MCP Server Documentation

Connect your AI assistants to OrbitalMCP using the Model Context Protocol. Works with Claude, Gemini, Cursor, and any MCP-compatible client.

Quick Start

The easiest way to connect - no local setup required. Just add your API key.

{
  "mcpServers": {
    "orbitalmcp": {
      "url": "https://www.orbitalmcp.com/sse",
      "transport": "sse",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}

Replace YOUR_API_KEY with your OrbitalMCP API key from the dashboard.

Available Tools

search_knowledge_baseRead

Search the knowledge base for relevant information. Returns the most semantically similar documents to your query, ranked by relevance score.

Parameters

Name	Type	Required	Description
`query`	string	Yes	The question or topic to search for
`limit`	number	No	Max results (1-20, default: 5)
`source`	string	No	Filter by source identifier

Example Usage

// In Claude, Gemini, or any MCP client:
"Search my knowledge base for authentication best practices"

// The AI will call:
search_knowledge_base({
  "query": "authentication best practices",
  "limit": 5
})

add_memoryWrite

Add new content to the knowledge base. The content is automatically chunked, embedded, and indexed for retrieval. A project must be selected first (see select_project).

Parameters

Name	Type	Required	Description
`content`	string	Yes	The text content to store
`source`	string	No	Identifier for the content source (e.g., file path, URL)
`metadata`	object	No	Additional metadata (tags, dates, etc.)

Example Usage

// In Claude, Gemini, or any MCP client:
"Add this to my knowledge base: Our API uses JWT tokens
with a 15-minute expiration for access tokens."

// The AI will call:
add_memory({
  "content": "Our API uses JWT tokens with a 15-minute expiration for access tokens.",
  "source": "api-documentation",
  "metadata": { "category": "authentication" }
})

list_projectsRead

List all available projects in your organization. Use this to see which projects exist before adding or searching content.

No parameters required.

create_projectWrite

Create a new project to organize your knowledge base content. Projects help separate different codebases or topics. The new project is automatically selected for the session.

Parameters

Name	Type	Required	Description
`name`	string	Yes	Name for the new project
`description`	string	No	Optional description for the project

select_projectRead

Select a project for the current session. All subsequent add_memory calls will store content in the selected project.

Parameters

Name	Type	Required	Description
`projectId`	string	Yes	The project ID (get IDs from `list_projects`)

Typical Workflow

When your AI connects via MCP, here's the typical flow:

1list_projects — See available projects in your organization
2select_project or create_project — Choose or create a project
3add_memory — Store content in the selected project
4search_knowledge_base — Query your knowledge base anytime

CLI Examples

CClaude CLI - Querying the Knowledge Base

$ claude

You: What do we know about rate limiting in our API?

Claude: I'll search your knowledge base for information about rate limiting.

[Calling tool: search_knowledge_base]
[Arguments: {"query": "rate limiting API", "limit": 5}]

Based on your knowledge base, here's what I found about rate limiting:

1. **Rate Limits by Plan**
   - Starter: 100 requests/minute
   - Pro: 1,000 requests/minute
   - Enterprise: Custom limits

2. **Rate Limit Headers**
   Your API returns these headers:
   - X-RateLimit-Limit: Maximum requests allowed
   - X-RateLimit-Remaining: Requests left in window
   - X-RateLimit-Reset: Unix timestamp when limit resets

3. **Handling 429 Errors**
   When rate limited, implement exponential backoff...

Would you like more details on any of these topics?

GGemini CLI - Adding to Memory

$ gemini

You: I just finished implementing the new webhook system. Add this
documentation to my knowledge base:

Webhook Events:
- user.created: Fired when a new user signs up
- user.updated: Fired when user profile changes
- payment.completed: Fired after successful payment
- subscription.changed: Fired when plan changes

All webhooks include a signature header for verification.
Retry policy: 3 attempts with exponential backoff.

Gemini: I'll store this webhook documentation in your knowledge base.

[Calling tool: add_memory]
[Arguments: {
  "content": "Webhook Events:\n- user.created: Fired when...",
  "source": "webhook-documentation",
  "metadata": {
    "type": "api-reference",
    "category": "webhooks",
    "author": "engineering"
  }
}]

Done! I've added the webhook documentation to your OrbitalMCP knowledge
base. It's now indexed and searchable. The content was split into 2
semantic chunks for optimal retrieval.

Would you like me to also add example payloads for each event type?

Transport Options

SSE (Server-Sent Events)

Recommended for most use cases. Connect directly to our hosted service.

No local setup required
Automatic updates and scaling
Works across firewall/NAT

GET https://www.orbitalmcp.com/sse
POST https://www.orbitalmcp.com/messages

Stdio (Standard I/O)

For self-hosted deployments or air-gapped environments.

Full data sovereignty
Works offline
Custom configurations

npx orbitalmcp

Troubleshooting

Connection refused or timeout

Ensure your API key is valid and has the correct permissions. Check that the Authorization header is properly formatted as 'Bearer YOUR_API_KEY'.

Tools not appearing in my AI client

Restart your MCP client after adding the configuration. Some clients require a full restart to detect new MCP servers.

Search returns no results

Make sure you've ingested content first. Use the add_memory tool or REST API to populate your knowledge base before searching.

Rate limiting errors

The MCP server respects the same rate limits as the REST API. If you're hitting limits, consider upgrading your plan or implementing request batching.