{ "data": { "a": { "slug": "melius", "name": "Melius", "vendor": "Melius AI, Inc.", "vendorUrl": "https://www.melius.com", "kind": "http-api", "category": "design", "summary": "Melius is a hosted node-based canvas for generating images, video, audio and text with many third-party models. Outside agents read and write projects, canvases, nodes, edges, runs and comments through a REST API, an MCP server and the mel CLI.", "url": "https://www.anchorterminal.com/tools/melius", "markdownUrl": "https://www.anchorterminal.com/tools/melius.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/melius.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/melius.json", "license": "Proprietary service under Melius's terms of service. The mel CLI on npm is MIT, with no public source repository found", "transports": [ "http", "streamable-http" ], "remoteUrl": "https://api.melius.com/api/v1", "packages": [ { "registry": "npm", "name": "@melius-ai/cli" } ], "auth": "mixed", "authNotes": "A person creates an API key in the Melius app under Team settings, Integrations. The REST API, the CLI and the MCP endpoint at https://api.melius.com/mcp take it as a Bearer token, with an optional `x-team-id` header. The MCP endpoint at https://mcp.melius.com/mcp uses OAuth (authorisation code with S256 PKCE and dynamic client registration), where the user signs in, picks one team and Melius creates a connector key. Keys have no scopes. A key works with its creator's access and that user's role in each team. Access is self-serve, with no app review or sales approval.", "pricing": "freemium", "pricingNotes": "Free plan at $0 with trial credits, amount not published. Creator $20 a month for 20,000 credits, Growth $50 for 50,000, Professional $110 for 110,000, Team $70 a seat for 70,000 pooled credits (2 to 10 seats), Enterprise custom. Annual billing cuts 15 to 20 per cent. API, CLI and MCP calls have no separate charge and generations draw team credits. Per-model credit costs come from an authenticated endpoint, not the pricing page. The page's comparison table shows different figures ($18, $45, $99+, $63). Whether Free teams can create API keys is not stated (https://www.melius.com/pricing, checked 2026-10-08).", "priceSummary": "$20 / mo", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the API, MCP or CLI docs, the OpenAPI spec or the pricing page (checked 2026-10-08).", "endpoints": [] }, "toolCount": 75, "popularity": { "githubStars": null, "npmWeekly": 9, "pypiWeekly": null, "asOf": "2026-10-08" }, "docsUrl": "https://docs.melius.com", "llmsTxt": "https://docs.melius.com/llms.txt", "openapi": "https://docs.melius.com/api/openapi.json", "capabilities": [ "design.canvas", "design.comments", "design.files", "image.generate", "image.edit", "image.upscale", "video.generate", "speech.tts" ], "tags": [ "hosted", "freemium", "free-tier", "closed-source", "mcp", "oauth", "api-key", "openapi", "llms-txt", "cli", "async-jobs", "status-page", "pre-1.0" ], "lastRelease": "2026-09-10", "graded": true, "anchor": { "graded": true, "score": 54.1, "grade": "C", "agentReady": false, "rank": 621, "ranked": true, "rankOf": 842, "categoryRank": 3, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 51, "maintenance": 66, "payments": 20, "reliability": 69, "schema": 70, "security": 43, "transparency": 55 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-08" }, "negative": 0, "verdict": "One backend serves a 59-operation REST API with a public OpenAPI spec, a hosted MCP server with OAuth sign-in and a JSON-only CLI, and the status page shows no incidents since July 2026. API keys carry no scopes and work with their creator's role, and no rate-limit numbers, changelog or per-model credit prices are published.", "bestFor": "An agent producing batches of ad creative, product images or short videos on a shared canvas that people then review, with many models behind one key.", "strengths": [ "Public OpenAPI 3.0.2 spec with 59 operations, plus llms.txt, llms-full.txt and a Markdown copy of every docs page", "Hosted MCP server with OAuth sign-in (PKCE, dynamic client registration) or a bearer API key, tied to one team chosen at authorisation", "429 responses carry `Retry-After` and `retryAfterSeconds`, and the docs give a bounded retry policy", "The mel CLI prints JSON only, uses six fixed exit codes and returns errors with a `code` and a `suggestion`", "status.melius.com lists no incidents for Web app or MCP from July to October 2026" ], "weaknesses": [ "API keys have no scopes. A key works with its creator's role in every team the creator belongs to", "No rate-limit numbers, SLA, public changelog or API deprecation policy found in the reviewed documentation", "The MCP reference lists 75 tools, and the setup guide tells users to select Always Allow for all of them", "Per-model credit costs are returned by an authenticated endpoint and shown in the app, not on the pricing page", "No security.txt or disclosure policy found, and the Vanta trust centre at trust.melius.com needs JavaScript we couldn't run" ], "agentNotes": [ "Generate by creating a node on a canvas, starting a run with POST /nodes/{nodeId}/runs, then polling GET /node-runs/{nodeRunId} until `status` is finished or failed", "Over MCP, call `get_guide` first, `show_presence` before node changes and `canvas_plan_layout` before `bulk_create_nodes`", "On 429 wait `Retry-After` seconds. After a timeout or 5xx on a write, read the canvas or run state before resubmitting, because there are no idempotency keys", "Read credit costs from GET /generation/models?category=image before a bulk run. A 400 can mean the team is out of credits", "Downloads arrive as a ZIP from a signed URL. Fetch that URL without the `Authorization` header" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "C", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 54.1 } ], "editorialScores": { "ergonomics": 51, "maintenance": 66, "payments": 20, "reliability": 69, "schema": 70, "security": 43, "transparency": 38 }, "provenanceScore": 72 }, "connect": { "install": "npm install -g @melius-ai/cli", "http": "curl -s -H \"Authorization: Bearer $MEL_API_KEY\" https://api.melius.com/api/v1/teams", "claudeCode": "claude mcp add melius --transport http https://mcp.melius.com/mcp --scope user", "config": { "mcpServers": { "melius": { "url": "https://mcp.melius.com/mcp" } } } }, "letme": { "capability": "https://letme.dev/design.canvas", "tool": "https://letme.dev/melius" }, "area": "design-diagrams", "unitPrices": [ { "item": "Creator plan", "unit": "month", "usd": 20, "note": "20,000 credits a month, $17 a month on annual billing" }, { "item": "Growth plan", "unit": "month", "usd": 50, "note": "50,000 credits a month, $43 on annual billing" }, { "item": "Professional plan", "unit": "month", "usd": 110, "note": "110,000 credits a month, $93 on annual billing. A 300,000-credit option is also listed" }, { "item": "Team plan", "unit": "seat-month", "usd": 70, "note": "70,000 pooled credits a seat, 2 to 10 seats, $56 on annual billing" } ], "provenance": { "legalEntity": "Melius AI, Inc.", "domain": "melius.com", "domainRegistered": "1998-11-24", "endpointOnVendorDomain": true, "terms": "https://www.melius.com/terms", "privacy": "https://www.melius.com/privacy", "statusPage": "https://status.melius.com", "changelog": "", "securityTxt": "none", "checked": "2026-10-08", "notes": [ "The terms of service (effective 28 August 2026) name Melius AI, Inc., 420 Lexington Avenue, New York, as the contracting party and are governed by Delaware law.", "The API answers at api.melius.com, the OAuth MCP endpoint at mcp.melius.com and the docs at docs.melius.com, all melius.com subdomains.", "/.well-known/security.txt returns 404 on www.melius.com, docs.melius.com and api.melius.com.", "RDAP for melius.com gives a registration date of 1998-11-24, which predates the company. The site says it is not affiliated with other organisations that share the Melius name.", "No public changelog was found. docs.melius.com/changelog and www.melius.com/changelog return 404, and release dates come from the npm registry.", "trust.melius.com is a Vanta trust centre that renders only with JavaScript, so its contents were not read." ], "score": 72 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/melius.json", "live": { "slug": "melius", "probe": { "target": "https://api.melius.com/api/v1", "method": "get", "lastAt": "2026-10-09T09:26:56.573339179Z", "lastOk": true, "lastStatus": 404, "lastMs": 409, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 334, "p95ms24h": 375, "samples24h": 194, "samples30d": 194, "days": [ { "date": "2026-10-08", "probes": 93, "ok": 93 }, { "date": "2026-10-09", "probes": 101, "ok": 101 } ] }, "vendorStatus": { "page": "https://status.melius.com", "indicator": "none", "summary": "All Systems Operational", "checkedAt": "2026-10-09T09:25:18.254611316Z" }, "versions": [ { "registry": "npm", "name": "@melius-ai/cli", "version": "0.16.2", "seenAt": "2026-10-08T16:20:12.72497812Z" } ], "npmWeekly": 9, "securityTxt": { "url": "https://melius.com/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-08T15:38:50.537934736Z" }, "pages": [ { "url": "https://www.melius.com/pricing", "kind": "pricing", "status": 200, "checkedAt": "2026-10-08T18:29:07.616845141Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "e10be360cae0" }, { "url": "https://www.melius.com/privacy", "kind": "privacy", "status": 200, "checkedAt": "2026-10-08T18:29:09.848367293Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "1f3a2bb3eee9" }, { "url": "https://www.melius.com/terms", "kind": "terms", "status": 200, "checkedAt": "2026-10-08T18:29:11.947870163Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "a03166dbf644" } ], "updatedAt": "2026-10-09T09:26:56.573339179Z" } }, "answer": "Melius scores 54.1 (C) on agent readiness against pen.dev's 47.6 (D), and leads in 5 of 7 scored categories. pen.dev leads on agent ergonomics and payments \u0026 pricing.", "b": { "slug": "pen-dev", "name": "pen.dev", "vendor": "High Agency, Inc.", "vendorUrl": "https://pen.dev", "kind": "mcp", "category": "design", "summary": "Design canvas from High Agency, Inc. that stores designs as JSON `.pen` files. Agents edit them through a local MCP server in the desktop app or IDE extension, or through a headless CLI. It was called Pencil until 2026.", "url": "https://www.anchorterminal.com/tools/pen-dev", "markdownUrl": "https://www.anchorterminal.com/tools/pen-dev.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/pen-dev.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/pen-dev.json", "repo": "https://github.com/highagency/pen-desktop-releases", "license": "Proprietary. The CLI package on npm carries a proprietary licence file, and the apps fall under the vendor's EULA", "transports": [ "stdio" ], "packages": [ { "registry": "npm", "name": "@pen.dev/cli" } ], "auth": "mixed", "authNotes": "A pen.dev account is required for the desktop app, the extension and the CLI. The MCP server takes no credential of its own and reaches the signed-in app over a local socket, after the owner enables each client in Settings, MCP. The CLI signs in with `pen login` (email with password or one-time code) or with `PEN_CLI_KEY`, an organisation-scoped key created in Developer Keys on the web app. No key scopes are documented. Access is self-serve.", "pricing": "freemium", "pricingNotes": "Free plan at $0 with 5 agent days and 25 image or SVG generations a month, including the CLI, MCP access and personal developer keys, so an agent's owner can start without a contract. Pro is $16 and Ultra $48 a user a month, and Enterprise is priced on request. Model usage on the user's own provider key is billed by that provider (https://pen.dev/pricing, checked 2026-10-08).", "priceSummary": "$16 / seat-mo", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the docs, the pricing page or the CLI reference (checked 2026-10-08).", "endpoints": [] }, "toolCount": 6, "popularity": { "githubStars": null, "npmWeekly": 3548, "pypiWeekly": null, "asOf": "2026-10-08" }, "docsUrl": "https://docs.pen.dev", "capabilities": [ "design.files", "design.canvas", "design.components", "design.code" ], "tags": [ "local", "desktop", "cli", "headless", "mcp", "stdio", "closed-source", "freemium", "free-tier", "vscode", "design-to-code" ], "lastRelease": "2026-10-08", "graded": true, "anchor": { "graded": true, "score": 47.6, "grade": "D", "agentReady": false, "rank": 740, "ranked": true, "rankOf": 842, "categoryRank": 5, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 66, "maintenance": 59, "payments": 38, "reliability": 33, "schema": 61, "security": 33, "transparency": 53 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-08" }, "negative": 0, "verdict": "An agent can create, edit and export `.pen` designs without a GUI through the `pen` CLI, with four compact MCP tools that carry annotations and a documented JSON format. The software is closed and needs a pen.dev account. No changelog, status page or security contact was found, and 14 public issue reports had no reply on 8 October 2026.", "bestFor": "A coding agent that designs screens beside the code and keeps them in Git, including in CI.", "strengths": [ "Headless CLI (`@pen.dev/cli`) runs the same editor engine as the desktop app and exports PNG, JPEG, WEBP, PDF and HTML", "Four standard MCP tools with typed inputs and readOnlyHint and destructiveHint annotations, plus two conditional tools", "The `.pen` format is JSON with a published TypeScript schema, so designs sit in Git beside code", "Free plan includes the CLI, MCP access and personal developer keys, with five agent days a month", "Privacy policy has a retention table and says prompts sent with the user's own provider key never reach the vendor's servers" ], "weaknesses": [ "No changelog. The three desktop releases on GitHub have empty notes, and the format docs reserve the right to make breaking changes", "14 issues opened between 28 July and 6 October 2026 in highagency/pen-desktop-releases had no comment or closure on 8 October", "No status page, security.txt, disclosure policy, bug bounty or certification was found", "`execute` takes one JavaScript snippet and carries destructiveHint true, with no read-only mode for an external MCP client", "Closed source under a proprietary licence that forbids reverse engineering, and every surface needs a pen.dev account" ], "agentNotes": [ "Call `read_skill()`, then `read_skill({ path: \"pen-schema.md\" })` and `read_skill({ path: \"execute.md\" })` before the first `execute`. The tool description alone doesn't document the operations", "Call `get_app_state()` and confirm the active document before editing. The MCP server works on whichever `.pen` file is open in the app", "In headless `pen interactive`, call `save()` before `exit()`, and keep `--in` and `--out` on different paths to preserve the source", "Check that an export file exists. The docs say an export failure can print an error without a nonzero exit status", "In CI set `PEN_CLI_KEY` plus a provider key such as `ANTHROPIC_API_KEY`. Run `pen version`, since `pen --version` is not a flag" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "D", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 47.6 } ], "editorialScores": { "ergonomics": 66, "maintenance": 59, "payments": 38, "reliability": 33, "schema": 61, "security": 33, "transparency": 54 }, "provenanceScore": 51 }, "connect": { "install": "npm install -g @pen.dev/cli", "headless": { "command": "pen --out design.pen --prompt \"$TASK\"", "env": { "ANTHROPIC_API_KEY": "\u003ckey\u003e", "PEN_CLI_KEY": "\u003ckey starting pencil_cli_\u003e" } } }, "letme": { "capability": "https://letme.dev/design.files", "tool": "https://letme.dev/pen-dev" }, "area": "design-diagrams", "unitPrices": [ { "item": "Pro plan", "unit": "seat-month", "usd": 16, "note": "unlimited agent days, 350 image or SVG generations a month, up to 3 agents in parallel" }, { "item": "Ultra plan", "unit": "seat-month", "usd": 48, "note": "750 image or SVG generations a month, up to 6 agents in parallel" } ], "provenance": { "legalEntity": "High Agency, Inc.", "domain": "pen.dev", "domainRegistered": "2025-09-10", "endpointOnVendorDomain": true, "terms": "https://pen.dev/terms-of-use", "privacy": "https://pen.dev/privacy-policy", "statusPage": "", "changelog": "", "securityTxt": "none", "checked": "2026-10-08", "notes": [ "The terms of use, EULA and privacy policy, each effective 6 October 2026, name High Agency, Inc., 440 N Barranca Ave #2993, Covina, CA 91723, USA, and choose Delaware law.", "The terms of use cover the desktop app, web app, extensions and CLI and hold the billing terms. A separate EULA at https://pen.dev/eula governs the installed software and prevails for it where the two conflict.", "The MCP server is local. The CLI and app sign in against https://api.pen.dev, and the web app is app.pen.dev.", "RDAP gives pen.dev a registration date of 2025-09-10 with Name.com, and pencil.dev the same day with GoDaddy. www.pencil.dev now answers with the pen.dev site.", "pen.dev/.well-known/security.txt and /security.txt return 404. status.pen.dev, pen.dev/changelog and pen.dev/security return 404.", "The footer says the company is backed by a16z speedrun." ], "score": 51 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/pen-dev.json" }, "facts": [ { "a": "HTTP API", "b": "MCP server", "name": "Kind" }, { "a": "Melius AI, Inc.", "b": "High Agency, Inc.", "name": "Vendor" }, { "a": "https://api.melius.com/api/v1", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "HTTP, Streamable HTTP", "b": "stdio", "name": "Transports" }, { "a": "OAuth or key", "b": "OAuth or key", "name": "Auth" }, { "a": "Freemium", "b": "Freemium", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Proprietary service under Melius's terms of service. The mel CLI on npm is MIT, with no public source repository found", "b": "Proprietary. The CLI package on npm carries a proprietary licence file, and the apps fall under the vendor's EULA", "name": "Licence" }, { "a": "75", "b": "6", "name": "Tools exposed" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "no", "name": "llms.txt" }, { "a": "2026-09-10", "b": "2026-10-08", "name": "Last release" }, { "a": "no date given", "b": "2026-10-06", "name": "Terms last updated" }, { "a": "no date given", "b": "2026-10-06", "name": "Privacy policy last updated" }, { "a": "not found in the text", "b": "not found in the text", "name": "Customer content may train models" }, { "a": "yes", "b": "yes", "name": "Terms restrict automated access" }, { "a": "yes", "b": "yes", "name": "Terms restrict benchmarking" }, { "a": "yes", "b": "not found in the text", "name": "Terms or service can change without notice" }, { "a": "yes", "b": "not found in the text", "name": "Arbitration or class-action waiver" }, { "a": "9 npm/wk", "b": "3.5k npm/wk", "name": "Popularity" } ], "faq": [ { "answer": "Melius scores 54.1 (C) on agent readiness against pen.dev's 47.6 (D), and leads in 5 of 7 scored categories. pen.dev leads on agent ergonomics and payments \u0026 pricing.", "question": "Which is better for AI agents, Melius or pen.dev?" }, { "answer": "Both take an API key or an OAuth sign-in.", "question": "Do Melius and pen.dev need an API key?" }, { "answer": "Melius has a hosted endpoint at https://api.melius.com/api/v1. pen.dev runs on your own machine, with no hosted endpoint listed.", "question": "Can an agent call Melius and pen.dev without installing anything?" } ], "goodFor": [ { "aheadOn": [ "Reliability, 69 against 33", "Schema \u0026 documentation, 70 against 61", "Security \u0026 auth, 43 against 33", "Maintenance \u0026 community, 66 against 59" ], "also": [ "A hosted endpoint, with nothing to install" ], "goodFor": "An agent producing batches of ad creative, product images or short videos on a shared canvas that people then review, with many models behind one key.", "slug": "melius", "watchFor": "API keys have no scopes. A key works with its creator's role in every team the creator belongs to" }, { "aheadOn": [ "Agent ergonomics, 66 against 51", "Payments \u0026 pricing, 38 against 20" ], "also": [ "Runs on your own machine" ], "goodFor": "A coding agent that designs screens beside the code and keeps them in Git, including in CI.", "slug": "pen-dev", "watchFor": "No changelog. The three desktop releases on GitHub have empty notes, and the format docs reserve the right to make breaking changes" } ], "job": { "capability": "design.canvas", "name": "Design canvas" }, "others": [ { "json": "https://www.anchorterminal.com/compare/figma-mcp-vs-melius.json", "title": "Figma API + MCP vs Melius", "url": "https://www.anchorterminal.com/compare/figma-mcp-vs-melius" }, { "json": "https://www.anchorterminal.com/compare/figma-mcp-vs-pen-dev.json", "title": "Figma API + MCP vs pen.dev", "url": "https://www.anchorterminal.com/compare/figma-mcp-vs-pen-dev" }, { "json": "https://www.anchorterminal.com/compare/framer-vs-melius.json", "title": "Framer Server API vs Melius", "url": "https://www.anchorterminal.com/compare/framer-vs-melius" }, { "json": "https://www.anchorterminal.com/compare/framer-vs-pen-dev.json", "title": "Framer Server API vs pen.dev", "url": "https://www.anchorterminal.com/compare/framer-vs-pen-dev" }, { "json": "https://www.anchorterminal.com/compare/miro-vs-pen-dev.json", "title": "Miro API + MCP vs pen.dev", "url": "https://www.anchorterminal.com/compare/miro-vs-pen-dev" }, { "json": "https://www.anchorterminal.com/compare/pen-dev-vs-penpot.json", "title": "pen.dev vs Penpot API + MCP", "url": "https://www.anchorterminal.com/compare/pen-dev-vs-penpot" }, { "json": "https://www.anchorterminal.com/compare/melius-vs-miro.json", "title": "Melius vs Miro API + MCP", "url": "https://www.anchorterminal.com/compare/melius-vs-miro" }, { "json": "https://www.anchorterminal.com/compare/melius-vs-penpot.json", "title": "Melius vs Penpot API + MCP", "url": "https://www.anchorterminal.com/compare/melius-vs-penpot" } ], "scores": [ { "by": 36, "edge": "melius", "key": "reliability", "melius": 69, "name": "Reliability", "pen-dev": 33, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 9, "edge": "melius", "key": "schema", "melius": 70, "name": "Schema \u0026 documentation", "pen-dev": 61, "weight": 13 }, { "by": 15, "edge": "pen-dev", "key": "ergonomics", "melius": 51, "name": "Agent ergonomics", "pen-dev": 66, "weight": 13 }, { "by": 10, "edge": "melius", "key": "security", "melius": 43, "name": "Security \u0026 auth", "pen-dev": 33, "weight": 14 }, { "by": 18, "edge": "pen-dev", "key": "payments", "melius": 20, "name": "Payments \u0026 pricing", "pen-dev": 38, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 7, "edge": "melius", "key": "maintenance", "melius": 66, "name": "Maintenance \u0026 community", "pen-dev": 59, "weight": 7 }, { "by": 2, "edge": "melius", "key": "transparency", "melius": 55, "name": "Transparency \u0026 trust", "pen-dev": 53, "weight": 7 } ], "summary": "Melius scores 54.1 (C) on agent readiness against pen.dev's 47.6 (D), and leads in 5 of 7 scored categories. pen.dev leads on agent ergonomics and payments \u0026 pricing. Both do design canvas.", "verdicts": { "melius": "One backend serves a 59-operation REST API with a public OpenAPI spec, a hosted MCP server with OAuth sign-in and a JSON-only CLI, and the status page shows no incidents since July 2026. API keys carry no scopes and work with their creator's role, and no rate-limit numbers, changelog or per-model credit prices are published.", "pen-dev": "An agent can create, edit and export `.pen` designs without a GUI through the `pen` CLI, with four compact MCP tools that carry annotations and a documented JSON format. The software is closed and needs a pen.dev account. No changelog, status page or security contact was found, and 14 public issue reports had no reply on 8 October 2026." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/melius-vs-pen-dev", "json": "https://www.anchorterminal.com/compare/melius-vs-pen-dev.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/melius-vs-pen-dev.md", "slim": "https://www.anchorterminal.com/compare/melius-vs-pen-dev.min.md" }, "markdown": "Melius scores 54.1 (C) on agent readiness against pen.dev's 47.6 (D), and leads in 5 of 7 scored categories. pen.dev leads on agent ergonomics and payments \u0026 pricing. Both do design canvas.\n\n- Melius: grade C, 54.1/100, rank #621 of 842. Markdown https://www.anchorterminal.com/tools/melius.md · JSON https://www.anchorterminal.com/api/v1/tools/melius.json\n- pen.dev: grade D, 47.6/100, rank #740 of 842. Markdown https://www.anchorterminal.com/tools/pen-dev.md · JSON https://www.anchorterminal.com/api/v1/tools/pen-dev.json\n\n## Which one, for what\n\n### Melius (C)\n\nGood for: An agent producing batches of ad creative, product images or short videos on a shared canvas that people then review, with many models behind one key.\n\nAhead on:\n- Reliability, 69 against 33\n- Schema \u0026 documentation, 70 against 61\n- Security \u0026 auth, 43 against 33\n- Maintenance \u0026 community, 66 against 59\n\nAlso in its favour:\n- A hosted endpoint, with nothing to install\n\nWatch for: API keys have no scopes. A key works with its creator's role in every team the creator belongs to\n\n### pen.dev (D)\n\nGood for: A coding agent that designs screens beside the code and keeps them in Git, including in CI.\n\nAhead on:\n- Agent ergonomics, 66 against 51\n- Payments \u0026 pricing, 38 against 20\n\nAlso in its favour:\n- Runs on your own machine\n\nWatch for: No changelog. The three desktop releases on GitHub have empty notes, and the format docs reserve the right to make breaking changes\n\n\n## Score by category\n\n| Category | Weight | Melius | pen.dev | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 69 | 33 | Melius +36 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 70 | 61 | Melius +9 |\n| Agent ergonomics | 13% (16.2 this run) | 51 | 66 | pen.dev +15 |\n| Security \u0026 auth | 14% (17.5 this run) | 43 | 33 | Melius +10 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 20 | 38 | pen.dev +18 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 66 | 59 | Melius +7 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 55 | 53 | Melius +2 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **54.1 · C** | **47.6 · D** | |\n\n## Facts side by side\n\n| Fact | Melius | pen.dev |\n| --- | --- | --- |\n| Kind | HTTP API | MCP server |\n| Vendor | Melius AI, Inc. | High Agency, Inc. |\n| Hosted endpoint | `https://api.melius.com/api/v1` | no (local only) |\n| Transports | HTTP, Streamable HTTP | stdio |\n| Auth | OAuth or key | OAuth or key |\n| Pricing | Freemium | Freemium |\n| x402 | no | no |\n| Licence | Proprietary service under Melius's terms of service. The mel CLI on npm is MIT, with no public source repository found | Proprietary. The CLI package on npm carries a proprietary licence file, and the apps fall under the vendor's EULA |\n| Tools exposed | 75 | 6 |\n| Read-only variant documented | no | no |\n| llms.txt | yes | no |\n| Last release | 2026-09-10 | 2026-10-08 |\n| Terms last updated | no date given | 2026-10-06 |\n| Privacy policy last updated | no date given | 2026-10-06 |\n| Customer content may train models | not found in the text | not found in the text |\n| Terms restrict automated access | yes | yes |\n| Terms restrict benchmarking | yes | yes |\n| Terms or service can change without notice | yes | not found in the text |\n| Arbitration or class-action waiver | yes | not found in the text |\n| Popularity | 9 npm/wk | 3.5k npm/wk |\n\n## Verdicts\n\n**Melius.** One backend serves a 59-operation REST API with a public OpenAPI spec, a hosted MCP server with OAuth sign-in and a JSON-only CLI, and the status page shows no incidents since July 2026. API keys carry no scopes and work with their creator's role, and no rate-limit numbers, changelog or per-model credit prices are published.\n\n**pen.dev.** An agent can create, edit and export `.pen` designs without a GUI through the `pen` CLI, with four compact MCP tools that carry annotations and a documented JSON format. The software is closed and needs a pen.dev account. No changelog, status page or security contact was found, and 14 public issue reports had no reply on 8 October 2026.\n\n## Before you call either\n\n### Melius\n\n1. Generate by creating a node on a canvas, starting a run with POST /nodes/{nodeId}/runs, then polling GET /node-runs/{nodeRunId} until `status` is finished or failed\n2. Over MCP, call `get_guide` first, `show_presence` before node changes and `canvas_plan_layout` before `bulk_create_nodes`\n3. On 429 wait `Retry-After` seconds. After a timeout or 5xx on a write, read the canvas or run state before resubmitting, because there are no idempotency keys\n4. Read credit costs from GET /generation/models?category=image before a bulk run. A 400 can mean the team is out of credits\n5. Downloads arrive as a ZIP from a signed URL. Fetch that URL without the `Authorization` header\n\n### pen.dev\n\n1. Call `read_skill()`, then `read_skill({ path: \"pen-schema.md\" })` and `read_skill({ path: \"execute.md\" })` before the first `execute`. The tool description alone doesn't document the operations\n2. Call `get_app_state()` and confirm the active document before editing. The MCP server works on whichever `.pen` file is open in the app\n3. In headless `pen interactive`, call `save()` before `exit()`, and keep `--in` and `--out` on different paths to preserve the source\n4. Check that an export file exists. The docs say an export failure can print an error without a nonzero exit status\n5. In CI set `PEN_CLI_KEY` plus a provider key such as `ANTHROPIC_API_KEY`. Run `pen version`, since `pen --version` is not a flag\n\n## Questions\n\n### Which is better for AI agents, Melius or pen.dev?\n\nMelius scores 54.1 (C) on agent readiness against pen.dev's 47.6 (D), and leads in 5 of 7 scored categories. pen.dev leads on agent ergonomics and payments \u0026 pricing.\n\n### Do Melius and pen.dev need an API key?\n\nBoth take an API key or an OAuth sign-in.\n\n### Can an agent call Melius and pen.dev without installing anything?\n\nMelius has a hosted endpoint at https://api.melius.com/api/v1. pen.dev runs on your own machine, with no hosted endpoint listed.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/melius-vs-pen-dev.json, and with the fewest tokens: https://www.anchorterminal.com/compare/melius-vs-pen-dev.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"melius\", \"b\": \"pen-dev\"}`. From a terminal: `anchor compare melius pen-dev`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/melius.json and https://www.anchorterminal.com/api/v1/tools/pen-dev.json\n\n## Other comparisons with Melius or pen.dev\n\n- [Figma API + MCP vs Melius](https://www.anchorterminal.com/compare/figma-mcp-vs-melius.md)\n- [Figma API + MCP vs pen.dev](https://www.anchorterminal.com/compare/figma-mcp-vs-pen-dev.md)\n- [Framer Server API vs Melius](https://www.anchorterminal.com/compare/framer-vs-melius.md)\n- [Framer Server API vs pen.dev](https://www.anchorterminal.com/compare/framer-vs-pen-dev.md)\n- [Miro API + MCP vs pen.dev](https://www.anchorterminal.com/compare/miro-vs-pen-dev.md)\n- [pen.dev vs Penpot API + MCP](https://www.anchorterminal.com/compare/pen-dev-vs-penpot.md)\n- [Melius vs Miro API + MCP](https://www.anchorterminal.com/compare/melius-vs-miro.md)\n- [Melius vs Penpot API + MCP](https://www.anchorterminal.com/compare/melius-vs-penpot.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-09", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.4", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "Melius vs pen.dev", "url": "" } ], "description": "Melius scores 54.1 (C) on agent readiness against pen.dev's 47.6 (D), and leads in 5 of 7 scored categories. pen.dev leads on agent ergonomics and payments \u0026 pricing. Both do design canvas. Category scores, facts, verdicts and agent notes side by side.", "facts": [ "Melius C 54.1", "pen.dev D 47.6", "scores" ], "h1": "Melius vs pen.dev", "image": "https://www.anchorterminal.com/assets/og/compare-melius-vs-pen-dev.png", "path": "/compare/melius-vs-pen-dev", "published": "2026-10-01", "section": "tools", "title": "Melius vs pen.dev for AI agents, C 54.1 vs D 47.6 | Anchor Terminal", "toc": null, "updated": "2026-10-09", "url": "https://www.anchorterminal.com/compare/melius-vs-pen-dev" }, "tokens": { "markdown": 2050, "slim": 680 }, "version": 1 }