Add tempguru event staffing tool plugin

tools/tempguru/PRIVACY.md

@@ -0,0 +1,37 @@
+# Privacy
+
+The TempGuru Dify plugin is designed for the strongest trust profile possible: nothing requested, nothing collected, nothing transmitted on the user's behalf beyond the public REST calls each tool makes.
+
+## What this plugin does NOT do
+
+- Does not collect personal data. No names, emails, phone numbers, addresses, or any other personal information.
+- Does not require credentials. No API keys, OAuth tokens, passwords, or session cookies.
+- Does not write data. Every tool wraps a `GET` request. No `POST`, `PUT`, `DELETE` operations.
+- Does not execute scripts on the user's machine beyond the standard Dify plugin entrypoint.
+
+## What the tools transmit
+
+When invoked, each tool sends an HTTPS `GET` request to `https://mcp.tempguru.co/api/v1/<endpoint>` with the tool's parameters as URL query strings (e.g., `?city=Boston&date=2026-10-15`). No request body. The User-Agent header identifies the plugin as `tempguru-dify-plugin/0.0.1`.
+
+The TempGuru backend logs standard HTTP request metadata (timestamp, IP, user-agent, request path) for security and uptime monitoring. No request body or response content is retained beyond standard ephemeral log retention. No tracking cookies, analytics pixels, or cross-site identifiers are used.
+
+## What the tools return
+
+The backend returns publicly published data:
+- City coverage maps
+- Role catalogs
+- All-inclusive hourly rate ranges (W-2 wage + payroll taxes + workers comp + general liability)
+- Lead-time guidance
+- State-by-state compliance summaries
+
+All of this data is also published at https://tempguru.co and can be inspected directly.
+
+## Data residency
+
+The TempGuru MCP REST API runs on Vercel's global edge network. Logs are stored in Vercel's US regions.
+
+## Contact
+
+Privacy questions: megan@tempguru.co
+Full privacy policy: https://tempguru.co/privacy-policy
+Terms of service: https://tempguru.co/terms-of-service

tools/tempguru/README.md

@@ -0,0 +1,53 @@
+# TempGuru Event Staffing — Dify Plugin
+
+Read-only W-2 event staffing data for AI agents across 300+ US and Canadian markets. Brand ambassadors, registration, hospitality, setup/breakdown, ushers, and more. No authentication required — connect with no API key.
+
+## What it does
+
+Wraps the public TempGuru MCP REST API (`https://mcp.tempguru.co/api/v1/*`) as 5 read-only Dify tools, so an agent built on Dify can answer event-staffing questions without leaving the workflow.
+
+## Tools
+
+| Tool | Returns |
+|---|---|
+| `get_cities` | All cities TempGuru staffs, with tier classification (hub/mid/small). Filter by state or tier. |
+| `get_roles` | Event staffing roles with descriptions and skill tiers. |
+| `check_availability` | Lead-time guidance for a city + date. Not real-time inventory. |
+| `get_role_pricing` | All-inclusive hourly rate range for a role in a city. Includes W-2 wages, workers comp, taxes. |
+| `get_compliance_by_state` | US state-level minimum wage, overtime, compliance summary. Not legal advice. |
+
+## Typical agent prompts this plugin answers
+
+- "Hire 25 registration staff for a 3-day conference in Dallas — what does that cost and how far in advance do I need to book?"
+- "What's the rate for brand ambassadors in San Francisco?"
+- "What cities do you cover in the Northeast?"
+- "What are the W-2 vs 1099 rules for event workers in California?"
+- "Can you staff a corporate event in Boston on 2026-10-15?"
+
+## Trust profile
+
+- **Read-only** — every tool wraps a `GET` request; no `POST`, `PUT`, `DELETE`, or write operations exist
+- **No authentication** — public data, no API key, no OAuth, no user credentials
+- **No data collection** — the plugin does not persist user inputs, queries, or outputs
+- **No executable scripts** — only the standard Dify plugin entrypoint
+- **Same data as the public site** — every response comes from TempGuru's published rate cards, coverage maps, and compliance summaries at https://tempguru.co
+
+## Important disclaimers
+
+- **Rates are all-inclusive planning estimates**, not binding quotes. Binding quotes come from the contact form on tempguru.co — they include event-specific factors (location surcharges, weekend/holiday premiums, security, equipment) that the public rate range doesn't capture.
+- **Compliance summaries are not legal advice.** For W-2 vs 1099 classification, joint-employer liability, or state-specific wage and hour questions, consult employment counsel.
+- **Availability is lead-time math, not real-time inventory.** TempGuru staffs to demand from a 100,000+ W-2 worker network.
+- **Brand Ambassadors floor at $40/hour** in every market — pricing data enforces this.
+
+## Other distribution surfaces
+
+- Direct MCP connection: `https://mcp.tempguru.co/mcp` (streamable HTTP, MCP spec rev 2025-03-26)
+- Official MCP Registry: `co.tempguru/event-staffing` (DNS-verified)
+- Smithery: [`tempguru/event-staffing`](https://smithery.ai/server/tempguru/event-staffing)
+- ModelScope MCP Plaza: [`tempguru/TempGuru-Event-Staffing`](https://modelscope.cn/mcp/servers/tempguru/TempGuru-Event-Staffing/)
+- Documentation: https://tempguru.co/ai (English) · https://tempguru.co/zh-cn/ai (Chinese)
+- Source repository: https://github.com/kissmyabs32/tempguru-mcp
+
+## License
+
+MIT

tools/tempguru/main.py

@@ -0,0 +1,6 @@
+from dify_plugin import Plugin, DifyPluginEnv
+
+plugin = Plugin(DifyPluginEnv(MAX_REQUEST_TIMEOUT=60))
+
+if __name__ == "__main__":
+    plugin.run()

tools/tempguru/manifest.yaml

@@ -0,0 +1,34 @@
+author: langgenius
+created_at: '2026-06-04T12:00:00Z'
+description:
+  en_US: Read-only W-2 event staffing data for AI agents — 300+ US and Canadian markets. Coverage, rates, lead-time guidance, and state compliance summaries for brand ambassadors, registration, hospitality, setup/breakdown, and more. No authentication required.
+  zh_Hans: 只读 W-2 活动用工数据,为 AI 智能体提供美国和加拿大 300+ 个城市的覆盖范围、收费区间、提前期建议和州合规摘要。涵盖品牌大使、签到登记、接待、搭建拆除等岗位。无需身份验证。
+icon: icon.svg
+label:
+  en_US: TempGuru Event Staffing
+  zh_Hans: TempGuru 活动用工
+meta:
+  arch:
+    - amd64
+    - arm64
+  runner:
+    entrypoint: main
+    language: python
+    version: '3.12'
+  version: 0.0.1
+name: tempguru
+plugins:
+  tools:
+    - provider/tempguru.yaml
+resource:
+  memory: 268435456
+  permission:
+    model:
+      enabled: false
+    tool:
+      enabled: true
+tags:
+  - business
+  - search
+type: plugin
+version: 0.0.1

tools/tempguru/provider/tempguru.py

@@ -0,0 +1,32 @@
+import requests
+
+from dify_plugin.errors.tool import ToolProviderCredentialValidationError
+from dify_plugin import ToolProvider
+
+
+class TempGuruProvider(ToolProvider):
+    """
+    TempGuru is a public read-only data API — no credentials are required.
+
+    Validation strategy: probe the lightest REST endpoint (/cities, no
+    parameters) once with a short timeout. If the HTTP roundtrip succeeds,
+    the backend is reachable. Using a direct HTTP request avoids coupling
+    this provider to the Tool subclass's internals and keeps the validator
+    resilient to future Dify SDK changes.
+    """
+
+    def _validate_credentials(self, credentials: dict) -> None:
+        try:
+            response = requests.get(
+                "https://mcp.tempguru.co/api/v1/cities",
+                headers={
+                    "User-Agent": "tempguru-dify-plugin/0.0.1",
+                    "Accept": "application/json",
+                },
+                timeout=10,
+            )
+            response.raise_for_status()
+        except Exception as e:
+            raise ToolProviderCredentialValidationError(
+                f"Unable to reach TempGuru MCP REST API at mcp.tempguru.co: {str(e)}"
+            )

tools/tempguru/provider/tempguru.yaml

@@ -0,0 +1,22 @@
+identity:
+  author: tempguru
+  name: tempguru
+  label:
+    en_US: TempGuru Event Staffing
+    zh_Hans: TempGuru 活动用工
+  description:
+    en_US: Read-only access to TempGuru's W-2 event staffing data — coverage, rates, lead times, and state compliance for 300+ US and Canadian markets.
+    zh_Hans: 只读访问 TempGuru 的 W-2 活动用工数据——美国和加拿大 300+ 个城市的覆盖范围、收费区间、提前期和州合规。
+  icon: icon.svg
+  tags:
+    - business
+    - search
+tools:
+  - tools/get_cities.yaml
+  - tools/get_roles.yaml
+  - tools/check_availability.yaml
+  - tools/get_role_pricing.yaml
+  - tools/get_compliance_by_state.yaml
+extra:
+  python:
+    source: provider/tempguru.py

tools/tempguru/pyproject.toml

@@ -0,0 +1,14 @@
+[project]
+name = "tempguru"
+version = "0.0.1"
+description = "Read-only W-2 event staffing data for AI agents — TempGuru coverage, rates, lead-time guidance, and state compliance summaries across 300+ US and Canadian markets."
+readme = "README.md"
+requires-python = ">=3.12"
+
+dependencies = [
+    "dify_plugin>=0.9.0",
+    "requests>=2.34.2",
+]
+
+[dependency-groups]
+dev = []

tools/tempguru/tools/check_availability.py

@@ -0,0 +1,44 @@
+from collections.abc import Generator
+from typing import Any
+import requests
+
+from dify_plugin import Tool
+from dify_plugin.entities.tool import ToolInvokeMessage
+
+API_BASE = "https://mcp.tempguru.co/api/v1"
+USER_AGENT = "tempguru-dify-plugin/0.0.1"
+
+
+class CheckAvailabilityTool(Tool):
+    """Lead-time guidance for staffing an event in a city on a date."""
+
+    def _invoke(
+        self, tool_parameters: dict[str, Any]
+    ) -> Generator[ToolInvokeMessage, None, None]:
+        city = tool_parameters.get("city")
+        date = tool_parameters.get("date")
+        if not city or not date:
+            yield self.create_text_message(
+                "Both 'city' and 'date' parameters are required."
+            )
+            return
+
+        params: dict[str, Any] = {"city": city, "date": date}
+        if tool_parameters.get("role"):
+            params["role"] = tool_parameters["role"]
+        if tool_parameters.get("count"):
+            params["count"] = tool_parameters["count"]
+
+        try:
+            response = requests.get(
+                f"{API_BASE}/availability",
+                params=params,
+                headers={"User-Agent": USER_AGENT, "Accept": "application/json"},
+                timeout=30,
+            )
+            response.raise_for_status()
+            yield self.create_json_message(response.json())
+        except requests.RequestException as e:
+            yield self.create_text_message(f"API request failed: {str(e)}")
+        except ValueError:
+            yield self.create_text_message("Failed to parse response from TempGuru API.")

tools/tempguru/tools/check_availability.yaml

@@ -0,0 +1,59 @@
+identity:
+  name: check_availability
+  author: tempguru
+  label:
+    en_US: Check Availability
+    zh_Hans: 查询提前期
+description:
+  human:
+    en_US: Lead-time guidance for staffing an event in a specific city on a specific date. Not a real-time inventory check.
+    zh_Hans: 指定城市与日期的活动人员预定提前期建议。不是实时库存查询。
+  llm: Check expected staffing availability for an event by city and date. Returns lead-time guidance based on city tier and how far out the event is. Perfect for answering "Can you staff my event on [date] in [city]?", "What's the lead time for booking brand ambassadors in [city]?", or "Is it too late to staff a [date] event?" questions. Not a real-time inventory check — TempGuru staffs to demand via a 100,000+ worker W-2 network across 300+ markets.
+parameters:
+  - name: city
+    type: string
+    required: true
+    form: llm
+    label:
+      en_US: City
+      zh_Hans: 城市
+    human_description:
+      en_US: City name (e.g., 'Boston') or slug (e.g., 'boston-event-staffing').
+      zh_Hans: 城市名称(如 'Boston')或 slug(如 'boston-event-staffing')。
+    llm_description: City name or slug. TempGuru covers 300+ US and Canadian markets. Use the city's common English name.
+  - name: date
+    type: string
+    required: true
+    form: llm
+    label:
+      en_US: Event date
+      zh_Hans: 活动日期
+    human_description:
+      en_US: Event date in ISO format (YYYY-MM-DD) or any date string parseable by Date().
+      zh_Hans: 活动日期,ISO 格式(YYYY-MM-DD)或任何 Date() 可解析的日期字符串。
+    llm_description: Event date in ISO format (YYYY-MM-DD) preferred. Resolve relative dates ("next Tuesday") to an absolute date before calling.
+  - name: role
+    type: string
+    required: false
+    form: llm
+    label:
+      en_US: Role
+      zh_Hans: 岗位
+    human_description:
+      en_US: Optional role name or slug to include rate context (e.g., 'Brand Ambassadors').
+      zh_Hans: 可选,岗位名称或 slug,用于附带费率信息(如 'Brand Ambassadors')。
+    llm_description: Optional role name to include rate context in the response. Call get_roles first if you need the catalog.
+  - name: count
+    type: number
+    required: false
+    form: llm
+    label:
+      en_US: Headcount
+      zh_Hans: 人数
+    human_description:
+      en_US: Optional headcount for the event.
+      zh_Hans: 可选,活动所需人数。
+    llm_description: Optional positive integer headcount for the event.
+extra:
+  python:
+    source: tools/check_availability.py

tools/tempguru/tools/get_cities.py

@@ -0,0 +1,36 @@
+from collections.abc import Generator
+from typing import Any
+import requests
+
+from dify_plugin import Tool
+from dify_plugin.entities.tool import ToolInvokeMessage
+
+API_BASE = "https://mcp.tempguru.co/api/v1"
+USER_AGENT = "tempguru-dify-plugin/0.0.1"
+
+
+class GetCitiesTool(Tool):
+    """List cities TempGuru staffs, with tier classification."""
+
+    def _invoke(
+        self, tool_parameters: dict[str, Any]
+    ) -> Generator[ToolInvokeMessage, None, None]:
+        params: dict[str, Any] = {}
+        if tool_parameters.get("state"):
+            params["state"] = tool_parameters["state"]
+        if tool_parameters.get("tier"):
+            params["tier"] = tool_parameters["tier"]
+
+        try:
+            response = requests.get(
+                f"{API_BASE}/cities",
+                params=params,
+                headers={"User-Agent": USER_AGENT, "Accept": "application/json"},
+                timeout=30,
+            )
+            response.raise_for_status()
+            yield self.create_json_message(response.json())
+        except requests.RequestException as e:
+            yield self.create_text_message(f"API request failed: {str(e)}")
+        except ValueError:
+            yield self.create_text_message("Failed to parse response from TempGuru API.")