The Dock AI MCP server enables AI agents to discover and connect to MCP endpoints for real-world businesses by querying a registry that maps business domains to available connectors.
Core capabilities:
Resolve business domains - Use the resolve_domain tool to find MCP connectors for specific business domains (e.g., restaurants, hotels, salons)
Discover MCP endpoints - Get detailed information about available MCP servers including provider names, endpoint URLs, entity IDs, and supported capabilities (e.g., reservations, availability)
Access entity information - Retrieve structured data about businesses including name, location (city, country), category, and verification status
Generate Claude Desktop configuration - Automatically create configuration snippets for connecting to discovered MCP servers
Check provider availability - Identify businesses with existing MCP connectors or those using providers where connectors are pending implementation
Primary use case: Enables AI agents to dynamically discover and connect to the right MCP servers for making reservations, checking availability, or performing other business interactions without needing pre-configured endpoints.
Deployment options: Use the hosted version at https://connect.dockai.co/mcp or self-host via Vercel deployment or local installation.
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., "@Dock AI MCP find MCP servers for olivegarden.com"
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.
MCP server for Dock AI - discover MCP endpoints for real-world entities.
Dock AI is a registry that maps businesses to their MCP connectors. This MCP server allows AI agents to discover which MCP servers can interact with a given entity (restaurant, hotel, salon, etc.) by querying the Dock AI registry.
Related MCP server: domainintel-mcp
Use the hosted version at https://connect.dockai.co/mcp - no installation required.
{
"mcpServers": {
"dock-ai": {
"url": "https://connect.dockai.co/mcp"
}
}
}# Using uvx
uvx dock-ai-mcp
# Or install and run
pip install dock-ai-mcp
dock-ai-mcpThe server starts on http://0.0.0.0:8080/mcp.
resolve_domainCheck if an MCP connector exists for a business domain.
Input:
domain (string): The business domain to resolve (e.g., "example-restaurant.com")
Output:
{
"domain": "example-restaurant.com",
"entities": [
{
"name": "Example Restaurant",
"path": null,
"location": { "city": "Paris", "country": "FR" },
"mcps": [
{
"provider": "booking-provider",
"endpoint": "https://mcp.booking-provider.com",
"entity_id": "entity-123",
"capabilities": ["reservations", "availability"],
"verification": { "level": 2, "method": "dual_attestation" }
}
]
}
],
"claude_desktop_config": {
"mcpServers": {
"booking-provider": { "url": "https://mcp.booking-provider.com/mcp" }
}
}
}User: "Book a table at Gloria Osteria Paris"
Agent: [searches web for "Gloria Osteria Paris official website"]
-> Finds domain: gloria-osteria.com
[calls resolve_domain("gloria-osteria.com")]
-> Gets MCP endpoint for SevenRooms
-> Connects to the MCP server
-> Books the tableUser: "I need a room at The Hoxton in London"
Agent: [searches web for "The Hoxton London website"]
-> Finds domain: thehoxton.com
[calls resolve_domain("thehoxton.com")]
-> Gets MCP endpoints for available booking providers
-> Uses the MCP to check availability and bookUser: "Book at Le Paris Paris restaurant"
Agent: [calls resolve_domain("leparisparis.fr")]
-> Response shows pending_providers: [{ "provider": "thefork", ... }]
-> Informs user: "This restaurant uses TheFork for reservations,
but TheFork hasn't published an MCP connector yet.
You can book directly on TheFork's website."Documentation: dockai.co/docs
Issues: GitHub Issues
Email: support@dockai.co
This MCP server queries the Dock AI registry API to resolve domains. No user data is collected or stored. See our Privacy Policy.
MIT
Resolve a domain to its MCP endpoints.
Given a domain, returns the entity information and available MCP endpoints that can interact with this entity.
Args: domain: The domain to resolve (e.g., "example-restaurant.com")
Returns: Entity information including name, category, verification level, and list of MCP endpoints with their capabilities.
| Name | Required | Description | Default |
|---|---|---|---|
| domain | Yes |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses the tool's behavior by describing what it returns (entity info and endpoints), but lacks details on error handling, rate limits, authentication needs, or performance characteristics. It adequately covers the core operation but misses deeper 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 well-structured and front-loaded, starting with the core purpose, followed by args and returns sections. Every sentence adds value: the first states the action, the second elaborates, and the bullet points clarify inputs and outputs without redundancy. It's efficient and easy 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?
Given the tool's moderate complexity (1 parameter, no annotations, but with an output schema), the description is fairly complete. It explains the purpose, parameter, and return values. The output schema exists, so it needn't detail return structure, but it could benefit from more behavioral context like error cases or usage examples.
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 0%, so the description must compensate. It adds meaningful semantics by explaining the 'domain' parameter with an example ('e.g., "example-restaurant.com"'), clarifying it's the domain to resolve. This goes beyond the bare schema, though it doesn't detail format constraints or edge cases.
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 ('resolve a domain') and resource ('MCP endpoints'), explaining it returns entity information and available endpoints. It distinguishes the tool's function with precise terminology like 'entity information' and 'capabilities', making its purpose unambiguous even without sibling tools for comparison.
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 by stating 'Given a domain, returns...', suggesting it's for resolving domains to endpoints. However, it lacks explicit guidance on when to use this tool versus alternatives, prerequisites, or exclusions. With no sibling tools, this is less critical, but the guidance remains implicit rather than explicit.
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.
v1.0.0resolve_domainScored across 1 tool
With only one tool, there is no possibility of ambiguity or overlap between tools. The tool 'resolve_domain' has a single, clear purpose, so an agent cannot misselect between multiple options.
The tool name 'resolve_domain' follows a consistent verb_noun pattern, and since there is only one tool, there is no inconsistency to evaluate. The naming is clear and predictable.
A single tool is too few for a server named 'Dock AI MCP,' which suggests a broader purpose like domain resolution or MCP endpoint management. One tool feels thin and limits functionality, indicating a significant mismatch in scope.
The tool set is severely incomplete for the inferred domain of MCP endpoint resolution. It only resolves domains without supporting operations like listing, updating, or managing endpoints, leaving obvious gaps that will hinder agent workflows.
Capability registry for the agentic economy. Semantic search over verified MCP server listings.
Search and discover 25,000+ MCP servers across all major registries. Connect and pay autonomously.
Search, vet & assemble MCP servers from your agent: verified tools, risk labels, and trust scores.
Custom domains for SaaS and AI agents: search, register, connect DNS, and issue HTTPS over MCP.
