AI interface to your Data
CameoDB integrates a fully-compliant Model Context Protocol (MCP) server directly into the core engine. Enable Claude, Cursor, or Windsurf to instantly retrieve and optimize knowledge base and context.
cable Client Configurations
Note: CameoDB defaults to port 9480. The MCP endpoints are nested natively under the /mcp path.
Windsurf
SSE TransportAdd to .windsurf/mcp.json or via Settings → MCP:
{
"mcpServers": {
"cameodb": {
"url": "http://localhost:9480/mcp/sse",
"transport": "sse"
}
}
}
Cursor
SSE TransportAdd to Cursor MCP settings:
{
"mcpServers": {
"cameodb": {
"url": "http://localhost:9480/mcp/sse",
"transport": "sse"
}
}
}
Claude Code
Native SSENative SSE transport via CLI, no bridge needed:
# Add via CLI (project-scoped)
claude mcp add --transport sse cameodb http://localhost:9480/mcp/sse
# Or add as Streamable HTTP
claude mcp add --transport http cameodb http://localhost:9480/mcp
# Verify connection
claude mcp get cameodb
claude mcp list
# Inside Claude Code, type /mcp to check status
Claude Desktop
Native SSEAdd to ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"cameodb": {
"type": "sse",
"url": "http://localhost:9480/mcp/sse"
}
}
}
For auth headers, add "headers" object with Authorization key.
build Available MCP Tools, Prompts & Resources
6 tools, 1 prompt, and 4 resource URIs exposed securely (Read-Only) to the AI agent.
Execute full-text search on a single CameoDB index.
- index (req)
- query (req)
- limit (opt)
- fields (opt array)
"arguments": {
"index": "papers",
"query": "machine learning AND year:[2020 TO 2024]",
"limit": 10,
"fields": ["title", "author"]
}
Execute federated search across multiple CameoDB indexes with per-index field projection.
"arguments": {
"indexes": [
{"index": "papers", "fields": ["title", "author"]},
{"index": "books", "fields": ["title", "isbn"]}
],
"query": "rust programming",
"limit": 20
}
Validates query syntax against the schema. Returns fuzzy "did you mean" suggestions for unknown fields and syntax tips.
Retrieve schema and statistics for a single index.
List all available indexes and their schemas.
Document counts, size, and aggregated cluster metadata.
Universal data retrieval and orchestration skill injected into agent context. Guides the agent through schema discovery, query construction, and result interpretation.
- cameodb://indexes
- cameodb://indexes/{index}
- cameodb://indexes/{index}/schema
- cameodb://indexes/{index}/stats
Every index response includes per-field query hints. Agents go from zero knowledge to well-formed queries in two tool calls (list_indexes to search_index) with no prior configuration.
account_tree Implementation & Transport
-
dnsShared-Port Architecture Runs in the same binary as CameoDB, sharing the same
AppStateand actor system. No sidecars needed. -
ruleStrict Spec Compliance (2024-11-05) Implements proper JSON-RPC 2.0 over SSE. Emits structured
endpointandmessageevents. -
hubMultiple Transport Modes Supports SSE (
GET /mcp/sse), direct HTTP JSON-RPC (POST /mcp), and compatibility endpoint (POST /mcp/sse) for maximum client compatibility. -
boltAsynchronous Processing Client POSTs to
/mcp/messagesare non-blocking. Server immediately returns202 Acceptedand processes via backgroundtokio::spawn. -
hourglass_emptySession Management Automatic session registry with a 5-minute timeout cleanup. Keepalive messages sent every 15 seconds to maintain connection.
Agent Query Syntax
Agents use the validate_query tool to learn this dynamically, but here is the reference.
| Syntax Type | Example Format |
|---|---|
| Basic Search | machine learning |
| Field-Targeted | title:rust |
| Phrase | title:"rust programming" |
| Boolean Operators | (title:rust OR title:go) AND year:[2020 TO 2024] |
| Range / Numeric | price:[10.0 TO *] |
| Date Comparisons | created_at:>2024-01-01 |
| Inline Modifiers | title:rust return title,author limit 5 |