finta-aurora-mcp 1.0.0__py3-none-any.whl

finta_aurora_mcp-1.0.0.dist-info/METADATA

@@ -0,0 +1,216 @@
+Metadata-Version: 2.4
+Name: finta-aurora-mcp
+Version: 1.0.0
+Summary: Aurora AI Agent for Finta
+Home-page: https://github.com/finta/aurora
+Author: Finta
+Author-email: support@trustfinta.com
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+Requires-Dist: pydantic>=2.0.0
+Requires-Dist: langchain-core
+Requires-Dist: langchain-community
+Requires-Dist: langchain-openai>=0.1.0
+Requires-Dist: langchain
+Requires-Dist: beautifulsoup4
+Requires-Dist: openai
+Requires-Dist: langgraph
+Requires-Dist: langgraph-cli
+Requires-Dist: langgraph-api>=0.2.3
+Requires-Dist: langgraph-sdk>=0.1.61
+Requires-Dist: langchain-mcp-adapters
+Requires-Dist: tavily-python
+Requires-Dist: google-search-results
+Requires-Dist: requests
+Requires-Dist: pinecone
+Requires-Dist: langchain-pinecone
+Requires-Dist: playwright
+Requires-Dist: flask
+Requires-Dist: tiktoken
+Requires-Dist: PyPDF2
+Requires-Dist: python-dotenv
+Requires-Dist: python-decouple
+Requires-Dist: flask_cors
+Requires-Dist: langchain-google-genai
+Requires-Dist: langchain-anthropic
+Requires-Dist: langchain-google-vertexai
+Requires-Dist: google-cloud-aiplatform>=1.84
+Requires-Dist: httpx>=0.27.0
+Requires-Dist: langchainhub
+Requires-Dist: mcp>=0.1.0
+Dynamic: author
+Dynamic: author-email
+Dynamic: home-page
+Dynamic: requires-python
+
+# Aurora
+
+## Running Aurora locally:
+
+Pre-requisite: Ensure you have Docker installed on your system and you are logged in. If not, download and install it from the [official website](https://www.docker.com/products/docker-desktop/).
+
+### LangGraph CLI (Recommended)
+
+Pre-requisite: Set up a virtual environment and install dependencies:
+
+1. Run `python3 -m venv .venv`
+2. Run `.venv/bin/pip install -r requirements.txt`
+3. Get the .env file contents from Kevin or someone on the team. Aurora will not run via docker without this file. 
+
+To run Aurora:
+
+1. Run `langgraph up` in the terminal from the aurora directory. This will start the Aurora server on `localhost:8123`.
+2. IMPORTANT: Before prompting Aurora, you will need to press the `+` button on the Chatbot UI in order to create a new thread.
+
+- Note: Langgraph up will start a build before running the container, so it may take a while to start
+
+### LangGraph Cloud Desktop GUI (For Graph UI)
+
+- Note:
+  - Apple Silicon only, as of 09/2024
+  - You will need to manually update the endpoint in equity-token-webapp/src/api/fintaAI/aurora
+
+Pre-requisite: Install [LangGraph Studio for Desktop](https://github.com/langchain-ai/langgraph-studio)
+
+1. Log in with LangSmith credentials
+2. Navigate to the cloned Aurora repo folder location
+3. When Aurora has finished building, find the 'localhost:xxxxx' endpoint to use in equity-token-webapp
+4. Update the client endpoint in equity-token-webapp/src/api/fintaAI/aurora.js to the 'localhost:xxxxx' endpoint
+   `const client = new Client({
+apiUrl: [YOUR ENDPOINT HERE],
+defaultHeaders: {
+'X-API-KEY': LANGSMITH_API_KEY,
+},
+});`
+
+## Using Aurora MCP (for Cursor/Claude Desktop/ChatGPT)
+
+The Aurora MCP allows you to chat with Aurora directly from Cursor, Claude Desktop, or ChatGPT, with automatic injection of your CRM contacts and deal information.
+
+**✅ Compatible with:**
+- **Cursor** - IDE with built-in MCP support
+- **Claude Desktop** - Anthropic's desktop app
+- **Any MCP-compatible client** - Uses standard stdio protocol
+
+### Installation
+
+Install the Aurora MCP package via pip:
+
+```bash
+pip install finta-aurora-mcp
+```
+
+Or if you have the repo:
+
+```bash
+cd aurora
+pip install -e .
+```
+
+### Step 1: Authenticate (one-time)
+
+Run the authentication command:
+
+```bash
+aurora-authenticate
+```
+
+This will:
+- Open your browser for Finta OAuth login
+- Store your authentication token in `~/.cursor/aurora_token.json`
+- Store your organization info in `~/.cursor/aurora_org_info.json`
+
+**Note:** By default, authentication uses the **staging** environment. To use production, set `FINTA_STAGING=false` before running:
+
+```bash
+FINTA_STAGING=false aurora-authenticate
+```
+
+### Step 2: Add to MCP config
+
+**For Cursor:**
+Add this to your `~/.cursor/mcp.json` (create the file if it doesn't exist):
+
+```json
+{
+  "mcpServers": {
+    "aurora": {
+      "command": "python3",
+      "args": ["-m", "finta_aurora_mcp.mcp"]
+    }
+  }
+}
+```
+
+**For Claude Desktop:**
+Add this to your `~/Library/Application Support/Claude/claude_desktop_config.json` (macOS) or `%APPDATA%\Claude\claude_desktop_config.json` (Windows):
+
+```json
+{
+  "mcpServers": {
+    "aurora": {
+      "command": "python3",
+      "args": ["-m", "finta_aurora_mcp.mcp"]
+    }
+  }
+}
+```
+
+**For ChatGPT/OpenAI:**
+If OpenAI supports MCP servers, configure it similarly. Check OpenAI's documentation for their MCP configuration format.
+
+**Note:** This references the installed package, so no file paths needed! The same package works with all MCP clients.
+
+### Step 3: Restart Your Application
+
+**Restart your application completely** (quit and reopen) for the MCP changes to take effect:
+- **Cursor**: Quit and reopen Cursor
+- **Claude Desktop**: Quit and reopen Claude Desktop
+- **ChatGPT**: Follow OpenAI's instructions for reloading MCP servers
+
+### Step 4: Use Aurora
+
+Once set up, you can use Aurora by:
+
+**In Cursor:**
+1. Type `@aurora_chat` followed by your question
+2. Example: `@aurora_chat Who are the investors in my CRM?`
+
+**In Claude Desktop:**
+1. Use the `aurora_chat` tool in Claude's tool picker
+2. Or mention it in conversation: "Use aurora_chat to tell me about my CRM"
+
+**In ChatGPT (if supported):**
+1. Follow OpenAI's MCP tool usage instructions
+2. The `aurora_chat` tool will be available in ChatGPT's tool list
+
+Aurora will automatically have access to:
+- Your CRM contacts (investors, status, emails)
+- Your deal information (terms, industry, deal notes, etc.)
+- All of Aurora's tools (search, add contacts, etc.)
+
+### Troubleshooting
+
+- **"Invalid or expired token"**: Run `aurora-authenticate` again to refresh your token
+- **"Unknown tool: aurora_chat"**: Make sure you restarted Cursor after adding the MCP config
+- **"Module not found: finta_aurora_mcp"**: Make sure you installed the package with `pip install finta-aurora-mcp`
+- **No CRM/deal info in responses**: Check that your organization handle is correct and you have a default deal set up in Finta
+
+## Deploying Aurora to LangGraph Cloud:
+
+Pre-requisites:
+
+1. Ensure you have access to [LangSmith](https://smith.langchain.com/)
+2. Ensure your changes are pushed to the respective branch of the Aurora repo:
+   - Production: `main`
+   - Staging: `develop-Oct-2025`
+
+#### On LangSmith:
+
+1. Click on the `Deployments` tab
+2. Find respective project:
+   - Production: `aurora-v1-production`
+   - Staging: `aurora-v1-staging`
+3. Click on the `+ New Revision` button on the top right
+4. Update environment variables as needed
+5. Click Submit to redeploy your changes

finta_aurora_mcp-1.0.0.dist-info/RECORD

@@ -0,0 +1,19 @@
+finta_aurora_mcp/__init__.py,sha256=-2uFvF_-ohVqH0r4acGPr1d2W1s7KYcDgESG7geu4JE,96
+finta_aurora_mcp/auth.py,sha256=dBkMohr4QoAYFkP91UXLDtYfelP2iNN1TpS4PBwodM0,3921
+finta_aurora_mcp/fix_org_info.py,sha256=UrGRBsjz99nAnrTAC6VPfPkAIiHb7LS69fRZoDdVMT4,1590
+finta_aurora_mcp/mcp.py,sha256=L-a1OT8QxnF3Ymu5dJaj49dHz1csGR20i9UGeWTC_tY,20930
+tools/__init__.py,sha256=oTvelMfzMN2Dc9-NYxX2z9JtLhayfqbhI0ooC2IxECY,868
+tools/addInvestorToTrackerTool.py,sha256=DKn3UpykKKvhzzCV1aYRoIdM_3AGTHU5ODisJ2g20Jg,6129
+tools/contactSupportTool.py,sha256=4HMTfeR44JhuWInVAknn5jpITj2rMhuGo_hXQRGfgw0,276
+tools/editInvestorTool.py,sha256=AjHX9X6sWluLexoun56s2Z5tNK9YdQzaUyINQzJ4VQM,38603
+tools/getInvestorTool.py,sha256=btIMapZ1YYen2_F75o5NCP_mugEIRERJT6AGYuFwKgA,4924
+tools/imageTool.py,sha256=IRnxCui7IvET_RKzGZ6-d711qtsmCyjNJuA2ZYSqOmc,2835
+tools/pdfScraperTool.py,sha256=Fp72IV4sCc52-w3I6Dn2ybpX-a9OOYP6IQT10wFyqaA,825
+tools/pineconeKnowledgeTool.py,sha256=4IRhTUkClRGcDNgYQcMyiCmP-TyIDdgYAiUvOkdyQr8,1280
+tools/pineconeResourceTool.py,sha256=1IuJ9xnIly2vN8ehWZMqxbYmLXxLeCZISeSQxiHxFLo,1054
+tools/serpAPITool.py,sha256=Mi6Yq-zTBdbvSiwqGeCiT_Jx2bpEbI8k9xXrCLtIzX8,544
+tools/webScraperTool.py,sha256=OKwCo1bkVXJpcldbI-dvSm0qjQmhr4wmJUrj_KFMBb4,1122
+finta_aurora_mcp-1.0.0.dist-info/METADATA,sha256=xhQCIdHzsNVhxtQ_4bqMYKRSOmwhugtGq8TrdopNJvU,6787
+finta_aurora_mcp-1.0.0.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
+finta_aurora_mcp-1.0.0.dist-info/top_level.txt,sha256=IHyK49UWbgesCaXyeEpE-cHkjwWoDOTv7RhPaCWKgwQ,23
+finta_aurora_mcp-1.0.0.dist-info/RECORD,,

finta_aurora_mcp-1.0.0.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (80.10.2)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

finta_aurora_mcp-1.0.0.dist-info/top_level.txt

@@ -0,0 +1,2 @@
+finta_aurora_mcp
+tools

tools/__init__.py

@@ -0,0 +1,23 @@
+from .contactSupportTool import contact_support_tool
+from .serpAPITool import serpAPITool
+from .addInvestorToTrackerTool import add_to_tracker_any_fields_tool
+from .getInvestorTool import get_investor_info_tool
+from .editInvestorTool import edit_target_investor_any_fields_tool
+from .imageTool import image_tool
+from .pineconeKnowledgeTool import pinecone_finta_knowledge_tool
+from .pineconeResourceTool import pinecone_finta_resource_tool
+from .webScraperTool import scrape_website_from_link_tool
+from .pdfScraperTool import pdf_scraper_tool
+
+__all__ = [
+    "contact_support_tool",
+    "serpAPITool",
+    "add_to_tracker_any_fields_tool",
+    "get_investor_info_tool",
+    "edit_target_investor_any_fields_tool",
+    "image_tool",
+    "pinecone_finta_knowledge_tool",
+    "pinecone_finta_resource_tool",
+    "scrape_website_from_link_tool",
+    "pdf_scraper_tool",
+]

tools/addInvestorToTrackerTool.py

@@ -0,0 +1,114 @@
+from langchain_core.tools import StructuredTool, ToolException
+import requests
+from pydantic.v1 import BaseModel, Field, ValidationError
+from typing import Optional, List
+import os
+from langchain_core.runnables.config import RunnableConfig
+
+API_BASE_URL = os.environ['API_BASE_URL']
+# API_BASE_URL = "https://us-central1-equity-token-1.cloudfunctions.net/"
+
+class AddToTrackerAnyFieldsInput(BaseModel):
+    firstName: str = Field(..., description="Investor's first name")
+    lastName: str = Field(default="", description="Investor's last name")
+    email: Optional[str] = Field(default="", description="Investor's email address")
+    location: Optional[str] = Field(default="", description="Investor's location")
+    organizationName: Optional[str] = Field(default="", description="Name of the investor's organization")
+    organizationWebsite: Optional[str] = Field(default="", description="Website of the investor's organization")
+    linkedIn: Optional[str] = Field(default="", description="Investor's LinkedIn profile URL")
+    twitter: Optional[str] = Field(default="", description="Investor's Twitter profile URL")
+    crunchbase: Optional[str] = Field(default="", description="Investor's Crunchbase profile URL")
+    angelList: Optional[str] = Field(default="", description="Investor's AngelList profile URL")
+    investmentRangeFrom: Optional[str] = Field(default="", description="Minimum investment range")
+    investmentRangeTo: Optional[str] = Field(default="", description="Maximum investment range")
+    investmentSweetSpot: Optional[str] = Field(default="", description="Investor's preferred investment amount")
+    fundSize: Optional[str] = Field(default="", description="Size of the investor's fund")
+    bio: Optional[str] = Field(default="", description="Short biography of the investor")
+    relevantPortfolioCompanies: Optional[str] = Field(default="", description="Relevant portfolio companies of the investor")
+    tags: Optional[List[str]] = Field(default=None, description="List of tags to assign when creating the investor. ALWAYS include ALL tags in THIS call as an array - do NOT use separate edit calls. When user says 'tag as X and Y' or 'add tags X, Y', put ALL tags in this array. Examples: tags=['Angel Investor'], tags=['Easy Investor', 'Interested'], tags=['Super Angel', 'Series A', 'Seed']. Tags are labels/categories - can have multiple per investor.")
+
+def call_add_to_tracker_any_fields(config: RunnableConfig, 
+    email: Optional[str] = "", 
+    firstName: str = "", 
+    lastName: str = "",
+    location: Optional[str] = "", 
+    organizationName: Optional[str] = "", 
+    organizationWebsite: Optional[str] = "", 
+    linkedIn: Optional[str] = "", 
+    twitter: Optional[str] = "", 
+    crunchbase: Optional[str] = "", 
+    angelList: Optional[str] = "", 
+    investmentRangeFrom: Optional[str] = "", 
+    investmentRangeTo: Optional[str] = "", 
+    investmentSweetSpot: Optional[str] = "", 
+    fundSize: Optional[str] = "", 
+    bio: Optional[str] = "", 
+    relevantPortfolioCompanies: Optional[str] = "",
+    tags: Optional[List[str]] = None):
+    """Given an input of different investor attributes, this functions adds all relevant investor field to Finta's CRM Tracker. Do not ask for more information, simply use what was given."""
+    org_info = config.get('configurable', {}).get("org_info", {})
+    handle = org_info["handle"]
+    sourceUserId = org_info["founderId"]
+    url = API_BASE_URL + "addTargetInvestorAnyFields"
+    
+    # Process tags - clean and validate
+    cleaned_tags = None
+    if tags is not None:
+        if isinstance(tags, list):
+            cleaned_tags = []
+            for tag in tags:
+                if tag is None:
+                    continue
+                if isinstance(tag, str):
+                    stripped = tag.strip()
+                    if stripped:
+                        cleaned_tags.append(stripped)
+                else:
+                    # If tag is not a string, convert to string
+                    stripped = str(tag).strip()
+                    if stripped:
+                        cleaned_tags.append(stripped)
+        else:
+            # If single string provided by mistake, wrap it
+            cleaned_tags = [str(tags).strip()] if str(tags).strip() else []
+    
+    data = {
+        "data": {
+            "organizationId": handle,
+            "sourceUserId": sourceUserId,
+            "investorFields": {
+                "email": email,
+                "firstName": firstName,
+                "lastName": lastName,
+                "location": location,
+                "organizationName": organizationName,
+                "organizationWebsite": organizationWebsite,
+                "linkedIn": linkedIn,
+                "twitter": twitter,
+                "crunchbase": crunchbase,
+                "angelList": angelList,
+                "investmentRangeFrom": investmentRangeFrom,
+                "investmentRangeTo": investmentRangeTo,
+                "investmentSweetSpot": investmentSweetSpot,
+                "fundSize": fundSize,
+                "bio": bio,
+                "relevantPortfolioCompanies": relevantPortfolioCompanies,
+            },
+        }
+    }
+    
+    # Add tags to payload if provided (tags are stored at top-level, not in investorFields)
+    if cleaned_tags is not None:
+        data["data"]["tags"] = cleaned_tags
+    
+    response = requests.post(url, json=data)
+    return 'Success! Investor added to Finta\'s CRM Tracker.'
+
+add_to_tracker_any_fields_tool= StructuredTool.from_function(
+        func=call_add_to_tracker_any_fields,
+        name="AddToTrackerAnyFields",
+        description="""Given an input of different investor attributes, this functions adds all relevant investor field to Finta's CRM Tracker. Do not ask for more information, simply use what was given. When user says 'tag [name] as [tag]' or 'add tag [tag]', use the 'tags' parameter with an array (e.g., tags=['Super Angel']). Tags are labels/categories, NOT the same as 'grade' (which is a single rating).""",
+        args_schema=AddToTrackerAnyFieldsInput,
+        return_direct=True,
+        verbose=True
+    )

tools/contactSupportTool.py

@@ -0,0 +1,7 @@
+import os
+from langchain_core.tools import tool
+
+@tool
+def contact_support_tool() -> str:
+    """Helps answer questions on where to go for more support, or if asked to contact support or talk to a human."""
+    return "Click on 'Get More Assistance' below to contact support."