What features of PracticePanther are available through this API?

The API provides access to: Matters/Cases (CRUD operations), Contacts/Clients (create and list), Time Entries (list and create), Bills/Invoices (list and get), Payments (list), Tasks (list), Calendar Events (list), Custom Fields (list), Activities (list), and Expenses (list). The API supports OData filtering, ordering, and pagination for flexible queries across all resources.

How do I get a PracticePanther API access token?

PracticePanther uses OAuth 2 authentication. Visit the PracticePanther OAuth authorization endpoint to authorize your application, then exchange the authorization code for an access token at the token endpoint. The access token is a Bearer token used in the Authorization header for all API requests. Contact PracticePanther support if you need help setting up API access for your firm.

Can I filter and order results using OData?

Yes! PracticePanther's API supports full OData query options. Use $filter for filtering (e.g. "Status eq 'Open'"), $orderby for ordering (e.g. "CreatedDate desc"), $top for limiting results, and $skip for pagination. These parameters are available on all list tools. For example, to find open matters ordered by creation date: use filter="Status eq 'Open'" and orderby="CreatedDate desc".

How do I track billable time with PracticePanther API?

Use `create_practicepanther_time_entry` to log time against any matter. Provide the matter GUID, description of work, and duration in minutes. You can specify whether the entry is billable and set a custom hourly rate. Use `list_practicepanther_time_entries` to view all time logged against a specific matter or across all matters.

PracticePanther MCP Server for Pydantic AI 18 tools — connect in under 2 minutes

Name: PracticePanther
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 18 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect PracticePanther through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to PracticePanther "
            "(18 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in PracticePanther?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About PracticePanther MCP Server

Connect to PracticePanther legal practice management platform and manage your entire law practice from any AI agent. Access matters, contacts, documents, time entries, calendar events, bills, payments, tasks, and expenses—all through a unified REST API with OData support.

Pydantic AI validates every PracticePanther tool response against typed schemas, catching data inconsistencies at build time. Connect 18 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Matters/Cases — List, search, create, and update legal matters with status, client, and practice area
Contacts/Clients — Manage your client database including individuals, organizations, and opposing parties
Time Tracking — Log billable and non-billable time entries against any matter
Bills/Invoices — List and review bills with amounts, status, and line items
Payments — Track payments received from clients
Tasks — View and manage tasks associated with matters and contacts
Calendar — View court dates, hearings, deadlines, and meetings
Custom Fields — Access custom fields configured for matters and contacts
Activities — Track calls, emails, meetings, and notes
Expenses — Log and review expenses associated with matters
OData Support — Use powerful OData filtering, ordering, and pagination for flexible queries

The PracticePanther MCP Server exposes 18 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect PracticePanther to Pydantic AI via MCP

Follow these steps to integrate the PracticePanther MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 18 tools from PracticePanther with type-safe schemas

Why Use Pydantic AI with the PracticePanther MCP Server

Pydantic AI provides unique advantages when paired with PracticePanther through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your PracticePanther integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your PracticePanther connection logic from agent behavior for testable, maintainable code

PracticePanther + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the PracticePanther MCP Server delivers measurable value.

Type-safe data pipelines: query PracticePanther with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple PracticePanther tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query PracticePanther and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock PracticePanther responses and write comprehensive agent tests

PracticePanther MCP Tools for Pydantic AI (18)

These 18 tools become available when you connect PracticePanther to Pydantic AI via MCP:

create_practicepanther_contact

USE WHEN: - User wants to add a new client - User needs to create a new contact record - User asks to "add a new contact" or "create a client" PARAMETERS: - first_name (REQUIRED): Contact's first name - last_name (REQUIRED): Contact's last name - email (OPTIONAL): Contact's email address - phone (OPTIONAL): Contact's phone number - type (OPTIONAL): Contact type — "Client", "Opposing Party", "Witness", "Referral Source", etc. EXAMPLES: - "Add a new contact John Smith" → call with first_name="John", last_name="Smith" - "Create client Jane Doe, jane@example.com, 555-0123" → call with first_name="Jane", last_name="Doe", email="jane@example.com", phone="555-0123", type="Client" Create a new contact/client in PracticePanther

create_practicepanther_matter

USE WHEN: - User wants to open a new legal matter - User needs to create a new case for a client - User asks to "create a new matter" or "open a case" PARAMETERS: - name (REQUIRED): Matter/case name - client_id (OPTIONAL): GUID of the contact/client this matter belongs to - status (OPTIONAL): Matter status (e.g. "Open", "Closed", "Pending") - description (OPTIONAL): Matter description - practice_area (OPTIONAL): Practice area for this matter EXAMPLES: - "Create a new matter called 'Smith Divorce'" → call with name="Smith Divorce" - "Open a new personal injury case for client John Smith" → call with name="Smith v. Johnson", client_id="client-guid" Create a new matter/case in PracticePanther

create_practicepanther_time_entry

USE WHEN: - User wants to log time spent on a matter - User needs to record billable hours - User asks to "add time entry" or "log hours" PARAMETERS: - matter_id (REQUIRED): GUID of the matter this time entry belongs to - description (REQUIRED): Description of the work performed - duration_minutes (REQUIRED): Duration in minutes - billable (OPTIONAL): Whether this is billable — true (default) or false - rate (OPTIONAL): Hourly rate for this entry EXAMPLES: - "Log 2 hours of legal research for matter 123" → call with matter_id="123", description="Legal research", duration_minutes=120 - "Add 30 minute phone call with client" → call with matter_id="123", description="Phone call with client", duration_minutes=30 Create a new time entry for billing

get_practicepanther_bill

Get detailed information for a specific bill/invoice

get_practicepanther_contact

Get detailed information for a specific contact/client

get_practicepanther_matter

Get detailed information for a specific matter/case

list_practicepanther_activities

List activities in PracticePanther

list_practicepanther_bills

List bills/invoices in PracticePanther

list_practicepanther_calendar_events

List calendar events in PracticePanther

list_practicepanther_contacts

USE WHEN: - User wants to see all their contacts and clients - User needs to find a contact by name or email - User is exploring their contact database - User asks "list my contacts" or "show all clients" PARAMETERS: - top (OPTIONAL): Number of results to return - skip (OPTIONAL): Number of results to skip for pagination - orderby (OPTIONAL): OData order expression (e.g. "LastName asc") - filter (OPTIONAL): OData filter expression (e.g. "Email ne null") EXAMPLES: - "List all my contacts" → call with no params - "Show my clients only" → call with filter="Type eq 'Client'" - "List contacts ordered by last name" → call with orderby="LastName asc" List all contacts/clients in PracticePanther

list_practicepanther_custom_fields

List custom fields defined in PracticePanther

list_practicepanther_expenses

List expenses in PracticePanther

list_practicepanther_matters

Supports OData filtering, ordering, and pagination for flexible queries. USE WHEN: - User wants to see all their legal matters/cases - User needs to find matters by status, client, or practice area - User is exploring their law firm's caseload - User asks "what matters do I have" or "list my open cases" PARAMETERS: - top (OPTIONAL): Number of results to return (e.g. "10", "50", "100") - skip (OPTIONAL): Number of results to skip for pagination - orderby (OPTIONAL): OData order expression (e.g. "CreatedDate desc", "Name asc") - filter (OPTIONAL): OData filter expression (e.g. "Status eq 'Open'") EXAMPLES: - "List all my matters" → call with no params - "Show my open cases" → call with filter="Status eq 'Open'" - "List matters ordered by creation date" → call with orderby="CreatedDate desc" List all matters/cases in PracticePanther

list_practicepanther_payments

List payments received in PracticePanther

list_practicepanther_tasks

List tasks in PracticePanther

list_practicepanther_time_entries

Supports filtering by matter, user, and date range. USE WHEN: - User wants to see all logged time entries - User needs to review billable hours for a matter - User is preparing invoices or reviewing time reports - User asks "show my time entries" or "list billable hours" PARAMETERS: - top (OPTIONAL): Number of results to return - skip (OPTIONAL): Number of results to skip for pagination - orderby (OPTIONAL): OData order expression (e.g. "Date desc") - filter (OPTIONAL): OData filter expression (e.g. "Matter/Name eq 'Smith Divorce'") EXAMPLES: - "List all time entries" → call with no params - "Show time entries for this matter" → call with filter="MatterId eq 'matter-guid'" - "List time entries from newest to oldest" → call with orderby="Date desc" List time entries logged in PracticePanther

search_practicepanther_matters

USE WHEN: - User wants to search for specific matters - User needs to find matters by name, client, or status - User asks to "find matters about X" or "search for open cases" PARAMETERS: - filter (REQUIRED): OData filter expression (e.g. "contains(Name, 'Smith')", "Status eq 'Open'") - top (OPTIONAL): Number of results to return - orderby (OPTIONAL): OData order expression EXAMPLES: - "Search for matters containing 'Smith'" → call with filter="contains(Name, 'Smith')" - "Find all open personal injury cases" → call with filter="Status eq 'Open' and PracticeArea eq 'Personal Injury'" Search matters/cases using OData filter

update_practicepanther_matter

Update an existing matter/case in PracticePanther

Example Prompts for PracticePanther in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with PracticePanther immediately.

"List all my open matters in PracticePanther."

"Create a new time entry for 2 hours of legal research on the Smith Divorce matter."

"Show me all contacts for client John Smith."

Troubleshooting PracticePanther MCP Server with Pydantic AI

Common issues when connecting PracticePanther to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

PracticePanther + Pydantic AI FAQ

Common questions about integrating PracticePanther MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer. your PracticePanther MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.