The MCP Uber Server enables AI assistants to book and manage Uber rides through a secure OAuth 2.0 integration with the Uber API. It allows you to:
Authenticate Users: Generate OAuth authorization URLs and set access tokens
Get Price Estimates: Fetch fare estimates between locations using coordinates
Request Rides: Book Uber rides with specific product IDs and details
Track Ride Status: Monitor ongoing ride requests
Cancel Rides: Terminate active ride requests
Provides tools for booking Uber rides, including getting price estimates, requesting rides, checking ride status, and canceling rides through the Uber API.
Click on "Install 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., "@MCP Uber Server get price estimate from Union Square to SFO airport"
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.
An MCP (Model Context Protocol) server for booking Uber rides through AI assistants.
OAuth 2.0 authentication with Uber
Get price estimates for rides
Request Uber rides
Check ride status
Cancel rides
Related MCP server: @striderlabs/mcp-ubereats
npm install -g mcp-ubernpx mcp-uberGo to Uber Developer Dashboard
Click "Sign in" and either:
Use an existing Uber rider/driver account
Create a new account specifically for development
💡 Tip: For organizations, create an email alias (e.g., dev@yourcompany.com) instead of using a personal account for easier ownership transfer.
In the Developer Dashboard, click "Create App" (top right corner)
Fill in the required information:
App Name: Your application name
Description: Brief description of what your app does
Click "Create"
Navigate to your app in the dashboard
Go to the Auth tab
You'll find:
Client ID: Public identifier for your app
Client Secret: Private key (keep this secure!)
Server Token: For server-side requests
In the Auth tab, add your redirect URI:
For local testing: http://localhost:3000/callback
For production: Your actual callback URL
Select required scopes:
profile - User's basic profile information
request - Request rides on user's behalf
ride_request - View and manage active ride requests
⚠️ Note: The request scope is privileged and requires Uber approval for production use. During development, your account can use it without approval.
Create environment variables with your credentials (see Configuration section below)
Add to your Claude Desktop configuration (~/Library/Application Support/Claude/claude_desktop_config.json):
{
"mcpServers": {
"uber": {
"command": "mcp-uber",
"env": {
"UBER_CLIENT_ID": "your_client_id",
"UBER_CLIENT_SECRET": "your_client_secret",
"UBER_REDIRECT_URI": "http://localhost:3000/callback",
"UBER_ENVIRONMENT": "sandbox"
}
}
}
}Add to your Claude Desktop configuration:
{
"mcpServers": {
"uber": {
"command": "npx",
"args": ["mcp-uber"],
"env": {
"UBER_CLIENT_ID": "your_client_id",
"UBER_CLIENT_SECRET": "your_client_secret",
"UBER_REDIRECT_URI": "http://localhost:3000/callback",
"UBER_ENVIRONMENT": "sandbox"
}
}
}
}uber_get_auth_url - Get OAuth authorization URL
uber_set_access_token - Set user's access token
uber_get_price_estimates - Get price estimates for a ride
uber_request_ride - Request an Uber ride
uber_get_ride_status - Check ride request status
uber_cancel_ride - Cancel a ride request
Use uber_get_auth_url to get the authorization URL
User visits the URL and authorizes your app
After callback, exchange the code for an access token
Use uber_set_access_token to store the token
Now you can make API calls
The MCP server requires the following environment variables:
UBER_CLIENT_ID: Your Uber app client ID
UBER_CLIENT_SECRET: Your Uber app client secret
UBER_REDIRECT_URI: OAuth callback URL (default: http://localhost:3000/callback)
UBER_ENVIRONMENT: Either sandbox or production (default: sandbox)
Use sandbox mode for testing:
Set UBER_ENVIRONMENT=sandbox in your environment
Sandbox mode simulates ride requests without real drivers
Perfect for development and testing
Test the OAuth flow:
Use the uber_get_auth_url tool to get an authorization URL
Visit the URL and authorize your app
After authorization, Uber will redirect to your callback URL with a code
Exchange the code for an access token (you'll need to set up your own callback handler)
Use uber_set_access_token to store the token in the MCP server
Setting up a callback handler:
For testing, you can use a simple Express server (see examples/oauth-server.js in the GitHub repo)
For production, implement a secure callback handler in your application
The callback URL must match exactly what's configured in your Uber app
Sandbox Mode (default):
Simulated rides and drivers
No real charges
Perfect for testing
Limited to your developer account
Production Mode:
Real rides and charges
Requires Uber approval for privileged scopes
Must pass Uber's review process
Never commit credentials: Keep your Client Secret secure
Use environment variables: Don't hardcode credentials
Implement proper token storage: The current in-memory storage is for demo only
Validate redirect URIs: Ensure your callback URLs are properly configured
Rate limits apply (check Uber's documentation)
Privileged scopes require approval for production use
Sandbox mode has some limitations compared to production
"Invalid scope" error: Your app needs approval for privileged scopes in production
"Invalid redirect URI": Make sure your redirect URI exactly matches what's configured in the Uber dashboard
"Unauthorized" errors: Check that your access token is valid and not expired
Cancel an ongoing ride request
| Name | Required | Description | Default |
|---|---|---|---|
| userId | Yes | Unique identifier for the user | |
| requestId | Yes | Ride request ID to cancel |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It states the action ('Cancel') but lacks details on side effects (e.g., cancellation fees, refund policies), permissions required, rate limits, or error conditions. This is inadequate for a mutation tool with zero annotation coverage.
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 a single, efficient sentence with zero waste. It is front-loaded with the core action and resource, making it easy to parse. Every word earns its place by directly contributing to understanding the tool's purpose.
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 complexity as a mutation operation with no annotations and no output schema, the description is incomplete. It fails to address critical aspects like return values, error handling, or behavioral implications (e.g., irreversible changes). This leaves significant gaps for an AI agent to use the tool effectively.
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 100%, with both parameters ('userId' and 'requestId') documented in the schema. The description does not add any parameter-specific details beyond what the schema provides, such as format examples or contextual usage. The baseline score of 3 reflects adequate but minimal value addition.
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 specific action ('Cancel') and resource ('an ongoing ride request'), distinguishing it from sibling tools like 'uber_request_ride' (create) or 'uber_get_ride_status' (read). It uses precise language that directly communicates the tool's function without ambiguity.
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 no guidance on when to use this tool versus alternatives. It does not mention prerequisites (e.g., needing an active ride request), exclusions (e.g., cannot cancel completed rides), or comparisons with sibling tools like 'uber_get_ride_status' for checking status first. Usage is implied but not explicitly defined.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get the Uber authorization URL for user to authenticate
| Name | Required | Description | Default |
|---|---|---|---|
| userId | Yes | Unique identifier for the user |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It states the tool retrieves an authorization URL but doesn't describe what the URL is used for, whether it's one-time use, expiration behavior, required user interaction, or error handling. For an authentication tool with zero annotation coverage, this is a significant gap.
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 a single, efficient sentence that directly states the tool's purpose with zero waste. It is appropriately sized and front-loaded, making it easy to parse quickly.
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 complexity of authentication flows, no annotations, and no output schema, the description is incomplete. It doesn't explain what the authorization URL is, how it should be used, what the expected output format is, or potential errors. For a tool with critical security implications, this leaves significant 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?
The schema description coverage is 100%, with the single parameter 'userId' documented as 'Unique identifier for the user'. The description adds no additional parameter semantics beyond what the schema provides, so the baseline score of 3 is appropriate given the schema does the heavy lifting.
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 with a specific verb ('Get') and resource ('Uber authorization URL'), and specifies the target ('for user to authenticate'). It distinguishes itself from siblings like ride management tools, though it doesn't explicitly differentiate from potential authentication-related siblings (none exist in the list).
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 implies usage in authentication flows but provides no explicit guidance on when to use this tool versus alternatives (e.g., uber_set_access_token for token management) or prerequisites. It suggests a context of user authentication but lacks details on timing or integration steps.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get price estimates for a ride between two locations
| Name | Required | Description | Default |
|---|---|---|---|
| userId | Yes | Unique identifier for the user | |
| startLatitude | Yes | Starting location latitude | |
| startLongitude | Yes | Starting location longitude | |
| endLatitude | Yes | Destination latitude | |
| endLongitude | Yes | Destination longitude |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool's function but doesn't reveal critical traits such as whether it's a read-only operation, if it requires authentication, potential rate limits, or what the output looks like (e.g., estimated price range, ride options). This leaves significant gaps for an agent to understand how to interact with it effectively.
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 a single, efficient sentence that front-loads the key action and resource without any wasted words. It's appropriately sized for a straightforward tool, making it easy for an agent to parse quickly.
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 complexity (5 required parameters, no annotations, no output schema), the description is insufficiently complete. It doesn't address behavioral aspects like authentication needs, output format, or error handling, which are crucial for an agent to use the tool correctly in real-world scenarios. The high parameter count and lack of structured support amplify this gap.
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 100%, with all parameters clearly documented in the input schema (e.g., 'userId', latitude/longitude pairs). The description adds minimal value beyond this, only implying that parameters define start and end locations without providing additional context like coordinate formats or user ID requirements. This meets the baseline for high schema coverage.
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 action ('Get price estimates') and resource ('for a ride between two locations'), making the purpose immediately understandable. However, it doesn't differentiate this from potential sibling tools like 'uber_request_ride' which might also involve pricing, though the distinction is somewhat implied through the 'estimates' keyword.
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 no explicit guidance on when to use this tool versus alternatives like 'uber_request_ride' or 'uber_get_ride_status'. It mentions the core function but lacks context about prerequisites (e.g., whether authentication is needed) or typical use cases (e.g., planning vs. booking).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get the current status of a ride request
| Name | Required | Description | Default |
|---|---|---|---|
| userId | Yes | Unique identifier for the user | |
| requestId | Yes | Ride request ID |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It states the tool retrieves status, implying a read-only operation, but doesn't cover critical aspects like authentication requirements, rate limits, error conditions, or what the status response includes (e.g., driver location, ETA). This leaves significant gaps for safe and effective use.
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 a single, efficient sentence that directly states the tool's purpose without unnecessary words. It's front-loaded and wastes no space, making it easy for an agent to parse quickly.
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 complexity of a ride status tool with no annotations and no output schema, the description is incomplete. It doesn't explain what the status includes (e.g., pending, en route, completed), how to interpret results, or error handling, which are essential for an agent to use this tool effectively in real-world scenarios.
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 100% description coverage, clearly documenting both required parameters ('userId' and 'requestId'). The description doesn't add any meaning beyond the schema, such as explaining how to obtain these IDs or their format, but the schema's completeness justifies the baseline score of 3.
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 with a specific verb ('Get') and resource ('current status of a ride request'), making it easy to understand what it does. However, it doesn't explicitly differentiate from sibling tools like 'uber_get_auth_url' or 'uber_get_price_estimates', which prevents a perfect score.
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 no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., needing a ride request ID from 'uber_request_ride'), exclusions, or comparisons to siblings like 'uber_cancel_ride', leaving the agent to infer usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Request an Uber ride
| Name | Required | Description | Default |
|---|---|---|---|
| userId | Yes | Unique identifier for the user | |
| productId | Yes | Uber product ID (from price estimates) | |
| startLatitude | Yes | Starting location latitude | |
| startLongitude | Yes | Starting location longitude | |
| endLatitude | Yes | Destination latitude | |
| endLongitude | Yes | Destination longitude | |
| fareId | No | Fare ID from price estimate |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. 'Request an Uber ride' implies a write/mutation operation that likely requires authentication, triggers real-world consequences (ride dispatch), and may have rate limits or payment implications, but none of these behavioral traits are mentioned. The description is minimal and fails to address critical operational aspects.
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 extremely concise at just three words, with zero wasted language. It's front-loaded with the core action and resource. While this conciseness comes at the cost of completeness, as a standalone statement it's efficiently structured.
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 complexity of a ride-request tool (real-world mutation with financial implications), no annotations, no output schema, and 7 parameters, the description is inadequate. It doesn't address authentication needs, response format, error conditions, or how this fits with sibling tools. The minimal description fails to provide sufficient context for safe and effective use.
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 100% description coverage, providing clear documentation for all 7 parameters. The tool description adds no additional parameter semantics beyond what's in the schema, so it meets the baseline of 3. However, it doesn't explain relationships between parameters (e.g., that fareId from price estimates is optional but recommended) or usage patterns.
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 'Request an Uber ride' clearly states the action (request) and resource (Uber ride), making the purpose immediately understandable. However, it doesn't differentiate from sibling tools like 'uber_cancel_ride' or 'uber_get_ride_status', which would require more specific language about initiating a new ride request versus managing existing ones.
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 no guidance on when to use this tool versus alternatives like 'uber_get_price_estimates' (which might be needed first to obtain productId/fareId) or 'uber_cancel_ride' (for post-request actions). It lacks context about prerequisites, timing, or workflow relationships with sibling tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Set the access token for a user after OAuth callback
| Name | Required | Description | Default |
|---|---|---|---|
| userId | Yes | Unique identifier for the user | |
| accessToken | Yes | Uber access token for the user |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It mentions setting an access token, implying a write/mutation operation, but doesn't disclose behavioral traits like whether this overwrites existing tokens, requires specific permissions, or has side effects like rate limits or authentication changes.
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 a single, efficient sentence that front-loads the purpose without unnecessary details. It earns its place by clearly stating the tool's function and context, with zero waste.
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 no annotations, no output schema, and a mutation tool (implied by 'Set'), the description is incomplete. It lacks details on what happens after setting the token, error conditions, or how this integrates with other Uber tools, leaving gaps for an AI agent to understand full behavior.
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 100%, so the schema already documents both parameters ('userId' and 'accessToken') adequately. The description doesn't add meaning beyond what the schema provides, such as explaining token format or user context, but baseline 3 is appropriate given high schema coverage.
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 action ('Set') and resource ('access token for a user'), specifying it occurs 'after OAuth callback'. However, it doesn't distinguish this from sibling tools like 'uber_get_auth_url', which might also relate to authentication flow.
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 implies usage context ('after OAuth callback'), suggesting when to use this tool, but doesn't explicitly state when not to use it or name alternatives. For example, it doesn't clarify if this is for initial token setup versus token refresh.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Each tool has a clearly distinct purpose with no overlap: authorization (get_auth_url, set_access_token), ride lifecycle (request_ride, get_ride_status, cancel_ride), and price estimation (get_price_estimates). The descriptions reinforce these distinct roles, making tool selection straightforward for an agent.
All tools follow a consistent 'uber_verb_noun' pattern with snake_case throughout (e.g., uber_cancel_ride, uber_get_price_estimates). This predictability makes the tool set easy to navigate and understand at a glance.
With 6 tools, this server is well-scoped for its Uber ride-hailing domain. It covers essential operations without bloat: authentication, price checks, ride requests, status tracking, and cancellation. Each tool earns its place in supporting a complete workflow.
The tool set provides complete coverage for the Uber ride lifecycle: authentication (get_auth_url, set_access_token), pre-ride (get_price_estimates), active ride (request_ride, get_ride_status, cancel_ride). There are no obvious gaps; agents can handle the full process from login to ride completion or cancellation.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Flight search MCP server providing search, pagination, and itinerary details for AI assistants.
Hosted MCP server connecting AI assistants to 9,000+ apps and 40,000+ actions via Zapier.
MCP server for building and testing AI agents with multi-model experimentation and insights.
MCP server that lets AI assistants use all OneSchema features exposed via the public API.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/199-mcp/mcp-uber'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
