Apidog MCP. Read API Contracts, Build Code, Test Endpoints.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
Apidog. Sync your API workflow with your AI agent. Use this server to list projects, fetch endpoint schemas, and export full OpenAPI specifications instantly.
You can ask your AI client to review API contracts, discover data models, or generate complete OpenAPI 3.0 JSON files without leaving your chat window.
What your AI agents can do
Export openapi
Exports the full OpenAPI 3.0 specification of an Apidog project as a JSON file.
Get endpoint
Fetches the complete schema and structure for a single API endpoint.
List endpoints
Lists all API endpoints defined within a specific Apidog project.
Lists all API projects defined in your connected Apidog organization.
Retrieves a list of all HTTP routes within a specific API project.
Fetches the complete schema and structure for one specific API endpoint.
Lists all reusable data models (DTOs or entities) defined in the project.
Generates a complete OpenAPI 3.0 JSON specification for the entire project.
Ask AI about this MCP
Supported MCP Clients
Gemini Waiting for input…
Apidog MCP Server: 5 Tools for API Contracts
These tools let your agent discover, inspect, and export every part of your Apidog API contracts, from projects to schemas.
019d754fexport openapi
Exports the full OpenAPI 3.0 specification of an Apidog project as a JSON file.
019d754fget endpoint
Fetches the complete schema and structure for a single API endpoint.
019d754flist endpoints
Lists all API endpoints defined within a specific Apidog project.
019d754flist projects
Lists all API projects within your connected Apidog organization.
019d754flist schemas
Lists all reusable data model schemas (DTOs, entities) defined in the project.
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
Make Your AI Do More
Start with Apidog, then connect any of our 4,700+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,700+ 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
What you can do with this MCP connector
Sync your API workflow with your AI agent. Use this server to list projects, fetch endpoint schemas, and export full OpenAPI specifications instantly. You can ask your AI client to review API contracts, discover data models, or generate complete OpenAPI 3.0 JSON files without leaving your chat window.
Discover API Projects: Use list_projects to see all API projects in your connected Apidog organization.
List All Endpoints: Use list_endpoints to retrieve every HTTP route within a specific API project.
Get Single Endpoint Details: Use get_endpoint to fetch the full schema and structure for one specific API endpoint, including the method, path parameters, headers, and exact request/response body schemas.
List Data Schemas: Use list_schemas to list every reusable data model—whether it's a DTO or an entity—defined in the project.
Export OpenAPI JSON: Use export_openapi to generate a complete OpenAPI 3.0 JSON specification for the entire project.
How Apidog MCP Works
- 1 Subscribe to the Apidog server and enter your Personal Apidog API Access Token.
- 2 Tell your AI client to perform an API action, like 'List all projects in the E-commerce API'.
- 3 The agent uses the appropriate tool, gets the data, and returns the structured results to your chat.
The bottom line is you let your agent handle the API contract details, keeping your focus on the code.
Who Is Apidog MCP For?
This is for the backend engineer who needs to generate unit tests and controllers fast. It's for the frontend developer who needs to write TypeScript interfaces without guessing the API structure. It's for QA automation teams who need predictable response payloads to build solid integration tests.
Uses export_openapi or get_endpoint to give the LLM full API context, allowing it to safely scaffold controllers or unit tests.
Asks the AI to inspect an endpoint schema using get_endpoint and generates the required TypeScript interfaces or API service layers.
Runs the agent to fetch expected response payloads for specific endpoints, building robust integration tests without manual API calls.
What Changes When You Connect
- Get full context instantly: Use
export_openapito generate the entire OpenAPI 3.0 JSON for a project. Your agent gets the complete map of 42 endpoints and 18 schemas in one go, eliminating manual documentation hunts. - Write client code faster: Ask the AI to inspect an endpoint schema using
get_endpoint. It returns the exact data structure, so you can generate TypeScript interfaces or service layers immediately. - Structure your testing: Use
list_schemasto get a list of reusable data models (DTOs, entities). This lets your agent validate payloads against the known, defined data structure. - See your API scope: Use
list_projectsto browse every API project in your organization. This is the first step before your agent can even look at endpoints or schemas. - Map your routes: Use
list_endpointsto get a complete list of HTTP routes for a project. This lets your agent confirm if the/usersendpoint exists before attempting to query its schema. - Generate complex specs: Combine
list_endpointsandget_endpointto let the agent check every route in a project. This ensures no API path is missed when scaffolding out a full client library.
Real-World Use Cases
Generating Unit Tests for a New Feature
A QA engineer needs to build tests for a new /cart endpoint. Instead of opening Apidog, they ask their agent to run list_endpoints to confirm the path, then get_endpoint to get the expected response schema. The agent uses that schema to write the test payload, solving the problem in the chat window.
Onboarding to a Large Monorepo API
A new backend developer joins and needs to know the API surface. They ask their agent to run list_projects first, then select the service. The agent runs export_openapi to dump the entire OpenAPI spec, giving the developer full context for scaffolding controllers.
Creating Client-Side Data Types
A frontend developer needs the TypeScript interfaces for the user profile service. They ask the agent to get_endpoint for /users. The agent analyzes the response schema and spits out the precise, type-safe TypeScript code snippet, eliminating guesswork.
Auditing API Changes Across Services
An architect needs to know if a common data structure (like User or Product) was updated across multiple services. They run list_schemas to aggregate all reusable DTOs and then ask the agent to compare them against the main export_openapi spec.
The Tradeoffs
Reading API docs manually
Opening the Apidog client, navigating through projects, clicking into endpoints, and copying JSON snippets into a document. This takes 15 minutes and is error-prone.
→
Ask your agent to run list_projects to find the right service, then export_openapi to get the full spec. This delivers all the context you need in seconds.
Guessing the required schema
Writing a request body for a new endpoint and hoping the field names match the backend contract. This causes runtime errors that take hours to debug.
→
Use get_endpoint to inspect the schema. The agent provides the exact request body requirements, ensuring your code matches the API contract every time.
Missing the full picture
Only running list_endpoints and assuming that gives you enough context to start coding. You't know the data types or full payloads.
→
First, run list_endpoints to map the paths, then run export_openapi to pull the complete specification. This gives you the full picture for scaffolding.
When It Fits, When It Doesn't
Use this server if your goal is to read, validate, or generate code based on existing, defined API contracts. You need a single source of truth for your API surface. Use export_openapi when you need the entire project specification. Use get_endpoint when you only care about one specific route's data contract. Don't use it if you're designing a brand new API from scratch; you'll need a different tool for that. If you only need a simple list of names, list_endpoints is enough. But if you need the full data structure, you must use get_endpoint or export_openapi.
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Apidog. 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
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 server provides 5 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Available Capabilities
API documentation shouldn't be a scavenger hunt.
Today, finding API details means opening Apidog, clicking into a project, selecting an endpoint, and scrolling through nested JSON models. You're constantly copy-pasting paths and schemas, and the chance of missing a required header or data type is high.
With the Apidog MCP Server, you just tell your agent what you need—like 'Give me the schema for the user profile endpoint.' The agent runs `get_endpoint` and returns the complete, structured contract directly in your chat. It’s instant, and it’s accurate.
Apidog MCP Server: Export Full OpenAPI Specs
You manually have to generate OpenAPI specs, or rely on outdated documentation, which means your code and your docs are out of sync. This forces teams to waste time reconciling the two.
The Apidog MCP Server lets your agent run `export_openapi` and import the definitive OpenAPI 3.0 JSON. You get the single source of truth, ready for immediate use in testing or code generation.
Common Questions About Apidog MCP
How do I use the `get_endpoint` tool with Apidog MCP Server? +
You ask your agent to fetch the schema for a specific endpoint. You provide the endpoint path and method (e.g., GET /users). The agent uses get_endpoint to return the full request and response body schemas.
Does `export_openapi` give me the whole API specification? +
Yes, export_openapi provides the complete OpenAPI 3.0 JSON for the entire project. This is much better than trying to piece together specs from multiple endpoints.
Can I list all projects using the `list_projects` tool? +
Yes, the list_projects tool retrieves all API projects in your connected Apidog organization. This is the best starting point for understanding your workspace scope.
What's the difference between `list_endpoints` and `list_schemas`? +
list_endpoints lists the available API paths (like /users). list_schemas lists the reusable data types (like User or Product) that those paths use.
How do I use the `list_schemas` tool to check available data models? +
The list_schemas tool retrieves all reusable data models defined in your project. It shows the names and basic descriptions of DTOs or entities, letting you see what data structures your API uses across different endpoints.
What happens if I use `get_endpoint` for a non-existent API route? +
The tool handles missing routes gracefully. It returns a specific error message detailing that the endpoint was not found, allowing your AI client to correctly handle the failure or suggest a fix.
Is the `export_openapi` output usable for code generation? +
Yes, the JSON output from export_openapi is the full OpenAPI 3.0 spec. You can feed this structured data directly to your AI client to scaffold controllers, build unit tests, or generate client code.
Can I combine `list_projects` and `list_endpoints` to narrow down my scope? +
Absolutely. First, use list_projects to get the relevant Project ID. Then, pass that ID to list_endpoints to filter the list down to just the endpoints you need to work on.
Can I import a complete OpenAPI spec into an AI chat session? +
Yes. Instruct the agent to run the export_openapi tool. It downloads the JSON metadata and safely passes it into your context. Given its size, the agent can use this massive reference guide to rapidly write tests, endpoints, or data models perfectly mimicking your production systems.
How can I check the payload requirements for a single specific route? +
If you know the general area of the project, use list_endpoints to verify the ID. Then query get_endpoint. It brings back the specific HTTP verbs, query arguments, path definitions, and expected JSON body — letting your agent craft exact functional requests to external systems.
Will my Apidog tokens expire? +
When generating your Personal Access Token in Apidog, you dictate the validity duration (e.g. 30 days, 1 year or never expire). If you choose a finite span, you will need to come back, generate a new token and insert it once more to reconnect the MCP server successfully.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
Trakt
Track TV shows and movies — search titles, get ratings, discover trending content and manage your watchlist.
Scribe
Create step-by-step guides and SOPs automatically by recording your workflow and generating visual documentation instantly.
PracticePanther
Manage law practice via PracticePanther — matters, contacts, time tracking, bills, payments, tasks, and calendar.
You might also like
Birdeye
Grow your local business reputation with review management, customer surveys, and listings that drive more foot traffic.
Dotdigital
Equip your AI agent to manage email campaigns, track contacts, and monitor marketing automation via the Dotdigital API.
Fastly
Manage edge computing and CDN via Fastly — monitor and activate service versions, manage domains and backends, and purge cache directly from any AI agent.