# Pitchly MCP > 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. ## Overview - **Category:** industry-titans - **Price:** Free - **Tags:** experience-data, professional-services, content-automation, data-tables, pitch-materials ## Description 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. ## Tools ### 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 natural language input. ### update_record Changes the value of one or more fields in an existing record. ## Prompt Examples **Prompt:** ``` List all tables in my 'Corporate' workspace in Pitchly. ``` **Response:** ``` I've retrieved your tables. You have 3 active collections: 'Tombstones', 'Professional Bios', and 'Client Projects'. Which one would you like to see records for? ``` **Prompt:** ``` Show me all records in the Client Engagements table that were updated this week. ``` **Response:** ``` 14 records updated this week in "Client Engagements". Notable changes: "Acme Corp Advisory" moved from Active to Completed (partner: James Park). "TechFlow Due Diligence" updated with new financial data (3 fields modified). "Meridian M&A" added 2 new team members. 4 records had status changes, 6 had field updates, and 4 had new attachments. Most active editor: Sarah Chen with 8 modifications. ``` **Prompt:** ``` Create a new record in the Deal Pipeline table for the ScaleUp Technologies opportunity. ``` **Response:** ``` Record created in "Deal Pipeline" (ID: rec_8472). Client: ScaleUp Technologies. Stage: Qualification. Estimated Value: $340,000. Lead Partner: assigned to your team. Industry: Enterprise Software. The record has been linked to 2 existing contact records and the associated workspace "Technology Sector". Next step field set to "Initial Assessment" due in 5 business days. ``` ## Capabilities ### 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. ## Use Cases ### 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. ### 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. ### 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. ### 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. ## Benefits - 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. ## How It 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. 1. First, subscribe to the server and provide your Pitchly API Key (Bearer Token) in your AI client settings. 2. 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. 3. 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`. ## Frequently Asked Questions **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.