Apiary MCP. Manage API specs, documentation, and tests from chat.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
Apiary. Connect your API design process directly to your AI agent. Read raw API blueprints, publish documentation updates, and run Dredd validation tests using natural conversation.
It gives you full control over your API specifications, without leaving your chat window.
What your AI agents can do
Get api
Gets the full API Blueprint source code for a specific Apiary API project.
Get doc url
Retrieves the documentation and mock server URLs for a given Apiary API project.
Get me
Pulls the authenticated user's profile details from Apiary.
Retrieves the full, raw API Blueprint source code for any specified project.
Gets the live URLs for both the documentation and the mock server for an API project.
Pulls and displays the authenticated user's profile information from Apiary.
Fetches specific details about a named Apiary team.
Shows a comprehensive list of all API projects visible within the Apiary platform.
Retrieves all API projects that belong specifically to a given team.
Lists every user member belonging to a specific Apiary team.
Retrieves a list of all teams the connected user belongs to.
Publishes and updates the core API Blueprint of a project using provided Markdown or Swagger code.
Executes Dredd-style API validation tests against a specified API project.
Ask AI about this MCP
Supported MCP Clients
Gemini Waiting for input…
Apiary MCP Server: 10 Tools for API Management
Manage API blueprints, retrieve documentation, and execute validation tests across your entire API ecosystem using your AI agent.
019d754fget api
Gets the full API Blueprint source code for a specific Apiary API project.
019d754fget doc url
Retrieves the documentation and mock server URLs for a given Apiary API project.
019d754fget me
Pulls the authenticated user's profile details from Apiary.
019d754fget team
Fetches specific details about a named Apiary team.
019d754flist apis
Lists every API project available on the Apiary platform.
019d754flist team apis
Lists all API projects that belong to a designated Apiary team.
019d754flist team members
Lists all user accounts belonging to a specific Apiary team.
019d754flist teams
Lists all teams the connected user is a member of.
019d754fpublish blueprint
Updates an API project's core Blueprint using provided Markdown or Swagger code.
019d754frun tests
Runs Dredd-style API validation tests against a specified Apiary 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 Apiary, 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
Yo, you can manage your whole API lifecycle right from your chat window. This server lets your AI agent talk directly to your Apiary workspace, so you don't gotta leave your conversation. You'll read raw API blueprints, publish documentation updates, and run Dredd validation tests—all using just natural talk. It gives you full control over your API specs, period.
Fetch API Specifications: You can get the full, raw API Blueprint source code for any specific Apiary API project using get_api. Generate Documentation Links: It pulls the live URLs for both the documentation and the mock server for an API project with get_doc_url. Retrieve User Info: Your AI client can pull and display your personal profile details from Apiary with get_me. Query Team Details: You can grab specific details about a named Apiary team using get_team. List API Projects: Need to know what's around? You can see a comprehensive list of all API projects available on the Apiary platform with list_apis. List Team APIs: To see what belongs to a specific group, you can list all API projects that belong to a designated team using list_team_apis. List Team Members: You can list every user member belonging to a specific Apiary team with list_team_members. List Teams: You'll also be able to get a list of all teams the connected user belongs to using list_teams. Update API Blueprints: You can publish and update an API project's core Blueprint by providing Markdown or Swagger code with publish_blueprint. Run API Tests: Finally, you can run Dredd-style API validation tests against a specific Apiary project using run_tests.
How Apiary MCP Works
- 1 Subscribe to the Apiary server and input your Personal Apiary Token.
- 2 Direct your AI client to perform an action (e.g., 'List all APIs for the finance team').
- 3 The server executes the necessary tool call and returns the resulting data, which your AI agent formats and presents to you.
The bottom line is, you manage your entire API life cycle—from spec writing to testing—without leaving your chat window.
Who Is Apiary MCP For?
This is for backend engineers, technical writers, and engineering managers who get frustrated switching between documentation portals, Git, and chat tools. If your job involves keeping APIs documented and tested, this cuts out the manual friction.
Asks the agent to fetch the current API blueprint, writes new endpoint specs, and publishes them back to the remote server.
Uses the server to review and fix API documentation formatting, submitting changes directly to the official API source.
Checks the testing status across all team APIs, lists active projects, and oversees member permissions without logging into the main dashboard.
What Changes When You Connect
- Publish updates instantly. Write new markdown code and use
publish_blueprintto update the API specs, which automatically refreshes the mock server and public documentation URL (get_doc_url). - Validate endpoints right away. Run Dredd tests via
run_teststo check your backend implementation against the blueprint without leaving your chat client. - See your team structure. Use
list_teamsandlist_team_membersto get an overview of who's on the team and what APIs they manage. - Get the source code fast.
get_apifetches the raw Markdown blueprint, letting you review the full specification without having to click through the web UI. - Scope your search. Use
list_team_apisto narrow down the massive list of all projects (list_apis) to just those owned by a specific team. - Quick user context.
get_meprovides your current Apiary profile, letting your agent confirm your permissions before making changes.
Real-World Use Cases
Updating a Deprecated API Endpoint
A backend engineer needs to update the payments-gateway blueprint. Instead of logging into Apiary, they tell their agent to fetch the current spec using get_api. They make the necessary Markdown changes in the chat, then instruct the agent to publish_blueprint with the revised code. The agent confirms the update and that the documentation is live.
Auditing Team Ownership
An engineering manager needs to check who owns the API for the 'user-profiles' service. They ask the agent to list_teams to find the relevant team, then use list_team_members to see who is on it, and finally list_team_apis to confirm the exact project owner.
Validating a New Feature Release
A developer completes a new feature. Before merging, they ask the agent to run_tests against the feature's API project. The agent executes the validation and reports back the test results, showing exactly which endpoints failed validation.
Checking Team Documentation Status
A technical writer needs to confirm that the documentation for the 'billing' team is up to date. They ask the agent to list_team_apis and then use get_doc_url on the target API to get the live link, verifying the documentation is published.
The Tradeoffs
Manual Copy/Paste
The developer manually copies the blueprint from the Apiary website into a local file, makes changes, and then pastes it back into the web editor, risking formatting errors or missing sync steps.
→
Just tell your agent to fetch the raw blueprint using get_api. Modify the code in the chat, and then use publish_blueprint to push the changes directly to the remote server. No copy/paste required.
Missing Context
The developer tries to list all APIs but doesn't know which team they belong to, so they manually check multiple dashboards, wasting time.
→
First, ask the agent to use list_teams to see all your team affiliations. Then, use list_team_apis to scope the list to a specific team's projects, saving you clicks.
Testing Blindly
A developer assumes the API works because the code compiles, but fails because a field type changed. They don't run full validation.
→
Always run run_tests immediately after making changes. This executes Dredd-style validation and confirms the live API implementation matches the written blueprint.
When It Fits, When It Doesn't
Use this server if your workflow involves reading, updating, or validating API specifications (blueprints, documentation, tests). It's perfect for any developer who lives in the chat interface and hates context switching. Don't use it if your only need is to view a single, static resource, or if you need a tool that manages non-API data (like simple user data not tied to a team structure). For pure documentation viewing, you still need the Apiary UI, but for managing the documentation, this is the one.
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Apiary. 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 10 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Available Capabilities
Managing APIs used to mean jumping between five different tabs.
Today, if you need to see an API blueprint, you open the Apiary portal. If you need to run tests, you switch to the test runner. If you need to check team membership, you open the team management tab. You copy the spec, you paste it into a local file, you switch to your editor, and you keep checking documentation sync status. It's a whole routine just to make one change.
With this MCP server, you just talk to your agent. Tell it, 'Fetch the blueprint for payments-gateway.' The raw spec appears in the chat. You edit it. You tell it to `publish_blueprint`. The agent handles the rest. You stay in one place.
Apiary MCP Server: Run tests and update specs from chat
You no longer have to manually navigate to the testing dashboard and input the project name. You simply ask your agent to `run_tests` and get the pass/fail results right here. Likewise, instead of manually updating the documentation through the web interface, you give the agent the markdown and it handles the entire remote publishing process.
This isn't just reading data; it's controlling the full deployment lifecycle. Your agent treats the API specification like a live service, giving you immediate, actionable feedback.
Common Questions About Apiary MCP
How do I use the `publish_blueprint` tool with Apiary MCP Server? +
You provide the raw API Blueprint code (Markdown/Swagger) and tell your agent to publish it. The agent ensures the syntax is valid and updates the live project, automatically refreshing the mock server and documentation.
What is the difference between `list_apis` and `list_team_apis` using Apiary MCP Server? +
list_apis shows every API project on the platform. list_team_apis filters that list, showing only the projects that belong to a specific team you specify.
Can I use `run_tests` before I've published the latest blueprint? +
Yes. run_tests validates the currently implemented API against the blueprint, regardless of when the blueprint was last updated. You must ensure the blueprint is current before testing for accurate results.
What does the `get_doc_url` tool provide? +
It gives you the live URLs for both the API's public documentation and its corresponding mock server, letting you share the working links immediately.
How do I check my user details using the `get_me` tool? +
The get_me tool fetches your authenticated Apiary user profile data. It shows your name, email, and role, confirming your current access level within the platform.
What's the difference between `list_teams` and `list_apis` when managing my accounts? +
list_teams shows every team you belong to on Apiary. list_apis lists all API projects available to your account generally, regardless of which team owns them.
Can I find all the APIs owned by a specific team using `list_team_apis`? +
Yes, list_team_apis retrieves every API project registered under a specific team's namespace. This helps you quickly scope down which services the team manages.
Which tool should I use to start working with a specific API blueprint's code? +
You should use get_api to fetch the raw Markdown blueprint source code for a specific API project. This gives your agent the full definition needed for modification or review.
Can the agent fetch the exact mock server endpoints for one of my APIs? +
Yes. You can use the get_doc_url capability to retrieve both the public facing documentation url and the private mock server endpoint string. Your agent can immediately use this url to simulate requests internally using other modules or tests.
Am I able to update the Blueprint markup completely through the agent? +
Absolutely. Instruct your AI agent to fetch the blueprint with get_api. Once read into context, prompt the agent to make your desired changes (e.g. 'Add a new POST route for user creation'). Then, instruct it to use publish_blueprint to upload the newly revised markdown.
How does the team feature list function mapping work? +
Apiary enables collaboration. Utilizing list_teams, the agent finds the slugs of your organizations. Then, using list_team_apis, it fetches all collaborative APIs available for that precise team. This hierarchy avoids hallucinating random endpoint repositories.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
Applitools
Bring AI-powered visual testing to your AI agent — inspect test batches, review UI diffs, and manage your visual baselines naturally.
Jokes API (API Ninjas)
Access random jokes — audit content and limits via AI.
ScrapingBee
Scrape websites without getting blocked using headless browsers, proxy rotation, and JavaScript rendering handled for you.
You might also like
KlickTipp
Grow your German-speaking audience with tag-based email marketing that segments subscribers by behavior and interest.
Cohere
Access Cohere AI models via API — chat with Command models, generate embeddings, rerank documents and tokenize text from any AI agent.
Pumble
Bring your AI agent into your Pumble workspace — read channel history, post messages, create channels, and manage team communication seamlessly.