Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Ravira MCP Server ask Ravira: do you accept my insurance?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Connect AI assistants (Claude, Cursor, etc.) directly to Ravira — the AI receptionist built for dental practices.
This MCP server gives any compatible AI tool access to Ravira's capabilities:
Tool | Description |
| Ask a patient question, see Ravira's AI response |
| Full feature overview of Ravira |
| Real example patient chat flows |
| Dental info on common patient questions |
| Book a live demo with Purnima |
Related MCP server: dental-ai
cd mcp-server
pip install mcp[cli] httpxcp .env.example .env
# Edit .env with your Ravira API URL and demo widget keyEdit your Claude Desktop config file:
Mac: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"ravira": {
"command": "python",
"args": ["C:/path/to/Ravira - Dental AI/mcp-server/server.py"]
}
}
}Restart Claude Desktop — you'll see Ravira tools available!
In Claude Desktop, try:
"Ask Ravira: do you accept Delta Dental?"
"Show me Ravira's features"
"Show me a sample dental patient conversation"
"Search dental topics: root canal"
To list Ravira in the official MCP Registry:
Push this folder to a public GitHub repo
Follow the guide at: https://modelcontextprotocol.io/registry/quickstart
Purnima — Founder of Ravira Website: ravira.ai
Ask Ravira a patient question and see the AI receptionist's response.
This demonstrates how Ravira handles real patient inquiries — including questions about hours, services, pricing, insurance, and appointment booking.
Args: patient_question: The patient's question (e.g. "Do you accept Delta Dental?", "I have a toothache — can I get seen today?", "How much does a cleaning cost?") practice_name: The dental practice name (default: Seattle Family Dentistry)
| Name | Required | Description | Default |
|---|---|---|---|
| patient_question | Yes | ||
| practice_name | No | Seattle Family Dentistry |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so the description carries full burden. It mentions that the tool 'demonstrates how Ravira handles real patient inquiries' but does not disclose behavioral traits such as response latency, auth requirements, or whether the AI is simulated. The return value is vaguely described as 'the AI receptionist's response'.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured with a brief statement, a sentence on scope, and an Args block. It is concise without superfluous details, though the examples could be more compact.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity and the presence of an output schema, the description covers the basic purpose and parameters. However, it lacks detail on the response format (e.g., plain text vs structured data) and error handling, which would complete the context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, but the description adds meaning with an Args block: patient_question includes examples, and practice_name states a default. This compensates for the sparse schema, providing clear context beyond type and title.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Ask Ravira a patient question and see the AI receptionist's response.' It specifies the verb 'ask' and the resource 'Ravira', and differentiates from sibling tools (e.g., get_ravira_features, search_dental_topics) by focusing on interactive Q&A.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides examples of suitable questions ('hours, services, pricing, insurance, appointment booking'), implying when to use. However, it does not explicitly state when not to use or compare with alternatives like search_dental_topics for static information.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get a full overview of Ravira's features and capabilities.
Use this to learn what Ravira offers dental practices, including its AI chat widget, knowledge base, appointment booking, escalation system, and HIPAA compliance.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must handle behavioral disclosure. It implies a read-only operation by being a 'get', but does not explicitly state that it has no side effects, requires no authentication, or any other behavioral traits.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise with two sentences that front-load the primary purpose immediately. Every sentence adds value, with no redundant or vague phrases.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given zero parameters and an existing output schema, the description adequately lists key features returned. It could be more precise about the structure of the output, but it provides enough context for an agent to decide when to use this tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has zero parameters, and schema description coverage is 100%. The description adds value by specifying what the overview includes (e.g., features, HIPAA compliance), which is beyond the empty schema. Baseline for high coverage is 3, but the additional context warrants a 4.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Get' and the resource 'full overview of Ravira's features and capabilities'. It lists specific features (AI chat widget, knowledge base, etc.), making the purpose distinct from sibling tools like ask_ravira or search_dental_topics.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly says 'Use this to learn what Ravira offers', providing clear context. It doesn't mention when not to use or alternatives, but the absence of parameters and the overview nature make it self-evident.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
See real example patient conversations handled by Ravira.
Shows how Ravira manages common dental patient inquiries including appointment booking, insurance questions, emergency triage, and more.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description must disclose behavioral traits. Only states it shows examples; lacks details about read-only nature, side effects, pagination, or limitations. Minimal information for a tool with no annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two concise sentences that front-load the purpose. Every sentence adds value without redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Output schema exists, so return value details are covered. However, description omits behavioral context like read-only nature or result ordering, leaving minor gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
No parameters in input schema, so description does not need to add parameter information. Baseline 4 for zero-parameter tools.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states the action ('See real example patient conversations') and resource ('handled by Ravira'). Distinct from siblings like ask_ravira and get_ravira_features, which serve different functions.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Implies when to use (to view sample conversations) but does not explicitly specify when not to use or provide alternatives. However, the context is clear enough for an agent to decide.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Request a live demo of Ravira for your dental practice.
Submit your contact info and Purnima (Ravira's founder) will reach out to schedule a personalized 20-minute demo.
Args: name: Your name (e.g. "Dr. Sarah Johnson" or "Mike - Office Manager") practice_name: Name of your dental practice email: Best email to reach you phone: Phone number (optional) best_time: Best time to call (e.g. "Tuesday morning", "weekday afternoons")
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | ||
| practice_name | Yes | ||
| Yes | |||
| phone | No | ||
| best_time | No | anytime |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description outlines the outcome: Purnima reaches out to schedule a 20-minute demo. No annotations exist, so the description carries full burden. It could add idempotency or data handling details, but the disclosed behavior is clear and sufficient for a simple demo request.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is brief but complete: a two-sentence overview followed by a structured Args list. Every sentence adds value, and the format is easy for an AI to parse.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description covers purpose, parameters, and outcome. An output schema exists but not shown; the description doesn't need to repeat return values. No critical gaps remain.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%, but the description provides meaningful examples and format guidance for each parameter (e.g., name format, best_time examples). This adds significant value beyond the schema's type definitions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description explicitly states the tool requests a live demo of Ravira for a dental practice, including the process after submission. It clearly distinguishes from sibling tools like ask_ravira or get_ravira_features.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The usage context is implied: use this to request a demo. Siblings cover different functions (Q&A, features, conversations, search), so no ambiguity. However, there is no explicit 'when not to use' or alternative tools mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search for information about common dental topics that patients ask about.
Covers procedures, insurance, hygiene, costs, and common conditions. Useful for understanding the types of questions Ravira handles daily.
Args: topic: The dental topic to look up (e.g. "root canal", "whitening", "insurance", "braces", "implants", "cleaning", "emergency")
| Name | Required | Description | Default |
|---|---|---|---|
| topic | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations; description only says 'search for information' without disclosing read-only nature, rate limits, or scope of results.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Concise with clear opening sentence and bullet-like examples. Could be more structured with explicit sections.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Adequate for a simple lookup tool with output schema present, but does not describe the form of returned information.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Adds value over schema by providing concrete examples of valid topics (e.g., root canal, whitening), though no format or enum constraints.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states 'Search for information about common dental topics' with examples. Differentiates from siblings implicitly but not explicitly.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Implies usage for understanding patient questions but no explicit when-to-use or alternatives compared to siblings like ask_ravira.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.0ask_raviraget_ravira_featuresget_sample_conversationsrequest_demosearch_dental_topicsScored across 5 tools
Each tool has a distinct purpose: ask_ravira for patient queries, get_ravira_features for overview, get_sample_conversations for examples, request_demo for scheduling, and search_dental_topics for information. No two tools overlap significantly.
All tool names use snake_case with verbs (ask, get, request, search). However, the verbs are not uniform (two 'get' tools but different objects), and the pattern is not strictly verb_noun (e.g., ask_ravira is verb_practice). Still, it's readable and clear.
Five tools is appropriate for a server that showcases an AI receptionist service. Each tool covers a key aspect: interaction, feature overview, examples, demo request, and dental topic lookup. Not too many or too few.
The tool set covers the main use cases for a demo server, but there is a minor gap: no direct appointment booking tool, though ask_ravira can simulate it. Overall, the surface is adequate for the intended purpose.
Connect your team's living knowledge base — docs, data, issues, CRM — to Claude and ChatGPT.
Connect Claude to Fathom meeting recordings, transcripts, and summaries
Connect AI tools to Weav customer service. Search conversations, reply, and manage knowledge.
Connect your AI assistant to Revensi OS agents, workflows, and business data.
