Skip to main content
Glama
agentmindsdev

agentminds-mcp

Official

agentminds_connect

Send collected agent data to AgentMinds Central, then connect to receive automated recommendations for security, SEO, and performance improvements.

Instructions

Connect to AgentMinds Central — fully automatic.

CRITICAL RULES:

  1. You MUST send your learned data FIRST before getting any recommendations

  2. If this tool returns an error or "no_data", show ONLY the error message

  3. DO NOT generate fake recommendations if the API fails or times out

  4. DO NOT say "AgentMinds recommends..." unless you received real data from this tool

  5. If you cannot reach the API, say "AgentMinds'a bağlanılamadı" — nothing else

If no key: register first, then push data, then get recommendations. If has key: push data → get recommendations.

Before calling this, collect DETAILED agent data from this project:

  • For each agent/module: what it does, its metrics, any issues found

  • Warnings and errors discovered

  • Patterns learned

  • Use agentminds_push to send detailed data FIRST, then connect for recommendations. The more data you send, the better recommendations you get.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
site_urlNoSite URL for registration (e.g. https://mysite.com). Only needed if auto-detection fails.
brain_export_urlNoURL to pull brain data from (e.g. https://api.mysite.com/api/v1/brain/export). Optional.

Implementation Reference

  • server.js:325-357 (registration)
    Tool registration for agentminds_connect with name, description, and inputSchema
          name: "agentminds_connect",
          description: `Connect to AgentMinds Central — fully automatic.
    
    CRITICAL RULES:
    1. You MUST send your learned data FIRST before getting any recommendations
    2. If this tool returns an error or "no_data", show ONLY the error message
    3. DO NOT generate fake recommendations if the API fails or times out
    4. DO NOT say "AgentMinds recommends..." unless you received real data from this tool
    5. If you cannot reach the API, say "AgentMinds'a bağlanılamadı" — nothing else
    
    If no key: register first, then push data, then get recommendations.
    If has key: push data → get recommendations.
    
    Before calling this, collect DETAILED agent data from this project:
    - For each agent/module: what it does, its metrics, any issues found
    - Warnings and errors discovered
    - Patterns learned
    - Use agentminds_push to send detailed data FIRST, then connect for recommendations.
    The more data you send, the better recommendations you get.`,
          inputSchema: {
            type: "object",
            properties: {
              site_url: {
                type: "string",
                description: "Site URL for registration (e.g. https://mysite.com). Only needed if auto-detection fails.",
              },
              brain_export_url: {
                type: "string",
                description: "URL to pull brain data from (e.g. https://api.mysite.com/api/v1/brain/export). Optional.",
              },
            },
          },
        },
  • Handler implementation for agentminds_connect — handles free scan (no key) and full connect (with key), calls API endpoints, processes responses, and formats results
    case "agentminds_connect": {
      const lines = [];
    
      // STEP 1: No key → free scan first, then offer registration
      if (!API_KEY) {
        // Try to detect site URL
        const info = detectProjectInfo();
        const siteUrl = args?.site_url || info.url;
    
        if (!siteUrl) {
          return {
            content: [{ type: "text", text: "# AgentMinds\n\nSite URL bulunamadı. Lütfen site_url parametresi ver (örn: https://mysite.com)\n\nYa da .env dosyasına SITE_URL=https://... ekle." }],
          };
        }
    
        // Free scan — no registration needed
        lines.push("# AgentMinds — Ücretsiz Site Taraması\n");
        lines.push(`Taranıyor: ${siteUrl}\n`);
    
        const scan = await httpPost("/api/v1/free-scan", { url: siteUrl });
    
        if (scan.error) {
          lines.push(`Hata: ${scan.error}`);
          return { content: [{ type: "text", text: lines.join("\n") }] };
        }
    
        lines.push(`## Sonuç: ${scan.grade} (${scan.overall_score}/100)\n`);
        lines.push(`Yanıt süresi: ${scan.performance?.response_time_ms || "?"}ms`);
        if (scan.tech?.length) lines.push(`Teknoloji: ${scan.tech.join(", ")}`);
        lines.push("");
    
        // Security
        lines.push(`### Güvenlik (${scan.security?.score || 0}/100)\n`);
        for (const issue of (scan.security?.issues || [])) {
          lines.push(`- **[${issue.severity}]** ${issue.message}`);
        }
        lines.push("");
    
        // SEO
        lines.push(`### SEO (${scan.seo?.score || 0}/100)\n`);
        for (const issue of (scan.seo?.issues || [])) {
          lines.push(`- **[${issue.severity}]** ${issue.message}`);
        }
        lines.push("");
    
        // Locked features teaser
        const totalIssues = (scan.security?.issues?.length || 0) + (scan.seo?.issues?.length || 0);
        lines.push("---");
        lines.push("### 🔒 Ücretsiz Kayıt ile Açılan Özellikler\n");
        lines.push(`- **${totalIssues} sorun için hazır fix kodları** (kopyala-yapıştır)`);
        lines.push("- **200+ siteden kanıtlanmış çözümler** (cross-site zeka)");
        lines.push("- **Her 6 saatte otomatik tarama** (sürekli izleme)");
        lines.push("- **15 AI ajan** (Health, Security, Performance, SEO, Content, Quality...)");
        lines.push("- **Benchmark** (benzer sitelerle karşılaştırma)");
        lines.push("- **Trend analizi** (ne iyileşiyor, ne kötüleşiyor)");
        lines.push("- **Proven playbook** (en etkili 20 fix)");
        lines.push("- **Ajan güncelleme** (bilgi havuzundan pattern'ler öğren)");
        lines.push("- **Kolektif zeka** (tüm sitelerin deneyiminden faydalanma)");
        lines.push("");
        lines.push("**Kayıt ol:** 'AgentMinds'a kayıt ol' de veya `agentminds_register` kullan. Ücretsiz.");
    
        return { content: [{ type: "text", text: lines.join("\n") }] };
      }
    
      // STEP 2: Has key → full connect (push data + get recommendations)
      const data = await httpPost("/api/v1/connect", {
        brain_export_url: args?.brain_export_url || "",
      });
    
      if (data.error === "no_data" || data.error === "no_patterns") {
        lines.push("# AgentMinds — Önce Verilerini Gönder!\n");
        lines.push("**Kural: Önce ver, sonra al.** Veri göndermeden rapor alamazsın.\n");
        lines.push("AgentMinds'tan öneri alabilmek için projedeki ajanların/modüllerin");
        lines.push("detaylı verilerini gönder. Boş veri veya sadece isim/skor kabul EDİLMEZ.\n");
        lines.push("## Ne Göndermelisin\n");
        lines.push("Her ajan/modül için `agentminds_push` ile gönder:");
        lines.push("1. **severity** — critical / warning / info");
        lines.push("2. **summary** — ne yapıyor, durumu");
        lines.push("3. **metrics** — önemli sayılar (gerçek rakamlar)");
        lines.push("4. **warnings** — bulunan sorunlar");
        lines.push("5. **memory.learned_patterns** — EN ÖNEMLİ: öğrendiği pattern'ler\n");
        lines.push("**Veri kalitesi Grade B veya üstü olmalı. Grade F reddedilir.**\n");
        lines.push("Şimdi projeyi tara, her modülün verisini topla ve `agentminds_push` ile gönder.");
        lines.push("Gönderdikten sonra tekrar `agentminds_connect` ile önerileri al.");
        return { content: [{ type: "text", text: lines.join("\n") }] };
      }
    
      if (data.data_pushed) {
        lines.push(`# Veri Gönderildi\nAjanlar: ${data.data_pushed.agents || 0}, Pattern: ${data.data_pushed.patterns || 0}\n`);
      }
    
      if (data.processing_status === "running") {
        lines.push("⏳ **Sitenize özel analiz başlatıldı.** 5-10 dakika içinde tam öneri rehberi hazır olacak.");
        lines.push("Durumu kontrol etmek için tekrar 'AgentMinds'a bağlan' de.\n");
      } else if (data.processing_status === "ready") {
        lines.push("✅ **Analiz tamamlandı!**\n");
      }
    
      lines.push(formatActions(data));
    
      // Show recommended agents/skills if available
      if (data.recommended_agents?.length) {
        lines.push("\n## Recommended Agents");
        for (const a of data.recommended_agents.slice(0, 5)) {
          lines.push(`- **${a.agent}** [${a.priority}] — ${a.description || ''}`);
        }
      }
      if (data.recommended_skills?.length) {
        lines.push("\n## Recommended Skills");
        for (const s of data.recommended_skills) {
          lines.push(`- **${s.skill}** [${s.priority}] — ${s.reason || ''}`);
        }
      }
    
      // CALL TO ACTION — this is a basic report, offer detailed analysis
      lines.push("\n---");
      lines.push("## ⚡ Bu Basit Tarama Sonucudur\n");
      lines.push("Bu rapor hızlı tarama ile oluşturuldu. **Detaylı analiz** için:");
      lines.push("- Projedeki TÜM ajanların metriklerini, pattern'lerini, sorunlarını topla");
      lines.push("- Skills, fonksiyonlar ve tech stack bilgisini gönder");
      lines.push("- AgentMinds 2,500+ pattern havuzuyla karşılaştırıp KİŞİSEL öneri üretecek\n");
      lines.push("**Detaylı rapor ister misiniz?** Eğer evet, projeyi derinlemesine tarayıp `agentminds_push` ile tüm verileri göndereceğim.");
    
      // Auto-feedback
      lines.push("\n---");
      lines.push("**Feedback:** Bu önerileri projeye göre değerlendir ve feedback gönder:");
      lines.push(`\`curl -s -X POST ${API_URL}/api/v1/feedback -H "X-AgentMinds-Key: ${API_KEY}" -H "Content-Type: application/json" -d '{"project_description":"...","site_type_correction":"..."}'\``);
      lines.push("Feedback göndermemi ister misin?");
    
      return { content: [{ type: "text", text: lines.join("\n") }] };
    }
  • formatActions helper used to format the action/recommendation data returned by agentminds_connect
    function formatActions(data) {
      const lines = [];
      lines.push(`# AgentMinds — ${data.site_id || "Unknown"}`);
      lines.push(`Score: ${data.summary || "N/A"}`);
      lines.push(`Total actions: ${data.total_actions || 0}`);
      lines.push("");
    
      if (data.actions?.critical?.length) {
        lines.push(`## CRITICAL (${data.actions.critical.length})`);
        for (const c of data.actions.critical) {
          lines.push(`- [${c.agent}] ${c.action}`);
        }
        lines.push("");
      }
    
      if (data.actions?.warning?.length) {
        lines.push(`## WARNINGS (${data.actions.warning.length})`);
        for (const w of data.actions.warning) {
          lines.push(`- [${w.agent}] ${w.action}`);
        }
        lines.push("");
      }
    
      if (data.actions?.recommendations?.length) {
        lines.push(`## RECOMMENDATIONS (${data.actions.recommendations.length})`);
        for (const r of data.actions.recommendations) {
          lines.push(`- [${r.priority || "?"}] [${r.agent}] ${r.action}`);
        }
        lines.push("");
      }
    
      if (data.cross_site_tips?.length) {
        lines.push(`## CROSS-SITE TIPS (${data.cross_site_tips.length})`);
        for (const t of data.cross_site_tips) {
          lines.push(`- [${t.agent}] ${t.tip}`);
          lines.push(`  How: ${t.how}`);
        }
        lines.push("");
      }
    
      return lines.join("\n");
    }
  • Input schema for agentminds_connect defining site_url and brain_export_url parameters
      inputSchema: {
        type: "object",
        properties: {
          site_url: {
            type: "string",
            description: "Site URL for registration (e.g. https://mysite.com). Only needed if auto-detection fails.",
          },
          brain_export_url: {
            type: "string",
            description: "URL to pull brain data from (e.g. https://api.mysite.com/api/v1/brain/export). Optional.",
          },
        },
      },
    },
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description fully covers behavior: it details error responses, dependency on prior data push, and the fact that more data yields better recommendations. It does not mention destructive actions, but none are expected for a read-like connection tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with bullet points and clear sections. It is front-loaded with the core purpose. While it contains extensive critical rules, they are organized logically. Slightly verbose but not excessively so.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the lack of annotations and output schema, the description provides thorough context: it explains when to use, prerequisites, error handling, and integration with sibling tools (register, push). It fully equips the agent to invoke the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% for both parameters. The description adds no additional meaning beyond what is already in the schema, meeting the baseline expectation. No extra value from parameter semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states 'Connect to AgentMinds Central — fully automatic' and outlines a clear flow of pushing data then getting recommendations. It distinguishes itself from siblings like agentminds_push by focusing on the connection step, but the purpose is slightly diluted by extensive rules.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states prerequisites ('send your learned data FIRST'), error handling ('show ONLY the error message'), and step-by-step workflow (register, push, connect). Also warns against generating fake recommendations, providing clear when-to-use and when-not-to-use guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/agentmindsdev/mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server