Pitchly MCP for AI. Manage structured data records from chat.

Q: Can I create a record with partial data?

It depends. You must first use gettabledetails to check the required fields. If certain fields are mandatory, createrecord will fail until all necessary information is provided.

Q: Which tool do I use if I just want a list of available data collections?

Use listtables. This command shows you the names of all the custom tables (like 'Tombstones' or 'Client Projects') that hold your organizational metadata.

Q: Is getworkspacedetails the same as listworkspaces?

No. listworkspaces just gives you a directory listing (names). getworkspacedetails fetches the specific metadata—like creation date or owner—for one workspace after you've selected it.

Q: If I suspect the underlying data structure has changed, should I use listfields before running createrecord?

Absolutely. Always check the schema first using listfields. This confirms the current set of field names and data types for a table, preventing run-time errors when your agent tries to write records that don't match the expected structure.

Claude

ChatGPT

Cursor

Gemini

Windsurf

VS Code

JetBrains

Vercel

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

Connect to your AI in seconds.

Pitchly MCP Server connects your AI agent directly to structured professional services data. It lets you read, write, and update records—like deal pipelines, team bios, and client projects—across multiple workspaces without ever touching a spreadsheet.

You take firm experience metadata and turn it into immediate, usable pitch materials.

What your AI can do

Create record

Adds a new record to any specified table in Pitchly.

Delete record

Permanently removes an existing record from a table.

Get record details

Fetches all specific details for one known record using its unique ID.

+ 8 more capabilities included

Listing all workspaces

Retrieves a list of every workspace (e.g., 'Corporate,' 'Mid-Market') you manage within Pitchly.

Managing table structures

Lists available tables within a specific workspace and retrieves the detailed field structure for any selected table.

Querying records by search criteria

Searches across all records in a specified table using natural language prompts (e.g., 'Show me deals over $1M').

Creating new data entries

Adds entirely new records to any custom table, ensuring required metadata like client name or deal stage is populated.

Updating existing records

Modifies details of a specific record—like changing a deal status or adding a team member's bio—using its unique ID.

Ask an AI about this

Included with Plan

Waiting for input…

AI Agent

Pitchly MCP Server: 11 Tools for Data Record Management

Use these eleven specific tools to manage every aspect of your firm's structured data—from listing workspaces to updating individual records.

Make your AI actually useful.

Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.

Start using Pitchly on Vinkius

Create Record

Adds a new record to any specified table in Pitchly.

Delete Record

Permanently removes an existing record from a table.

Get Record Details

Fetches all specific details for one known record using its unique ID.

Get Table Details

Retrieves the full schema and metadata structure of a particular table.

Get Workspace Details

Gets metadata about a specific Pitchly workspace, like its name or owner.

List Fields

Lists all available data fields (columns) within a given table schema.

List Table Records

Retrieves a basic list of record IDs and primary details from an entire table.

List Tables

Lists all the available data tables within a specified workspace.

List Workspaces

Returns a list of every Pitchly workspace the user has access to.

Search Records

Performs keyword searches across multiple records within a specific table based on...

Update Record

Changes the value of one or more fields in an existing record.

Security and governance baked right in.

Pick your AI client below to get set up. Just create a Vinkius account, subscribe, and you're instantly up and running. We handle the entire backend infrastructure, delivering out-of-the-box support for HTTPS Streamable, SSE, and OAuth2—zero messy routing required.

Claude AI

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL:

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.

Start a conversation

Open a new chat. The Pitchly integration is available immediately — no restart needed.

Antigravity

Configure Agent Environment

Open your Antigravity agent's workspace configuration or mcp-servers.json file.

Bind the Endpoint

Add the Vinkius endpoint URL to your agent's MCP connections list:

"mcp_servers": {
  "pitchly": {
    "serverUrl": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
  }
}

Provide your secure token in place of [YOUR_TOKEN_HERE] to ensure your agent requests are authenticated.

Execute

Start your Antigravity session. The agent will autonomously discover and utilize the Pitchly tools with full Vinkius guardrails applied.

VS Code Copilot

⚡

One-Click Install (Recommended)

In your Vinkius Dashboard, simply click the Add to VS Code button for this server. We'll automatically configure your local workspace.

Or configure manually

Open MCP Settings

Open VS Code, press Ctrl/Cmd + Shift + P, and search for GitHub Copilot: MCP Servers.

Add Server Config

Add the Vinkius endpoint configuration to your mcp-servers.json file:

"pitchly": {
  "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
}

Ensure you replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.

LangChain

Install Dependencies

Install the LangChain MCP adapters for your environment:

pip install langchain-mcp-adapters

Connect the Server

Use the SSEClient in LangChain to connect to the Vinkius managed endpoint:

from langchain_mcp_adapters.client import SSEClient

# Connect to Vinkius
client = SSEClient(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
tools = client.get_tools()

CrewAI

Define the Tool

Load the Vinkius MCP tools into your CrewAI agents:

from crewai import Agent
from mcp_crewai import MCPTool

# Connect securely to Vinkius
vinkius_tools = MCPTool(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

# Assign to Agent
researcher = Agent(
    role='Data Researcher',
    tools=vinkius_tools.get_all()
)

Execute Task

Run your CrewAI process. The agent will autonomously route tasks to the Vinkius managed server.

Choose How to Get Started

Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.

Build Your Own

Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.

Import from OpenAPI, Swagger, or YAML specs
Create Agent Skills with progressive disclosure
Deploy to edge with MCPFusion framework
Built in DLP, auth, and compliance on every call
Real time usage dashboard and cost metering
Publish to catalog or keep private

Start building

Make Your AI Do More

Start with Pitchly, then connect any of our 5,000+ other servers whenever your AI needs more. One click, no limits.

Use this MCP plus 5,000+ others, all in one place
Add new capabilities to your AI anytime you want
Every connection is secured and compliant automatically
Track usage and costs across all your servers
Works with Claude, ChatGPT, Cursor, and more
New servers added to the catalog every week

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Pitchly. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

VINKIUS INFRASTRUCTURE

Cloud Hosted

Managed infra

V8 Isolated

Sandboxed per request

Zero-Trust Proxy

No stored credentials

DLP Enforced

Policy on every call

GDPR Compliant

EU data residency

Token Compression

~60% cost reduction

Your data is protected. See how we built it.

Works with Claude, ChatGPT, Cursor, and more

The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.

This connection provides 11 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.

Manually building pitch decks from siloed company history takes forever.

Today, pulling together a single client pitch means hopping between five systems: the CRM for deals, SharePoint for bios, Google Sheets for financials, and a local drive for old presentations. You spend hours copying names, finding ID numbers, cross-checking statuses, and manually ensuring every piece of data is formatted correctly.

With this MCP server, you tell your agent what story you need to tell. The AI handles the database coordination—it runs `search_records` across 'Professional Bios' and pulls details from 'Client Projects,' compiling a clean, verified narrative in seconds. You just get the final answer.

Pitchly MCP Server: Control your data flow with Pitchly.

Before this server, updating a deal meant logging into the platform and clicking through multiple status dropdowns. Adding a new team member's bio required manually creating a record in a separate spreadsheet that had to be merged back later.

Now you speak naturally. You tell your agent: 'Update the Meridian M&A deal; change status to Negotiation.' The agent knows exactly which tool (`update_record`) and which table to hit, handling all the field changes in one go. It's direct.

Support 24/7 support@vinkius.com ↗

Security Vinkius Trust Center ↗

SLA Service Level Agreement ↗

Report Listing Send Report ↗

What your AI can actually do with this

Pitchly MCP Server hooks your AI agent straight into Pitchly’s structured data. This isn't just reading reports; it gives your client administrative access to your core business metadata—your deals, team bios, and client projects. You can make your agent act on the data.

Starting with Discovery:
If you don't know where to start, your agent first checks what’s available. It uses list_workspaces to pull a list of every Pitchly workspace you manage, like 'Corporate Deals' or 'Mid-Market Accounts.' Once it knows the space, it can use list_tables to show you all the data tables within that specific container.

For deeper structure checks, it runs get_table_details and then uses list_fields to pull a complete schema—the exact column names and types—for any table you point it toward.

Finding Data:
When you need information, your agent doesn't guess. It can use search_records, allowing you to run keyword searches across multiple records in a specific table using natural language prompts. You could ask it something like, 'Show me all deals over $1M that closed last quarter.' To get the full picture of one item, it runs get_record_details using a unique record ID.

If you just need a quick overview of what exists in a whole table without digging into every field, list_table_records pulls back a basic list of all record IDs and primary details.

Modifying Data:
This is where the power is. Your agent doesn't stop at reading; it writes. You can create entirely new data entries using create_record, ensuring required fields—like populating a client name or setting a deal stage—are filled in correctly from your chat prompt. If an existing record needs tweaking, it uses update_record to modify specific fields of that record based on its unique ID.

Need to clean up old data? It handles permanent removal using delete_record.

Putting It Together:
Your AI client executes complex flows. For instance, you can ask it to find a deal ('search_records'), grab the full details for that deal ('get_record_details'), and then modify the status of that record AND update two team members' bios simultaneously ('update_record'). You don’t touch a spreadsheet; your agent handles the whole workflow, keeping all your business intelligence accurate and instantly accessible.

It manages multiple workspaces (list_workspaces) and helps you understand table structure (get_table_details, list_fields) so you always know where to look or what to change.

Built · Hosted · Managed by Vinkius Pitchly MCP Server - Manage Deal Sheets & Credentials

Server ID 019dd13c-7abf-7279-8f0c-7ba1c2f7b38a

Vinkius Inspector

Compliance Grade A+

Score 100/100

Report View Report ↗

Here's how it actually works

The bottom line is: your AI client acts as a data coordinator, executing complex chains of reads, writes, and updates using Pitchly's underlying structure.

First, subscribe to the server and provide your Pitchly API Key (Bearer Token) in your AI client settings.

Next, prompt your agent with a high-level goal, like 'List all tables in my Corporate workspace.' The agent uses list_tables to identify available data sources.

Finally, instruct the agent on the desired action: 'Search for records where the deal value is over $500k and the status is open.' The agent then executes tools like search_records or get_record_details.

Who is this actually for?

This is for the Partner or Consultant who spends their mornings switching between CRM tabs, internal wikis, and spreadsheets just to build a single pitch deck. It’s also for the Business Development (BD) Manager drowning in metadata they can't easily locate. If your job involves translating raw company experience into client-ready content, this server is built for you.

Management Consultant

Uses the tool to pull specific historical project details (bios, deal values) and compile them instantly into a draft pitch deck narrative.

Business Development Manager

Runs searches across 'Client Projects' or 'Deals' to find evidence of past success matching a prospect's industry vertical. Must track professional bios accurately.

Knowledge Manager

Periodically checks the system health by calling list_workspaces and running schema checks (get_table_details) to ensure data consistency across all teams.

What Changes When You Connect

Stop searching. Use search_records to find specific deals or bios instantly by asking your agent a question, rather than running complex filters in the UI.

Never lose track of metadata again. You can use list_workspaces and then get_table_details to map out exactly what data exists across your entire firm's knowledge base.

Automate clean-up work. Use create_record or update_record to log new client engagements or adjust a deal stage without ever opening the Pitchly web interface.

See the whole picture. The agent can run multiple tools in sequence—for example, first listing tables (list_tables), then getting details for one (get_table_details), and finally searching it all up (search_records).

Control your data flow completely. By exposing delete_record, you give the AI client necessary permission to clean out obsolete or outdated records when requested.

See it in action

01 01

Client Pitch Prep: Finding a single source of truth for team experience.

A consultant needs to build a pitch sheet on 'Quantum Computing.' Instead of manually searching three different tables, they ask their agent. The agent uses list_tables to find the 'Professional Bios' table, then runs search_records to pull every relevant person who worked in that domain, generating a compiled list instantly.

02 02

Post-Meeting Data Logging: Capturing new deal progress.

The BD Manager just finished a meeting. Instead of opening the CRM, they tell their agent: 'Create a record for ScaleUp Technologies in Deal Pipeline.' The agent uses create_record, populating fields like stage and estimated value automatically.

03 03

Data Audit: Checking if all team bios are complete.

The Knowledge Manager runs an audit. They use list_workspaces to check the 'Corporate' workspace, then call get_table_details on the 'Professional Bios' table. This confirms the required fields (like job title and years of experience) exist before running any reports.

04 04

Updating a Project: Changing status and adding new team members.

A project wraps up early. The agent is told to update the record. It uses get_record_details first to grab the ID, then calls update_record, changing the 'Client Projects' stage from Active to Completed and linking two new team member IDs.

The honest tradeoffs

Trying to filter data locally.

Anti-pattern

Running list_table_records on a massive table (10,000+ records) and then expecting the AI client or local code to efficiently filter out only 'Active' deals based on status. This dumps too much data and slows everything down.

The Fix

Don't list everything. Use search_records instead. It handles filtering by criteria (like 'status=Active') directly within the Pitchly API, giving you only what you need.

Assuming data consistency across tables.

Anti-pattern

Writing a multi-step workflow that assumes every new record created in Table A automatically has an associated entry in Table B. If one table is missing the required field, the whole process fails.

The Fix

Always check schemas first. Use get_table_details to confirm all necessary fields exist before attempting to run complex transactions with create_record or update_record.

Relying on general chat for structured data.

Anti-pattern

Asking the agent, 'Tell me about Acme Corp.' This is too vague and doesn't tell the agent which specific table (Tombstones? Bios?) to look in, leading to generic or incorrect answers.

The Fix

Be explicit. Always start by asking: 'Search the Professional Bios table for records mentioning Acme Corp.' This directs the tool call immediately to search_records on the right source.

When It Fits, When It Doesn't

Use this server if your primary business need is managing, tracking, or generating content from structured metadata (deals, bios, projects). The flow must be: Query -> Find ID/Data -> Update/Create Content. If you only need to read unstructured documents (like PDF contracts) and pull general information without needing to update the underlying database, this server isn't built for that—you need a pure RAG system instead. However, if you know your data lives in discrete tables with defined fields, then Pitchly is exactly what you want. Use get_table_details first; if the schema looks right, proceed with the tools.

Questions you might have

How do I start using the search_records tool? +

You initiate this by asking your agent a question that requires data lookup, like 'What deals were closed last quarter?' The agent uses search_records on the appropriate table and handles the parameters for you.

Can I create a record with partial data? +

It depends. You must first use get_table_details to check the required fields. If certain fields are mandatory, create_record will fail until all necessary information is provided.

Which tool do I use if I just want a list of available data collections? +

Use list_tables. This command shows you the names of all the custom tables (like 'Tombstones' or 'Client Projects') that hold your organizational metadata.

How do I update multiple records at once? +

You don't. You tell the agent which specific record IDs you want to modify, and it calls update_record for each one sequentially. It’s best practice to handle these in batches of 5 or less.

Is get_workspace_details the same as list_workspaces? +

No. list_workspaces just gives you a directory listing (names). get_workspace_details fetches the specific metadata—like creation date or owner—for one workspace after you've selected it.

If I forget to pass a valid Pitchly Bearer Token, will the `get_record_details` tool execute successfully? +

No. You must include a current Pitchly API Key in the Authorization header for any operation. Without it, the call fails instantly with an authentication error code (401). This ensures your agent never attempts to access private data without proper credentials.

Does the system impose rate limits on the `search_records` tool if I run multiple queries quickly? +

Yes. Pitchly enforces an API rate limit to protect performance across all users. If your agent exceeds this quota, it receives a 429 error code. Your workflow must implement proper backoff logic before retrying the search.

If I suspect the underlying data structure has changed, should I use `list_fields` before running `create_record`? +

Absolutely. Always check the schema first using list_fields. This confirms the current set of field names and data types for a table, preventing run-time errors when your agent tries to write records that don't match the expected structure.

Can my AI automatically find a specific deal record by its ID? +

Yes! Use the get_record tool with the Table ID and Record ID. Your agent will respond with the complete metadata for the entry, including all custom field values in seconds.

How do I find my Pitchly API Key? +

Log in to your Pitchly account, navigate to Settings or your Developer Dashboard, and you will find your unique secret API key there. You may need organization admin privileges to see it.

Does this work with custom tables? +

Absolutely. This integration dynamically lists all tables available in your workspaces, allowing the AI to interact with any custom schema you've created for deals, bios, or projects.

Connect to your AI in seconds.

Create record

Delete record

Get record details

Pitchly MCP Server: 11 Tools for Data Record Management

Make your AI actually useful.

Create Record

Delete Record

Get Record Details

Get Table Details

Get Workspace Details

List Fields

List Table Records

List Tables

List Workspaces

Search Records

Update Record

Security and governance baked right in.

Claude AI

Open Claude Settings

Add Custom Connector

Start a conversation

Claude Code

Open your terminal

Add the MCP Server

Start coding

Cursor

One-Click Install (Recommended)

Open Cursor Settings

Add New Server

Use in Composer

Antigravity

Configure Agent Environment

Bind the Endpoint

Execute

VS Code Copilot

One-Click Install (Recommended)

Open MCP Settings

Add Server Config

Windsurf

One-Click Install (Recommended)

Open Windsurf Settings

Add Server Endpoint

LangChain

Install Dependencies

Connect the Server

CrewAI

Define the Tool

Execute Task

Choose How to Get Started

Build Your Own

Make Your AI Do More

Works with Claude, ChatGPT, Cursor, and more

Manually building pitch decks from siloed company history takes forever.

Pitchly MCP Server: Control your data flow with Pitchly.

What your AI can actually do with this

Here's how it actually works

Who is this actually for?

What Changes When You Connect

See it in action

Client Pitch Prep: Finding a single source of truth for team experience.

Post-Meeting Data Logging: Capturing new deal progress.

Data Audit: Checking if all team bios are complete.

Updating a Project: Changing status and adding new team members.

The honest tradeoffs

Trying to filter data locally.

Assuming data consistency across tables.

Relying on general chat for structured data.

When It Fits, When It Doesn't

Questions you might have