and load_diagram can open again). The format is auto-detected from the file extension, or can be specified explicitly. Images get a 20 px margin; a PNG has a white background (or the page's own background color) unless transparent is true. Multi-page behaviour: - .drawio with NO page selector: writes the full <mxfile> (all pages). - .drawio with a page selector: writes a single-page <mxfile> containing only that page. - .png / .svg with NO page selector: exports the currently active page in the browser. - .png with a page selector: renders that page without changing what the user sees. - .svg / .drawio.svg with a page selector: temporarily loads that page into the browser, captures it, then restores the full document (the user sees a brief flicker).list_pagesList every page (tab) in the current diagram. Returns each page's id, name, 0-based index, and cell count. Use this to discover what pages exist before targeting one with edit_diagram, get_diagram, export_diagram, rename_page, or delete_page.- +4 more on the listing page
Ready-to-paste client configs
Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
Aiterm MCP
{
"mcpServers": {
"aiterm-mcp": {
"command": "npx",
"args": [
"-y",
"aiterm-mcp"
]
}
}
}
Next AI Draw IO
{
"mcpServers": {
"next-ai-draw-io": {
"command": "npx",
"args": [
"-y",
"@next-ai-drawio/mcp-server@latest"
]
}
}
}
Frequently asked questions
Aiterm MCP is categorized under Developer Tools and uses a local stdio subprocess. Next AI Draw IO belongs to Developer Tools and uses a local stdio subprocess. Pick Aiterm MCP for developer tools work and Next AI Draw IO for developer tools.
Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.
Aiterm MCP has no declared pricing — check the project's own site. Next AI Draw IO is bring-your-own-key: usage is billed by the API provider you supply a key for. Auth: api key required. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.
Yes. MCP clients support multiple servers: add aiterm-mcp and next-ai-draw-io as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Aiterm MCP has a quality signal of 64/100 (Good) with 1 views, 0 installs and 6 GitHub stars. Next AI Draw IO has 72/100 (Great) with 2 views, 0 installs and 36,373 GitHub stars.