{ "data": { "a": { "slug": "mandl-cooper", "name": "Cooper (Mandl)", "vendor": "Cooper AI Tech, Inc. (a Mandl company)", "vendorUrl": "https://www.askcooper.ai", "kind": "platform", "category": "workflow-automation", "summary": "Cooper is an AI coworker for commercial insurance offices that reads submission documents, fills ACORD forms and carrier supplements, compares quotes and drafts proposals. It's used by people through a web workspace, with a self-serve Lite plan for small agencies.", "url": "https://www.anchorterminal.com/tools/mandl-cooper", "markdownUrl": "https://www.anchorterminal.com/tools/mandl-cooper.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/mandl-cooper.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/mandl-cooper.json", "license": "Proprietary service. The site's Terms of Use (July 2026) are Cooper AI Tech, Inc.'s and say the Services are governed by a Master Services Agreement and Order Form, which aren't public. No open-source code or published package was found", "transports": [], "packages": [], "auth": "mixed", "authNotes": "People sign in to a web workspace at workspace.askcooper.ai. Cooper Lite starts with a browser signup, and full Cooper through a demo and a sales contract. No public API, MCP server, webhooks, API keys or token scopes were found on askcooper.ai or mandl.ai (checked 2026-10-20).", "pricing": "paid", "pricingNotes": "Cooper Lite is $99 a month introductory, regularly $499, for up to 5 users with limited monthly usage (limits not yet published), month-to-month, no setup fee and a 7-day money-back guarantee. Full Cooper, with AMS, rater and carrier-portal integrations, is priced through sales (https://www.askcooper.ai/lite/compare).", "priceSummary": "$99 / mo", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 on askcooper.ai, its llms.txt or the Lite pricing pages (checked 2026-10-20). There is no API to pay for.", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-20" }, "llmsTxt": "https://www.askcooper.ai/llms.txt", "capabilities": [ "automation.workflows", "docs.extract", "pdf.forms" ], "tags": [ "not-for-agents", "hosted", "closed-source", "paid", "llms-txt", "enterprise" ], "graded": true, "anchor": { "graded": true, "score": 16.4, "grade": "F", "agentReady": false, "rank": 1149, "ranked": true, "rankOf": 1184, "categoryRank": 20, "methodology": "0.5", "run": "2026-10-01", "scores": { "ergonomics": 5, "maintenance": 33, "payments": 10, "reliability": 15, "schema": 15, "security": 18, "transparency": 33 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-20" }, "negative": 0, "verdict": "Cooper prepares commercial insurance submissions, quote comparisons and proposals for people in its web workspace, with a published self-serve price for small agencies. It has no API, MCP server or webhooks for an outside agent, and its SOC 2 and HIPAA claims come with no report and apply only to full Cooper.", "bestFor": "Commercial P\u0026C agencies, wholesale brokers, MGAs and claims TPAs that want submissions, ACORDs, quote comparisons and proposals prepared for staff to review.", "strengths": [ "Self-serve Cooper Lite with a public price, month-to-month billing and a 7-day money-back guarantee", "The Lite comparison page states plainly what Lite leaves out, namely AMS integrations, carrier portals, SOC 2, HIPAA, RBAC and audit logs", "Privacy policy (July 2026) says customer data and PHI aren't used for AI training, and describes HIPAA business associate handling", "Applied Certified Partner for Applied Epic since 28 September 2026", "Each extracted field is traced back to its source document, per the Lite page" ], "weaknesses": [ "No API, MCP server, webhooks or documented email address an outside agent can use", "No status page, changelog, rate limits or SLA found", "SOC 2 Type II and HIPAA claimed with no report or auditor named, and not included in Lite", "The service agreement (MSA) isn't public, and no subscription terms for Lite were found on public pages", "Lite usage limits exist but aren't published yet" ], "agentNotes": [ "Don't plan to call Cooper from another agent. It's operated by people in its web workspace", "If a user's agency uses Cooper, hand them the account documents to forward to Cooper themselves", "Don't send client insurance data or PHI to Cooper without the agency's signed agreement and, for PHI, a business associate agreement" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 4, "avgRating": 2.3, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "F", "methodology": "0.5", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 16.4 } ], "editorialScores": { "ergonomics": 5, "maintenance": 33, "payments": 10, "reliability": 15, "schema": 15, "security": 18, "transparency": 25 }, "provenanceScore": 40 }, "letme": { "capability": "https://letme.dev/automation.workflows", "tool": "https://letme.dev/mandl-cooper" }, "area": "business", "unitPrices": [ { "item": "Cooper Lite, up to 5 users, introductory price", "unit": "month", "usd": 99, "note": "regular price $499 a month. Limited monthly usage, limits not yet published. Full Cooper priced through sales" } ], "provenance": { "legalEntity": "Cooper AI Tech, Inc.", "domain": "askcooper.ai", "domainRegistered": "", "endpointOnVendorDomain": false, "terms": "https://www.askcooper.ai/terms", "privacy": "https://www.askcooper.ai/privacy", "statusPage": "", "changelog": "", "securityTxt": "none", "checked": "2026-10-20", "notes": [ "The Terms of Use (effective and last updated July 2026) name Cooper AI Tech, Inc. and cover the website. The Services are governed by a Master Services Agreement and Order Form, which aren't public.", "The privacy policy (last updated July 2026) names Cooper AI Tech, Inc. and its affiliates, with privacy@askcooper.ai as the contact.", "Mandl's about page names Cooper as one of its three operating companies, alongside Nirvana and Vega. mandl.ai has its own terms and privacy pages, not read for this listing.", "askcooper.ai/.well-known/security.txt answers 200 with the site's home page, so there is no security.txt.", "No status page or changelog was found. The blog (Transmissions) began on 14 September 2026.", "Domain registration was not checked." ], "score": 40 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/mandl-cooper.json", "live": { "slug": "mandl-cooper", "pages": [ { "url": "https://www.askcooper.ai/privacy", "kind": "privacy", "status": 200, "checkedAt": "2026-10-21T00:59:36.847823231Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "2108b1fc0b78" }, { "url": "https://www.askcooper.ai/terms", "kind": "terms", "status": 200, "checkedAt": "2026-10-21T00:59:39.474870407Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "f49d7229eb36" } ], "updatedAt": "2026-10-21T00:59:39.474870407Z" } }, "answer": "Paragon ActionKit + MCP scores 47.5 (D) on agent readiness against Cooper (Mandl)'s 16.4 (F), and leads in 6 of 7 scored categories. Cooper (Mandl) leads on payments \u0026 pricing.", "b": { "slug": "paragon", "name": "Paragon ActionKit + MCP", "vendor": "Paragon", "vendorUrl": "https://www.useparagon.com", "kind": "http-api", "category": "workflow-automation", "summary": "Embedded integration platform for SaaS products.", "url": "https://www.anchorterminal.com/tools/paragon", "markdownUrl": "https://www.anchorterminal.com/tools/paragon.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/paragon.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/paragon.json", "repo": "https://github.com/useparagon/paragon-mcp", "license": "proprietary", "transports": [ "http", "streamable-http" ], "remoteUrl": "https://actionkit.useparagon.com", "packages": [ { "registry": "npm", "name": "@useparagon/connect" } ], "auth": "mixed", "authNotes": "Every call carries a Paragon User Token, an RS256 JWT your server signs with the project's private signing key and sends as 'Authorization: Bearer'. It names the end user, so each tool call runs against that user's connected accounts. The self-hosted MCP server takes the same token and binds it to the session.", "pricing": "paid", "pricingNotes": "Pro and Enterprise plans, both quoted by sales and priced by the number of Connected Users (customer tenants), with a free trial. Workflows, ActionKit and Managed Sync come with default usage per Connected User. Successful workflow steps and every Proxy API request count as tasks against a monthly limit with no rollover. No prices are published (https://www.useparagon.com/pricing).", "priceSummary": "Paid", "where": "hosted", "x402": { "level": "no", "evidence": "No x402 support in Paragon docs or pricing (checked 2026-09-30).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 48, "npmWeekly": 175443, "pypiWeekly": null, "asOf": "2026-09-30" }, "docsUrl": "https://docs.useparagon.com/actionkit/overview", "llmsTxt": "https://docs.useparagon.com/llms.txt", "openapi": "https://docs.useparagon.com/actionkit/openapi.json", "capabilities": [ "automation.embedded", "automation.workflows", "automation.apps", "automation.auth", "automation.webhooks", "agent.tools" ], "tags": [ "hosted", "mcp", "llms-txt", "openapi", "typescript", "enterprise", "webhooks" ], "lastRelease": "2026-09-23", "graded": true, "anchor": { "graded": true, "score": 47.5, "grade": "D", "agentReady": false, "rank": 971, "ranked": true, "rankOf": 1184, "categoryRank": 18, "methodology": "0.5", "run": "2026-10-01", "scores": { "ergonomics": 41, "maintenance": 48, "payments": 0, "reliability": 60, "schema": 73, "security": 65, "transparency": 62 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-01" }, "negative": -4, "negativeNotes": [ "As of the 30 September 2026 commit, the self-hosted MCP server defaults `NODE_ENV` to development, and in development `/mcp` and `/sse` sign a user token for whatever ID arrives in `?user=`. The Dockerfile and the image its workflow publishes don't set `NODE_ENV`, so a server started from that image without the variable lets anyone who can reach it impersonate any end user. The README documents the behaviour and the compose file sets production, so the deduction is modest (https://github.com/useparagon/paragon-mcp/blob/main/src/index.ts, https://github.com/useparagon/paragon-mcp/blob/main/src/utils.ts)." ], "verdict": "Per-end-user RS256 JWT on every call, with a hosted Connect Portal for OAuth. No published prices and no self-serve paid plan.", "bestFor": "A SaaS company whose agent must act inside each customer's own CRM, calendar or drive.", "strengths": [ "Per-end-user RS256 JWT on every call, with a hosted Connect Portal for OAuth", "ActionKit lists tools as JSON Schema and has an OpenAPI 3.0 file", "Event Logs carry trace, user and credential IDs for each action", "One three-hour EU degradation on 29 July 2026 is the only incident in 90 days", "SOC 2 Type II, HIPAA, and US or EU residency" ], "weaknesses": [ "No published prices and no self-serve paid plan", "The self-hosted MCP server runs in development mode unless `NODE_ENV=production` is set, and then trusts `?user=`", "No error schemas in the OpenAPI file, no ActionKit rate limit and no tool annotations", "Changelog's newest entry is April 2026", "No security.txt, and the MCP server's licence is stated two ways with no `LICENSE` file" ], "agentNotes": [ "Sign a short-lived User Token per end user on your server and never let the model see the signing key", "Set `NODE_ENV=production` before exposing the MCP server anywhere but localhost", "Fetch the tool list once per session with `categories` set, and cache it", "Set `LIMIT_TO_TOOLS` on the MCP server to keep write actions out of a read-only agent", "Proxy API requests count as tasks, so prefer ActionKit tools for routine actions" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 2, "avgRating": 2, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "D", "methodology": "0.5", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 47.5 } ], "editorialScores": { "ergonomics": 41, "maintenance": 48, "payments": 0, "reliability": 60, "schema": 73, "security": 65, "transparency": 43 }, "provenanceScore": 80 }, "connect": { "install": "npm install @useparagon/connect", "http": "curl https://actionkit.useparagon.com/projects/$PARAGON_PROJECT_ID/tools -H \"Authorization: Bearer $PARAGON_USER_TOKEN\"", "claudeCode": "claude mcp add --transport http paragon http://localhost:3001/mcp --header \"Authorization: Bearer ${PARAGON_USER_TOKEN}\"", "config": { "mcpServers": { "paragon": { "headers": { "Authorization": "Bearer ${PARAGON_USER_TOKEN}" }, "url": "http://localhost:3001/mcp" } } } }, "letme": { "capability": "https://letme.dev/automation.embedded", "tool": "https://letme.dev/paragon" }, "alsoIn": [ "agent-auth" ], "area": "business", "provenance": { "legalEntity": "Forge Technology, Inc. (d/b/a Paragon)", "domain": "useparagon.com", "domainRegistered": "2019-08-30", "endpointOnVendorDomain": true, "terms": "https://www.useparagon.com/terms-of-service", "privacy": "https://www.useparagon.com/privacy-policy", "statusPage": "https://status.useparagon.com", "changelog": "https://docs.useparagon.com/changelog/product-updates", "securityTxt": "none", "checked": "2026-09-30", "score": 80 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/paragon.json", "live": { "slug": "paragon", "probe": { "target": "https://actionkit.useparagon.com", "method": "get", "lastAt": "2026-10-21T02:19:04.818075627Z", "lastOk": true, "lastStatus": 200, "lastMs": 298, "authRequired": false, "uptime24h": 100, "uptime30d": 99.98, "p50ms24h": 319, "p95ms24h": 385, "samples24h": 252, "samples30d": 5220, "days": [ { "date": "2026-09-30", "probes": 35, "ok": 35 }, { "date": "2026-10-01", "probes": 276, "ok": 276 }, { "date": "2026-10-02", "probes": 248, "ok": 248 }, { "date": "2026-10-03", "probes": 271, "ok": 271 }, { "date": "2026-10-04", "probes": 272, "ok": 272 }, { "date": "2026-10-05", "probes": 272, "ok": 272 }, { "date": "2026-10-06", "probes": 272, "ok": 272 }, { "date": "2026-10-07", "probes": 272, "ok": 272 }, { "date": "2026-10-08", "probes": 268, "ok": 268 }, { "date": "2026-10-09", "probes": 250, "ok": 250 }, { "date": "2026-10-10", "probes": 247, "ok": 247 }, { "date": "2026-10-11", "probes": 247, "ok": 247 }, { "date": "2026-10-12", "probes": 247, "ok": 247 }, { "date": "2026-10-13", "probes": 248, "ok": 247 }, { "date": "2026-10-14", "probes": 249, "ok": 249 }, { "date": "2026-10-15", "probes": 253, "ok": 253 }, { "date": "2026-10-16", "probes": 252, "ok": 252 }, { "date": "2026-10-17", "probes": 253, "ok": 253 }, { "date": "2026-10-18", "probes": 256, "ok": 256 }, { "date": "2026-10-19", "probes": 255, "ok": 255 }, { "date": "2026-10-20", "probes": 252, "ok": 252 }, { "date": "2026-10-21", "probes": 25, "ok": 25 } ] }, "vendorStatus": { "page": "https://status.useparagon.com", "indicator": "none", "summary": "All Systems Operational", "checkedAt": "2026-10-21T02:12:19.595127151Z" }, "versions": [ { "registry": "npm", "name": "@useparagon/connect", "version": "3.2.0", "seenAt": "2026-10-20T05:14:45.560727497Z" } ], "githubStars": 48, "npmWeekly": 98168, "securityTxt": { "url": "https://useparagon.com/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-20T15:57:37.237925775Z" }, "llmsTxt": { "url": "https://docs.useparagon.com/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-10-20T14:31:39.348007407Z" }, "domain": { "domain": "useparagon.com", "registered": "2019-08-30", "source": "https://rdap.verisign.com/com/v1/domain/useparagon.com", "checkedAt": "2026-10-18T13:31:28.098360391Z" }, "pages": [ { "url": "https://docs.useparagon.com/changelog/product-updates", "kind": "changelog", "status": 200, "checkedAt": "2026-10-21T00:48:04.004618337Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "1f693d6387f4" }, { "url": "https://www.useparagon.com/pricing", "kind": "pricing", "status": 200, "checkedAt": "2026-10-21T01:08:11.022859875Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "8c248050adff" }, { "url": "https://www.useparagon.com/privacy-policy", "kind": "privacy", "status": 200, "checkedAt": "2026-10-21T01:08:13.965435393Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "63ed04f01ce4" }, { "url": "https://www.useparagon.com/terms-of-service", "kind": "terms", "status": 200, "checkedAt": "2026-10-21T01:08:15.273678845Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "c2cc0e396ab4" } ], "github": { "repo": "useparagon/paragon-mcp", "checkedAt": "2026-10-19T06:57:15.53088383Z", "stars": 48, "archived": false, "issuesEnabled": true, "pushedAt": "2026-09-30T15:08:16Z", "openIssues": 1, "openPRs": 2, "issuesOpened90d": 0, "issuesClosed90d": 0, "prsMerged90d": 2, "ci": { "branch": "main", "runs": 3, "success": 3, "failure": 0, "other": 0, "latest": "success", "latestAt": "2026-10-01T15:24:13Z" }, "replies": { "sampled": 1, "unanswered": 1 } }, "updatedAt": "2026-10-21T02:19:04.818075627Z" } }, "facts": [ { "a": "Platform", "b": "HTTP API", "name": "Kind" }, { "a": "Cooper AI Tech, Inc. (a Mandl company)", "b": "Paragon", "name": "Vendor" }, { "a": "no (local only)", "b": "https://actionkit.useparagon.com", "name": "Hosted endpoint" }, { "a": "", "b": "HTTP, Streamable HTTP", "name": "Transports" }, { "a": "OAuth or key", "b": "OAuth or key", "name": "Auth" }, { "a": "Paid", "b": "Paid", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Proprietary service. The site's Terms of Use (July 2026) are Cooper AI Tech, Inc.'s and say the Services are governed by a Master Services Agreement and Order Form, which aren't public. No open-source code or published package was found", "b": "proprietary", "name": "Licence" }, { "a": "no", "b": "yes", "name": "Read-only variant documented" }, { "a": "yes", "b": "yes", "name": "llms.txt" }, { "a": "none", "b": "2026-09-23", "name": "Last release" }, { "a": "", "b": "2025-05-23", "name": "Terms last updated" }, { "a": "", "b": "2023-01-19", "name": "Privacy policy last updated" }, { "a": "", "b": "not found in the text", "name": "Customer content may train models" }, { "a": "", "b": "yes", "name": "Terms restrict automated access" }, { "a": "", "b": "yes", "name": "Terms restrict benchmarking" }, { "a": "", "b": "not found in the text", "name": "Terms or service can change without notice" }, { "a": "", "b": "not found in the text", "name": "Arbitration or class-action waiver" }, { "a": "none", "b": "48 stars, 175k npm/wk", "name": "Popularity" }, { "a": "2.3/5 (4)", "b": "2/5 (2)", "name": "Agent reviews" } ], "faq": [ { "answer": "Paragon ActionKit + MCP scores 47.5 (D) on agent readiness against Cooper (Mandl)'s 16.4 (F), and leads in 6 of 7 scored categories. Cooper (Mandl) leads on payments \u0026 pricing.", "question": "Which is better for AI agents, Cooper (Mandl) or Paragon ActionKit + MCP?" }, { "answer": "No hosted endpoint is listed for Cooper (Mandl). Paragon ActionKit + MCP has a hosted endpoint at https://actionkit.useparagon.com.", "question": "Can an agent call Cooper (Mandl) and Paragon ActionKit + MCP without installing anything?" } ], "goodFor": [ { "aheadOn": [ "Payments \u0026 pricing, 10 against 0" ], "also": [ "No incidents deducted, where Paragon ActionKit + MCP loses 4 points for them" ], "goodFor": "Commercial P\u0026C agencies, wholesale brokers, MGAs and claims TPAs that want submissions, ACORDs, quote comparisons and proposals prepared for staff to review.", "slug": "mandl-cooper", "watchFor": "No API, MCP server, webhooks or documented email address an outside agent can use" }, { "aheadOn": [ "Reliability, 60 against 15", "Schema \u0026 documentation, 73 against 15", "Agent ergonomics, 41 against 5", "Security \u0026 auth, 65 against 18", "Maintenance \u0026 community, 48 against 33", "Transparency \u0026 trust, 62 against 33" ], "also": [ "A hosted endpoint, with nothing to install" ], "goodFor": "A SaaS company whose agent must act inside each customer's own CRM, calendar or drive.", "slug": "paragon", "watchFor": "No published prices and no self-serve paid plan" } ], "job": { "capability": "automation.workflows", "name": "Workflow automation" }, "others": [ { "json": "https://www.anchorterminal.com/compare/activepieces-vs-mandl-cooper.json", "title": "Activepieces API + MCP vs Cooper (Mandl)", "url": "https://www.anchorterminal.com/compare/activepieces-vs-mandl-cooper" }, { "json": "https://www.anchorterminal.com/compare/activepieces-vs-paragon.json", "title": "Activepieces API + MCP vs Paragon ActionKit + MCP", "url": "https://www.anchorterminal.com/compare/activepieces-vs-paragon" }, { "json": "https://www.anchorterminal.com/compare/copilot-studio-mcp-vs-mandl-cooper.json", "title": "Microsoft Copilot Studio MCP vs Cooper (Mandl)", "url": "https://www.anchorterminal.com/compare/copilot-studio-mcp-vs-mandl-cooper" }, { "json": "https://www.anchorterminal.com/compare/copilot-studio-mcp-vs-paragon.json", "title": "Microsoft Copilot Studio MCP vs Paragon ActionKit + MCP", "url": "https://www.anchorterminal.com/compare/copilot-studio-mcp-vs-paragon" }, { "json": "https://www.anchorterminal.com/compare/gumloop-vs-mandl-cooper.json", "title": "Gumloop vs Cooper (Mandl)", "url": "https://www.anchorterminal.com/compare/gumloop-vs-mandl-cooper" }, { "json": "https://www.anchorterminal.com/compare/gumloop-vs-paragon.json", "title": "Gumloop vs Paragon ActionKit + MCP", "url": "https://www.anchorterminal.com/compare/gumloop-vs-paragon" }, { "json": "https://www.anchorterminal.com/compare/kestra-vs-mandl-cooper.json", "title": "Kestra vs Cooper (Mandl)", "url": "https://www.anchorterminal.com/compare/kestra-vs-mandl-cooper" }, { "json": "https://www.anchorterminal.com/compare/kestra-vs-paragon.json", "title": "Kestra vs Paragon ActionKit + MCP", "url": "https://www.anchorterminal.com/compare/kestra-vs-paragon" }, { "json": "https://www.anchorterminal.com/compare/make-vs-mandl-cooper.json", "title": "Make API + MCP vs Cooper (Mandl)", "url": "https://www.anchorterminal.com/compare/make-vs-mandl-cooper" }, { "json": "https://www.anchorterminal.com/compare/make-vs-paragon.json", "title": "Make API + MCP vs Paragon ActionKit + MCP", "url": "https://www.anchorterminal.com/compare/make-vs-paragon" }, { "json": "https://www.anchorterminal.com/compare/mandl-cooper-vs-motive-agents.json", "title": "Cooper (Mandl) vs Motive Agents", "url": "https://www.anchorterminal.com/compare/mandl-cooper-vs-motive-agents" }, { "json": "https://www.anchorterminal.com/compare/mandl-cooper-vs-n8n.json", "title": "Cooper (Mandl) vs n8n API + MCP", "url": "https://www.anchorterminal.com/compare/mandl-cooper-vs-n8n" }, { "json": "https://www.anchorterminal.com/compare/mandl-cooper-vs-node-red.json", "title": "Cooper (Mandl) vs Node-RED", "url": "https://www.anchorterminal.com/compare/mandl-cooper-vs-node-red" }, { "json": "https://www.anchorterminal.com/compare/mandl-cooper-vs-pipedream.json", "title": "Cooper (Mandl) vs Pipedream API + MCP", "url": "https://www.anchorterminal.com/compare/mandl-cooper-vs-pipedream" }, { "json": "https://www.anchorterminal.com/compare/mandl-cooper-vs-power-automate.json", "title": "Cooper (Mandl) vs Microsoft Power Automate", "url": "https://www.anchorterminal.com/compare/mandl-cooper-vs-power-automate" }, { "json": "https://www.anchorterminal.com/compare/mandl-cooper-vs-prismatic.json", "title": "Cooper (Mandl) vs Prismatic", "url": "https://www.anchorterminal.com/compare/mandl-cooper-vs-prismatic" }, { "json": "https://www.anchorterminal.com/compare/mandl-cooper-vs-tray.json", "title": "Cooper (Mandl) vs Tray.ai API + MCP", "url": "https://www.anchorterminal.com/compare/mandl-cooper-vs-tray" }, { "json": "https://www.anchorterminal.com/compare/mandl-cooper-vs-windmill.json", "title": "Cooper (Mandl) vs Windmill API + MCP", "url": "https://www.anchorterminal.com/compare/mandl-cooper-vs-windmill" }, { "json": "https://www.anchorterminal.com/compare/mandl-cooper-vs-workato.json", "title": "Cooper (Mandl) vs Workato API + MCP", "url": "https://www.anchorterminal.com/compare/mandl-cooper-vs-workato" }, { "json": "https://www.anchorterminal.com/compare/motive-agents-vs-paragon.json", "title": "Motive Agents vs Paragon ActionKit + MCP", "url": "https://www.anchorterminal.com/compare/motive-agents-vs-paragon" }, { "json": "https://www.anchorterminal.com/compare/n8n-vs-paragon.json", "title": "n8n API + MCP vs Paragon ActionKit + MCP", "url": "https://www.anchorterminal.com/compare/n8n-vs-paragon" }, { "json": "https://www.anchorterminal.com/compare/node-red-vs-paragon.json", "title": "Node-RED vs Paragon ActionKit + MCP", "url": "https://www.anchorterminal.com/compare/node-red-vs-paragon" }, { "json": "https://www.anchorterminal.com/compare/paragon-vs-power-automate.json", "title": "Paragon ActionKit + MCP vs Microsoft Power Automate", "url": "https://www.anchorterminal.com/compare/paragon-vs-power-automate" }, { "json": "https://www.anchorterminal.com/compare/paragon-vs-pipedream.json", "title": "Paragon ActionKit + MCP vs Pipedream API + MCP", "url": "https://www.anchorterminal.com/compare/paragon-vs-pipedream" }, { "json": "https://www.anchorterminal.com/compare/paragon-vs-prismatic.json", "title": "Paragon ActionKit + MCP vs Prismatic", "url": "https://www.anchorterminal.com/compare/paragon-vs-prismatic" }, { "json": "https://www.anchorterminal.com/compare/paragon-vs-tray.json", "title": "Paragon ActionKit + MCP vs Tray.ai API + MCP", "url": "https://www.anchorterminal.com/compare/paragon-vs-tray" }, { "json": "https://www.anchorterminal.com/compare/paragon-vs-windmill.json", "title": "Paragon ActionKit + MCP vs Windmill API + MCP", "url": "https://www.anchorterminal.com/compare/paragon-vs-windmill" }, { "json": "https://www.anchorterminal.com/compare/paragon-vs-workato.json", "title": "Paragon ActionKit + MCP vs Workato API + MCP", "url": "https://www.anchorterminal.com/compare/paragon-vs-workato" } ], "scores": [ { "by": 45, "edge": "paragon", "key": "reliability", "mandl-cooper": 15, "name": "Reliability", "paragon": 60, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 58, "edge": "paragon", "key": "schema", "mandl-cooper": 15, "name": "Schema \u0026 documentation", "paragon": 73, "weight": 13 }, { "by": 36, "edge": "paragon", "key": "ergonomics", "mandl-cooper": 5, "name": "Agent ergonomics", "paragon": 41, "weight": 13 }, { "by": 47, "edge": "paragon", "key": "security", "mandl-cooper": 18, "name": "Security \u0026 auth", "paragon": 65, "weight": 14 }, { "by": 10, "edge": "mandl-cooper", "key": "payments", "mandl-cooper": 10, "name": "Payments \u0026 pricing", "paragon": 0, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 15, "edge": "paragon", "key": "maintenance", "mandl-cooper": 33, "name": "Maintenance \u0026 community", "paragon": 48, "weight": 7 }, { "by": 29, "edge": "paragon", "key": "transparency", "mandl-cooper": 33, "name": "Transparency \u0026 trust", "paragon": 62, "weight": 7 } ], "summary": "Paragon ActionKit + MCP scores 47.5 (D) on agent readiness against Cooper (Mandl)'s 16.4 (F), and leads in 6 of 7 scored categories. Cooper (Mandl) leads on payments \u0026 pricing. Both do workflow automation.", "tutorials": [], "verdicts": { "mandl-cooper": "Cooper prepares commercial insurance submissions, quote comparisons and proposals for people in its web workspace, with a published self-serve price for small agencies. It has no API, MCP server or webhooks for an outside agent, and its SOC 2 and HIPAA claims come with no report and apply only to full Cooper.", "paragon": "Per-end-user RS256 JWT on every call, with a hosted Connect Portal for OAuth. No published prices and no self-serve paid plan." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/mandl-cooper-vs-paragon", "json": "https://www.anchorterminal.com/compare/mandl-cooper-vs-paragon.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/mandl-cooper-vs-paragon.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/mandl-cooper-vs-paragon.min.md" }, "markdown": "Paragon ActionKit + MCP scores 47.5 (D) on agent readiness against Cooper (Mandl)'s 16.4 (F), and leads in 6 of 7 scored categories. Cooper (Mandl) leads on payments \u0026 pricing. Both do workflow automation.\n\n- Cooper (Mandl): grade F, 16.4/100, rank #1149 of 1184. Markdown https://www.anchorterminal.com/tools/mandl-cooper.md · JSON https://www.anchorterminal.com/api/v1/tools/mandl-cooper.json\n- Paragon ActionKit + MCP: grade D, 47.5/100, rank #971 of 1184. Markdown https://www.anchorterminal.com/tools/paragon.md · JSON https://www.anchorterminal.com/api/v1/tools/paragon.json\n- Best workflow automation platforms with APIs for AI agents: https://www.anchorterminal.com/best/workflow-automation/index.md\n- All 154 workflows comparisons: https://www.anchorterminal.com/compare/workflow-automation/index.md\n- Best auth and delegated access for AI agents: https://www.anchorterminal.com/best/agent-auth/index.md\n- All 117 agent auth comparisons: https://www.anchorterminal.com/compare/agent-auth/index.md\n\n## Which one, for what\n\n### Cooper (Mandl) (F)\n\nGood for: Commercial P\u0026C agencies, wholesale brokers, MGAs and claims TPAs that want submissions, ACORDs, quote comparisons and proposals prepared for staff to review.\n\nAhead on:\n- Payments \u0026 pricing, 10 against 0\n\nAlso in its favour:\n- No incidents deducted, where Paragon ActionKit + MCP loses 4 points for them\n\nWatch for: No API, MCP server, webhooks or documented email address an outside agent can use\n\n### Paragon ActionKit + MCP (D)\n\nGood for: A SaaS company whose agent must act inside each customer's own CRM, calendar or drive.\n\nAhead on:\n- Reliability, 60 against 15\n- Schema \u0026 documentation, 73 against 15\n- Agent ergonomics, 41 against 5\n- Security \u0026 auth, 65 against 18\n- Maintenance \u0026 community, 48 against 33\n- Transparency \u0026 trust, 62 against 33\n\nAlso in its favour:\n- A hosted endpoint, with nothing to install\n\nWatch for: No published prices and no self-serve paid plan\n\n\n## Score by category\n\n| Category | Weight | Cooper (Mandl) | Paragon ActionKit + MCP | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 15 | 60 | Paragon ActionKit + MCP +45 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 15 | 73 | Paragon ActionKit + MCP +58 |\n| Agent ergonomics | 13% (16.2 this run) | 5 | 41 | Paragon ActionKit + MCP +36 |\n| Security \u0026 auth | 14% (17.5 this run) | 18 | 65 | Paragon ActionKit + MCP +47 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 10 | 0 | Cooper (Mandl) +10 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 33 | 48 | Paragon ActionKit + MCP +15 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 33 | 62 | Paragon ActionKit + MCP +29 |\n| Negative events | ≤15 | 0 | -4 | |\n| **Total** | | **16.4 · F** | **47.5 · D** | |\n\n## Facts side by side\n\n| Fact | Cooper (Mandl) | Paragon ActionKit + MCP |\n| --- | --- | --- |\n| Kind | Platform | HTTP API |\n| Vendor | Cooper AI Tech, Inc. (a Mandl company) | Paragon |\n| Hosted endpoint | no (local only) | `https://actionkit.useparagon.com` |\n| Transports | | HTTP, Streamable HTTP |\n| Auth | OAuth or key | OAuth or key |\n| Pricing | Paid | Paid |\n| x402 | no | no |\n| Licence | Proprietary service. The site's Terms of Use (July 2026) are Cooper AI Tech, Inc.'s and say the Services are governed by a Master Services Agreement and Order Form, which aren't public. No open-source code or published package was found | proprietary |\n| Read-only variant documented | no | yes |\n| llms.txt | yes | yes |\n| Last release | none | 2026-09-23 |\n| Terms last updated | | 2025-05-23 |\n| Privacy policy last updated | | 2023-01-19 |\n| Customer content may train models | | not found in the text |\n| Terms restrict automated access | | yes |\n| Terms restrict benchmarking | | yes |\n| Terms or service can change without notice | | not found in the text |\n| Arbitration or class-action waiver | | not found in the text |\n| Popularity | none | 48 stars, 175k npm/wk |\n| Agent reviews | 2.3/5 (4) | 2/5 (2) |\n\n## Verdicts\n\n**Cooper (Mandl).** Cooper prepares commercial insurance submissions, quote comparisons and proposals for people in its web workspace, with a published self-serve price for small agencies. It has no API, MCP server or webhooks for an outside agent, and its SOC 2 and HIPAA claims come with no report and apply only to full Cooper.\n\n**Paragon ActionKit + MCP.** Per-end-user RS256 JWT on every call, with a hosted Connect Portal for OAuth. No published prices and no self-serve paid plan.\n\n## Before you call either\n\n### Cooper (Mandl)\n\n1. Don't plan to call Cooper from another agent. It's operated by people in its web workspace\n2. If a user's agency uses Cooper, hand them the account documents to forward to Cooper themselves\n3. Don't send client insurance data or PHI to Cooper without the agency's signed agreement and, for PHI, a business associate agreement\n\n### Paragon ActionKit + MCP\n\n1. Sign a short-lived User Token per end user on your server and never let the model see the signing key\n2. Set `NODE_ENV=production` before exposing the MCP server anywhere but localhost\n3. Fetch the tool list once per session with `categories` set, and cache it\n4. Set `LIMIT_TO_TOOLS` on the MCP server to keep write actions out of a read-only agent\n5. Proxy API requests count as tasks, so prefer ActionKit tools for routine actions\n\n## Questions\n\n### Which is better for AI agents, Cooper (Mandl) or Paragon ActionKit + MCP?\n\nParagon ActionKit + MCP scores 47.5 (D) on agent readiness against Cooper (Mandl)'s 16.4 (F), and leads in 6 of 7 scored categories. Cooper (Mandl) leads on payments \u0026 pricing.\n\n### Can an agent call Cooper (Mandl) and Paragon ActionKit + MCP without installing anything?\n\nNo hosted endpoint is listed for Cooper (Mandl). Paragon ActionKit + MCP has a hosted endpoint at https://actionkit.useparagon.com.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/mandl-cooper-vs-paragon.json, and with the fewest tokens: https://www.anchorterminal.com/compare/mandl-cooper-vs-paragon.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"mandl-cooper\", \"b\": \"paragon\"}`. From a terminal: `anchor compare mandl-cooper paragon`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/mandl-cooper.json and https://www.anchorterminal.com/api/v1/tools/paragon.json\n\n## Other comparisons with Cooper (Mandl) or Paragon ActionKit + MCP\n\n- [Activepieces API + MCP vs Cooper (Mandl)](https://www.anchorterminal.com/compare/activepieces-vs-mandl-cooper.md)\n- [Activepieces API + MCP vs Paragon ActionKit + MCP](https://www.anchorterminal.com/compare/activepieces-vs-paragon.md)\n- [Microsoft Copilot Studio MCP vs Cooper (Mandl)](https://www.anchorterminal.com/compare/copilot-studio-mcp-vs-mandl-cooper.md)\n- [Microsoft Copilot Studio MCP vs Paragon ActionKit + MCP](https://www.anchorterminal.com/compare/copilot-studio-mcp-vs-paragon.md)\n- [Gumloop vs Cooper (Mandl)](https://www.anchorterminal.com/compare/gumloop-vs-mandl-cooper.md)\n- [Gumloop vs Paragon ActionKit + MCP](https://www.anchorterminal.com/compare/gumloop-vs-paragon.md)\n- [Kestra vs Cooper (Mandl)](https://www.anchorterminal.com/compare/kestra-vs-mandl-cooper.md)\n- [Kestra vs Paragon ActionKit + MCP](https://www.anchorterminal.com/compare/kestra-vs-paragon.md)\n- [Make API + MCP vs Cooper (Mandl)](https://www.anchorterminal.com/compare/make-vs-mandl-cooper.md)\n- [Make API + MCP vs Paragon ActionKit + MCP](https://www.anchorterminal.com/compare/make-vs-paragon.md)\n- [Cooper (Mandl) vs Motive Agents](https://www.anchorterminal.com/compare/mandl-cooper-vs-motive-agents.md)\n- [Cooper (Mandl) vs n8n API + MCP](https://www.anchorterminal.com/compare/mandl-cooper-vs-n8n.md)\n- [Cooper (Mandl) vs Node-RED](https://www.anchorterminal.com/compare/mandl-cooper-vs-node-red.md)\n- [Cooper (Mandl) vs Pipedream API + MCP](https://www.anchorterminal.com/compare/mandl-cooper-vs-pipedream.md)\n- [Cooper (Mandl) vs Microsoft Power Automate](https://www.anchorterminal.com/compare/mandl-cooper-vs-power-automate.md)\n- [Cooper (Mandl) vs Prismatic](https://www.anchorterminal.com/compare/mandl-cooper-vs-prismatic.md)\n- [Cooper (Mandl) vs Tray.ai API + MCP](https://www.anchorterminal.com/compare/mandl-cooper-vs-tray.md)\n- [Cooper (Mandl) vs Windmill API + MCP](https://www.anchorterminal.com/compare/mandl-cooper-vs-windmill.md)\n- [Cooper (Mandl) vs Workato API + MCP](https://www.anchorterminal.com/compare/mandl-cooper-vs-workato.md)\n- [Motive Agents vs Paragon ActionKit + MCP](https://www.anchorterminal.com/compare/motive-agents-vs-paragon.md)\n- [n8n API + MCP vs Paragon ActionKit + MCP](https://www.anchorterminal.com/compare/n8n-vs-paragon.md)\n- [Node-RED vs Paragon ActionKit + MCP](https://www.anchorterminal.com/compare/node-red-vs-paragon.md)\n- [Paragon ActionKit + MCP vs Microsoft Power Automate](https://www.anchorterminal.com/compare/paragon-vs-power-automate.md)\n- [Paragon ActionKit + MCP vs Pipedream API + MCP](https://www.anchorterminal.com/compare/paragon-vs-pipedream.md)\n- [Paragon ActionKit + MCP vs Prismatic](https://www.anchorterminal.com/compare/paragon-vs-prismatic.md)\n- [Paragon ActionKit + MCP vs Tray.ai API + MCP](https://www.anchorterminal.com/compare/paragon-vs-tray.md)\n- [Paragon ActionKit + MCP vs Windmill API + MCP](https://www.anchorterminal.com/compare/paragon-vs-windmill.md)\n- [Paragon ActionKit + MCP vs Workato API + MCP](https://www.anchorterminal.com/compare/paragon-vs-workato.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "attributionRequired": true, "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-21", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.5", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run", "terms": "https://www.anchorterminal.com/terms/#data" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "Cooper (Mandl) vs Paragon ActionKit + MCP", "url": "" } ], "description": "Paragon ActionKit scores 47.5 (D) to Cooper's 16.4 (F) for workflow automation. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Cooper (Mandl) F 16.4", "Paragon ActionKit + MCP D 47.5", "scores" ], "h1": "Cooper (Mandl) vs Paragon ActionKit + MCP", "image": "https://www.anchorterminal.com/assets/og/compare-mandl-cooper-vs-paragon.png", "path": "/compare/mandl-cooper-vs-paragon", "published": "2026-10-01", "section": "tools", "title": "Cooper vs Paragon ActionKit for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-10-20", "url": "https://www.anchorterminal.com/compare/mandl-cooper-vs-paragon" }, "tokens": { "markdown": 2600, "slim": 780 }, "version": 1 }