Labsco — the lab for AI agents, MCP servers & skills

MCP

Connect your AI agent to Cala's MCP

https://api.cala.ai/mcp/

For more information about MCP and how it works, you can read more about it here.

Pair with the agent skill. The MCP server gives your agent access to Cala's tools. The agent skill gives it the knowledge to use them well. Install both for the full experience.

Connect your agent to Cala's MCP

You can use Cala via our MCP. To get started, you need to get an API key to authenticate your MCP client. Go to our Console and create a new API key.

Create a free Cala account and get your API key.

With your API key in hand, you can connect your AI agent such as Cursor, Claude Code and others to our MCP server. Cala MCP gives AI agents access to verified, structured and typed knowledge — both as natural-language answers and structured data — as well as entity information.

Add to ~/.cursor/mcp.json:

```json theme={null}
{
 "mcpServers": {
 "Cala": {
 "url": "https://api.cala.ai/mcp/",
 "headers": {
 "X-API-KEY": "YOUR_CALA_API_KEY"
 }
 }
 }
}

For more information, follow their documentation here.


 
 
 Add to `.vscode/mcp.json`:

{
 "servers": {
 "Cala": {
 "type": "http",
 "url": "https://api.cala.ai/mcp/",
 "headers": {
 "X-API-KEY": "YOUR_CALA_API_KEY"
 }
 }
 }
}

For more information, follow their documentation here


 
 
 For Claude Desktop you don't need to have an API key as authentication is done via OAuth.

You can configure Cala MCP in Claude Desktop from the Connectors UI.

Individual account

Go to Customize → Connectors, click +, and select Add custom connector.

Enter the following information:

Name: Cala
URL: https://api.cala.ai/mcp/

And in Advanced settings:

Client ID: sZasi0PYnHtNtiPBSFBAro5XYzZrVl8Q
Client Secret: leave empty

A sign-in pop-up will appear — log in with your Cala credentials to authenticate. Once connected, toggle on the tools you want to make available to Claude.

Organization account (Team or Enterprise)

An Owner or Primary Owner can go to Organization settings → Connectors, click Add.

Enter the following information:

Name: Cala
URL: https://api.cala.ai/mcp/

And in Advanced settings:

Client ID: sZasi0PYnHtNtiPBSFBAro5XYzZrVl8Q
Client Secret: leave empty

If you are not an admin, ask your administrator to complete this step.

Go to Customize → Connectors, find Cala (labeled Custom), and click Connect.

A sign-in pop-up will appear — log in with your Cala credentials to authenticate. Once connected, toggle on the tools you want to make available to Claude.


 
 
 Run the following command in your terminal adding your API key:

claude mcp add --transport http cala https://api.cala.ai/mcp/ --header "X-API-KEY: YOUR_CALA_API_KEY"


 
 
 Add to `~/.vibe/config.json`:

{
 "mcpServers": {
 "Cala": {
 "url": "https://api.cala.ai/mcp",
 "headers": {
 "X-API-KEY": "YOUR_CALA_API_KEY"
 }
 }
 }
}


 
 
 Add to `~/.codex/config.toml`:

[mcp_servers.cala]
enabled = true
command = "npx"
args = [
 "-y",
 "mcp-remote",
 "https://api.cala.ai/mcp",
 "--header",
 "X-API-Key:${CALA_API_KEY}"
]

[mcp_servers.cala.env]
CALA_API_KEY = "YOUR_CALA_API_KEY"


 
 
 
 To support the full power of our graph's flexible schema, this MCP server utilizes dynamic JSON objects. This provides a "schema-less" experience for the LLM. Because of this, it is incompatible with OpenAI's "strict mode" so please ensure `strict: false` is set in your OpenAI specification.

For more information, follow their documentation here


 
 
 For clients with built-in remote MCP support:

{
 "mcpServers": {
 "Cala": {
 "url": "https://api.cala.ai/mcp/",
 "headers": {
 "X-API-KEY": "YOUR_CALA_API_KEY"
 }
 }
 }
}

For clients without built-in remote MCP support:

{
 "mcpServers": {
 "Cala": {
 "command": "npx",
 "args": [
 "mcp-remote",
 "https://api.cala.ai/mcp/",
 "--header",
 "X-API-KEY: YOUR_CALA_API_KEY"
 ]
 }
 },
}


## Available Tools

Here are the tools available to the Cala MCP:

 
 Get a succinct, token-optimized answer in natural-language markdown, with sources, explainability, and matching entities. Accepts either a natural-language question or a Cala QL expression as input.
 
 
 Get verified knowledge as structured, typed JSON rows plus matching entities. Accepts either a Cala QL expression or a natural-language question as input.
 
 
 Search entities by name with fuzzy matching.
 
 
 Get the field schema for an entity by its UUID. Returns the available properties, relationships, and numerical observations you can use when querying an entity.
 
 
 Retrieve information about an entity by its UUID.

## Hubs & Marketplaces

You can also find Cala's MCP server listed on the following hubs and marketplaces:

 
 Browse Cala's MCP server listing on mcpservers.org.
 
 
 Browse Cala's MCP server listing on mcp.so.