ARC 1 vs Next AI Draw IO
A side-by-side look at the ARC 1 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 ARC 1 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 ARC 1 when
- You need dedicated capabilities in the Developer Tools domain.
- You prefer a local stdio subprocess transport.
- Its auth model fits you: other.
- You want tools like
SAPRead, SAPSearch, SAPNavigate.
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 | 63/100 · Good | 73/100 · Great |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | other | API key required |
| Pricing | Free | BYOK (pay the provider) |
| Required env vars | None listed | None listed |
| Verified owner | Community listing | Community listing |
| GitHub stars | 238 | 36,403 |
| Directory activity | 0 views 0 installs 0 upvotes | 7 views 0 installs 0 upvotes |
| Tools | 9 | 16 |
| Full listing | View ARC 1 | View Next AI Draw IO |
Tools & capabilities
ARC 1 tools 9
SAPReadRead SAP ABAP source, metadata and syntax results. For source purpose, explanations, specs, reviews or pre-change context, prefer SAPContext first. DDIC metadata: omit format (default text); structured is CLAS-only for ordinary reads. TABLE_QUERY: multi-column filters, data preview required; CDS needs SAP_BASIS 752+. TABLE_CONTENTS: single-column filter. INACTIVE_OBJECTS: no name. TABL/DTT: technical settings. SYNTAX: read-only SAP check (objectType+name, optional source for unsaved text). CLAS: method="*" for signatures, method="NAME" for one body, or grep. Global class declaration/implementation: MAIN (omit include). definitions/implementations contain local helpers.SAPSearchSearch for ABAP objects, exact object-directory entries, or source code. Modes: 1. Object search (default): name pattern with wildcards (*); returns type, name, package, description, ADT URI. 2. TADIR lookup (searchType="tadir_lookup"): exact cross-package lookup of one or more names (prefer over long SAPQuery TADIR IN-lists). 3. Source code search (searchType="source_code"): full-text search across source (SAP_BASIS ≥ 7.51). Tips: BOR objects appear as SOBJ; the uri field feeds SAPNavigate, objectType feeds SAPRead/SAPWrite/SAPActivate. Searches object NAMES only — for field names use SAPRead(type='DDLS', include='elements') or SAPQuery on DD03L.SAPNavigateNavigate code: definitions, references, completion, hierarchy. references: where-used objects by default; detail=positions/snippets adds bounded native usages; objectType filters results (e.g. CLAS/OC, PROG/P); type+name replaces uri. hierarchy queries SEOMETAREL for superclass/interfaces/direct subclasses: requires data/SQL opt-in + matching scope; otherwise inspect class MAIN with SAPRead. CDS (DDLS) impact: SAPContext(action="impact") classifies where-used into RAP buckets. Experimental relations: dependency maps or package neighborhoods, then selected reads. Consumer locations: references; objectType="CLAS/OC" for class-only; otherwise omit. Active metadata, not source-call/runtime proof. Coverage unknown. type+name required, no uri/source.SAPLintRun local abaplint rules on ABAP/CDS source (auto-selects cloud or on-prem rules by system type). Actions: - "lint": check source (errors+warnings) for ABAP (PROG/CLAS/INTF/FUNC) and CDS (DDLS). - "lint_and_fix": lint + auto-fix fixable issues (keyword case, obsolete statements); returns fixed source. - "list_rules": list rules + current config (no source). - "format": pretty-print via SAP's ADT formatter (needs source). - "get_formatter_settings" / "set_formatter_settings": read/update the system's global PrettyPrinter (indentation bool, style keywordUpper|keywordLower|keywordAuto|none; set is blocked read-only). lint/lint_and_fix/list_rules run locally; format/*_formatter_settings call SAP. Syntax: SAPRead(type="SYNTAX"); ATC/unit tests: SAPDiagnose.SAPDiagnoseABAP diagnostics: - "syntax": check objects[] (CLAS/INTF/PROG/DDLS; version active/inactive). Single: prefer SAPRead SYNTAX. - "unittest": harmless ABAP Unit for CLAS/PROG/FUGR or DEVC (exact; includeSubpackages recurses). - "unittest_ci": harmless package tests with source reconciliation; empty/incomplete runs fail. - "atc": ATC (name+type or objects [{type,name}], max 20). Omit variant for system default; unknown variant errors. "atc_variants": read variants/default, optional variant name filter. - "atc_ci": package ATC CI; requires available API and verified selection. - "cds_testcases": read suggested CDS Unit tests (name; SAP_BASIS 8.16+). - "object_state": active/inactive ETags/hashes/divergence (name+type; CLAS includes). No server-driven types. - "quickfix": proposals: name+type+source+line; optional column/sourceUri. - "apply_quickfix": text deltas, no save; quickfix inputs + proposalUri/proposalUserContent. - "dumps": ST22, newest: user/from/to/maxResults/filters; id=detail. - "feed_schema": optional dump filters; action only. - "traces": list profiler traces; id+analysis analyzes one. - "trace_start": arm NEXT matching execution (write; defaults HTTP, SQL on); reproduce, then read "traces". - "trace_requests": list armed traces. "trace_cancel": cancel by id (write). - "system_messages": list SM02 messages. "gateway_errors": list /IWFND/ERROR_LOG (on-prem; detailUrl or id+errorType for detail). - "odata_perf": read OData timing (url: host-relative; DB/ABAP/framework/auth); needs allowDataPreview. - "authorization_trace": read STUSERTRACE/SUAUTHVALTRC (on-prem; needs SAP_ALLOW_DATA_PREVIEW). - "cds_sql": read CDS native SQL (name). - "sql_trace_state" / "set_sql_trace_state" (sqlOn; needs SAP_ALLOW_WRITES) / "sql_trace_directory": ST05 SQL-trace control. Quickfix: syntax/ATC → quickfix → apply_quickfix → SAPWrite.SAPContextPrimary tool for understanding ABAP/CDS objects before specs, reviews, explanations, or changes — use instead of SAPRead when the user asks what an object does. Returns intent first (the object KTD when available) then compressed dependency contracts. Use SAPRead after SAPContext for exact source/method bodies/grep/drafts. Decision rule — pick the action from the user's question: - "What breaks if I change <CDS>?" / "Who consumes <I_*>?" / "Blast radius" → action="impact" (DDLS only). - "Which includes/appends extend <TABL>?" → action="structure", type="TABL". - "What does <object> do?" / "Explain" / "deps before editing" → action="deps" (default); type+name required. - "Find all callers of <object>" → action="usages" (live SAP where-used lookup). impact (CDS blast-radius): upstream AST deps + downstream where-used, classified into RAP buckets (projectionViews, bdefs, serviceDefinitions, serviceBindings, accessControls, metadataExtensions, abapConsumers, documentation, tables, other) + sibling-consistency hints. Use this instead of text-scanning DDDDLSRC/ACMDCLSRC with SAPQuery (it filters the noise). Optional includeIndirect, siblingCheck, siblingMaxCandidates. deps: target KTD when available + selected dependency contracts, derived from source (not SAP-native relationships or a complete inventory). Counts distinguish root candidates from recursive attempts. Standard helper names are filtered. For CDS, includes dependency DDL/field catalogs for cl_cds_test_environment. structure (TABL only): the DDIC include/append tree. Non-CDS reverse-lookup: SAPNavigate(references); CDS: impact. Full detail: docs_page SAPContext.SAPManageProbe and report SAP system capabilities. Use BEFORE operations that depend on optional features (abapGit, RAP/CDS, AMDP, HANA, UI5/Fiori, CTS transports, FLP). Also handles package (DEVC) lifecycle. Actions: - "features": cached feature status (fast, no round-trip; id, available, mode, probedAt). "probe": re-probe now (feature probes + auth + discovery refresh). "cache_stats": object cache health. - "create_package" / "delete_package" / "change_package": DEVC lifecycle via ADT packages API. - FLP read: flp_list_catalogs, flp_list_groups, flp_list_tiles (catalogId). FLP write: flp_create_catalog, flp_create_group, flp_create_tile, flp_add_tile_to_group, flp_delete_catalog. Classic designer tile/target-mapping model, deprecated since S/4HANA 2023; Work Zone exposure v2 needs LADIs (SAPRead type=UIAD). - "set_api_state": release/revoke an object's API release contract (objectUri, or name+objectType; apiState defaults RELEASED, contract defaults C1 — C0 for SRVD, C3 for classic views). Write counterpart of SAPRead(type="API_STATE"). Returns features + systemType ("onprem"/"btp"); "available: false" means do NOT attempt dependent operations.SAPTransportManage CTS transport requests (SE09/SE10). Actions: list (current user, modifiable), get (tasks + objects), create (always a Workbench (K) request — the package/target sets target & layer, not the request category; optional explicit target), release, delete, remove_object (keep the request), reassign (change owner), release_recursive (tasks then parent), check (does a package need a transport — type, name, package), history (legacy name: current object lock plus assignment candidates — type, name; not complete transport history; read-only, no write scope needed). IDs look like A4HK900123. Status: D/L=modifiable, O/P=releasing, R/N=released.SAPGitGit reads and gated abapGit workflows. gCTS mutations are quarantined. abapGit mutations need write/Git gates and allowedPackages ROOT/** or *; clone/pull evidence is unverified. external_info is gated HTTPS SAP egress.
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.
ARC 1
{
"mcpServers": {
"arc-1-2": {
"command": "npx",
"args": [
"-y",
"arc-1@latest"
]
}
}
}
Next AI Draw IO
{
"mcpServers": {
"next-ai-draw-io": {
"command": "npx",
"args": [
"-y",
"@next-ai-drawio/mcp-server@latest"
]
}
}
}
Frequently asked questions
ARC 1 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 ARC 1 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.
ARC 1 is listed as free. Auth: other. 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 arc-1-2 and next-ai-draw-io as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, ARC 1 has a quality signal of 63/100 (Good) with 0 views, 0 installs and 238 GitHub stars. Next AI Draw IO has 73/100 (Great) with 7 views, 0 installs and 36,403 GitHub stars.