Agent Field Kit
Search, price and buy field-tested agent-ops kits (evals, security, runbooks) via Stripe checkout.
我該用這個嗎
品質與安全性
根據工具定義與協定合規性的自動化分析。
上下文成本
這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高，可用於其他工作的注意力就越少。
安裝
一鍵安裝
將以下內容加入你的 `claude_desktop_config.json` 檔案：
{
"mcpServers": {
"kits": {
"url": "https://agentfieldkit.com/mcp"
}
}
}遠端端點
https://agentfieldkit.com/mcpstreamable-http它能做什麼
工具清單
工具（12）
🟢search_products(query, type, limit)
Search Agent Field Kit templates, bundles and licenses by keyword. Read-only.
輸入結構描述
{
"type": "object",
"properties": {
"query": {
"type": "string",
"maxLength": 200
},
"type": {
"type": "string",
"enum": [
"template",
"bundle",
"license"
]
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 20
}
},
"additionalProperties": false
}🟢get_product(id)
Get one Agent Field Kit product by id. Read-only.
輸入結構描述
{
"type": "object",
"properties": {
"id": {
"type": "string",
"enum": [
"cost-roi-calculator",
"eval-test-plan",
"incident-runbooks",
"vendor-security-questionnaire",
"afk-cyber-bundle-pro-year",
"cyber-defense-bundle",
"mcp-tool-access-review",
"prompt-injection-test-pack",
"agent-observability-starter",
"agent-security-audit-kit",
"realtime-agent-monitoring-kit",
"ai-slop-editing-kit",
"secrets-rotation-kit",
"approval-gates-kit",
"eu-ai-act-transparency-kit",
"mcp-server-auth-kit",
"agent-skill-authoring-kit",
"ai-supply-chain-defense-kit",
"inference-key-abuse-kit",
"ci-registry-credential-kit",
"oauth-grant-revocation-kit",
"cyber-defense-dashboard-kit",
"full-kit",
"team-license"
]
}
},
"required": [
"id"
],
"additionalProperties": false
}🟡create_checkout(product_id, email, agent_name)
Create a Stripe-hosted checkout for one Agent Field Kit product and return its URL. Does NOT charge anything: a human, or an agent with explicit payment authority, must pay on the returned page. Prices: single template $29 (Agent Security Audit Kit $79), full kit of the 4 original templates $79, team license (10 users) $199. 14-day no-questions refunds. Returns 'checkout_not_open' until checkout launches.
輸入結構描述
{
"type": "object",
"properties": {
"product_id": {
"type": "string",
"enum": [
"cost-roi-calculator",
"eval-test-plan",
"incident-runbooks",
"vendor-security-questionnaire",
"afk-cyber-bundle-pro-year",
"cyber-defense-bundle",
"mcp-tool-access-review",
"prompt-injection-test-pack",
"agent-observability-starter",
"agent-security-audit-kit",
"realtime-agent-monitoring-kit",
"ai-slop-editing-kit",
"secrets-rotation-kit",
"approval-gates-kit",
"eu-ai-act-transparency-kit",
"mcp-server-auth-kit",
"agent-skill-authoring-kit",
"ai-supply-chain-defense-kit",
"inference-key-abuse-kit",
"ci-registry-credential-kit",
"oauth-grant-revocation-kit",
"cyber-defense-dashboard-kit",
"full-kit",
"team-license"
]
},
"email": {
"type": "string",
"description": "Buyer email for the receipt (optional)"
},
"agent_name": {
"type": "string",
"maxLength": 100,
"description": "Name of the purchasing agent/app (optional, analytics only)"
}
},
"required": [
"product_id"
],
"additionalProperties": false
}🟢request_kit(topics, idea, tier, email, notify, ...)
Tell Agent Field Kit which new kit you (or the person you act for) would most want to buy. Pick topics and/or describe an idea; optional price tier. Email is optional and only used to notify when a matching kit ships; include it only with that person's consent. Max 5 requests/hour.
輸入結構描述
{
"type": "object",
"properties": {
"topics": {
"type": "array",
"items": {
"type": "string",
"enum": [
"eu-ai-act-readiness",
"agent-privacy-dpia",
"rag-quality-eval",
"human-escalation-design",
"multi-agent-testing",
"model-selection-scorecard",
"agent-slo-sla",
"support-agent-playbook",
"agent-cost-chargeback",
"other"
]
},
"maxItems": 10
},
"idea": {
"type": "string",
"maxLength": 1000
},
"tier": {
"type": "string",
"enum": [
"29",
"79",
"199",
"not_sure"
]
},
"email": {
"type": "string"
},
"notify": {
"type": "boolean"
},
"agent_name": {
"type": "string",
"maxLength": 100
}
},
"additionalProperties": false
}⚪vote_agent_poll(choices, other, agent_name)
Vote in Agent Field Kit's poll 'Which AI agent platforms do you use regularly?' on behalf of the person you act for, only with their consent and with their real answer. Multi-select. Returns live results after voting. Self-selected, not a scientific sample. Max 3 votes/day per network.
輸入結構描述
{
"type": "object",
"properties": {
"choices": {
"type": "array",
"items": {
"type": "string",
"enum": [
"openclaw",
"grok-bot",
"chatgpt-dots",
"muse",
"instinct",
"claude-cowork",
"gemini-spark",
"microsoft-copilot",
"manus",
"other",
"none"
]
},
"minItems": 1,
"maxItems": 11
},
"other": {
"type": "string",
"maxLength": 80
},
"agent_name": {
"type": "string",
"maxLength": 100
}
},
"required": [
"choices"
],
"additionalProperties": false
}🟢get_cyber_advisories(since, component, limit)
Sourced cyber-defense advisories (free: headlines from the last 30 days; subscribers: full detail and history) affecting AI agent stacks (platforms, packages, frameworks, consumer bots). Read-only. Filter by date (YYYY-MM-DD) and/or component (e.g. 'litellm', 'railway', 'grok-bot', 'package:pypi/litellm').
輸入結構描述
{
"type": "object",
"properties": {
"since": {
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$"
},
"component": {
"type": "string",
"maxLength": 80
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 50
}
},
"additionalProperties": false
}🟢check_my_stack(components)
Given the components an agent runs on (frameworks, bots, platforms, packages with optional versions), return matching advisories (AFK intel plus live OSV.dev, which includes GitHub Security Advisories, for packages with an ecosystem or version), free steps first, relevant kits, and per-component coverage (matched / covered_no_match / not_covered). PREMIUM (Bearer API key). Read-only; inputs are not stored. Package entries may be 'name==version' (PyPI style).
輸入結構描述
{
"type": "object",
"properties": {
"components": {
"type": "array",
"items": {
"type": "string",
"maxLength": 80
},
"minItems": 1,
"maxItems": 50
}
},
"required": [
"components"
],
"additionalProperties": false
}🟢get_hardening_checklist(stack)
PREMIUM (Bearer API key). Hardening checklist for one agent stack: key rotation, connector/OAuth revocation, plugin/skill review, approval gates, logging, with config surfaces and a verification level. Independent guidance; no vendor affiliation.
輸入結構描述
{
"type": "object",
"properties": {
"stack": {
"type": "string",
"enum": [
"grok-bot",
"openclaw",
"instinct",
"muse",
"openai-dots",
"chatgpt",
"claude",
"cursor",
"goose",
"n8n",
"manus",
"devin",
"replit-agent",
"lindy",
"zapier-agents",
"gemini-spark",
"claude-duet",
"langchain",
"crewai",
"autogen",
"openai-agents-sdk",
"litellm-proxy",
"dspy",
"mcp-client"
]
}
},
"required": [
"stack"
],
"additionalProperties": false
}🟢get_cyber_dashboard_data(components, since)
PREMIUM (Bearer API key). Full advisory dataset plus stack index and kit versions, for the Cyber Defense Dashboard kit to auto-update. Optional components: also returns check_my_stack results (AFK intel + live OSV.dev / GitHub advisories) and per-component coverage. Read-only; inputs are not stored.
輸入結構描述
{
"type": "object",
"properties": {
"components": {
"type": "array",
"items": {
"type": "string",
"maxLength": 80
},
"maxItems": 50
},
"since": {
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$"
}
},
"additionalProperties": false
}🟢changes_since(since, limit)
Free. What's new or updated in Agent Field Kit's cyber-defense advisories since a date (YYYY-MM-DD or ISO UTC). Returns headlines plus next_since: store it and pass it on your next scheduled poll so you only fetch changes. Read-only.
輸入結構描述
{
"type": "object",
"properties": {
"since": {
"type": "string",
"maxLength": 30
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 100
}
},
"required": [
"since"
],
"additionalProperties": false
}🟢get_advisory(id)
Get one advisory by id. Free: headline, free first steps and sources. Subscribers (Bearer key): full detail plus a fix-it brief (patch status, fixed version, am I affected, exact steps, how to verify, matching kit). Read-only.
輸入結構描述
{
"type": "object",
"properties": {
"id": {
"type": "string",
"maxLength": 100
}
},
"required": [
"id"
],
"additionalProperties": false
}🟢search_advisories(query, limit)
Keyword search over Agent Field Kit cyber-defense advisories (e.g. 'litellm', 'mcp oauth', 'railway'). Free: headlines. Subscribers: full detail and fix-it briefs. Read-only.
輸入結構描述
{
"type": "object",
"properties": {
"query": {
"type": "string",
"maxLength": 200
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 25
}
},
"required": [
"query"
],
"additionalProperties": false
}社群
證據