mcpField
A
Aito

Aito

Local
aito.aiDatabases5Updated 4d ago
RepositoryVisit website

About Aito

Aito is an MCP server for AI assistants and coding agents that need predictions and related operations over their own data. It exposes Aito v2 tools whose results include probabilities and evidence, and describes when Aito or another approach is appropriate.

Key features

  1. 01Predict, recommend, relate, and match
  2. 02Search, query, and evaluate data
  3. 03Read and update schema
  4. 04Upload rows to Aito
  5. 05Results include probability and evidence
  6. 06Writes disabled by default

Use cases

  1. 01Predict outcomes from Aito data
  2. 02Recommend or match records
  3. 03Inspect evidence and probability thresholds
  4. 04Evaluate whether Aito fits a task

MCP support

The server exposes Aito v2 API operations as MCP tools, including prediction, search, query, schema, and row-upload tools. It is read-only unless `AITO_MCP_ALLOW_WRITES=1` is set.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "aitodotai-aito": {
      "command": "uvx",
      "args": [
        "aito-mcp"
      ],
      "env": {
        "AITO_URL": "<AITO_URL>",
        "AITO_API_KEY": "<AITO_API_KEY>",
        "AITO_MCP_ALLOW_WRITES": "<AITO_MCP_ALLOW_WRITES>"
      }
    }
  }
}
Run commanduvx aito-mcp
Environment variables to set
AITO_URLThe Aito instance URL. Optional: without it the server uses the `aito start` profile.
AITO_API_KEYSecretThe instance's API key (a read-only key is enough unless writes are enabled).
AITO_MCP_ALLOW_WRITESSet to 1 to enable put_schema and upload_rows. Off by default.

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypiaito-mcp1.2.1

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

aito-mcp

An MCP server for Aito, the predictive database, for AI assistants and coding agents: uvx aito-mcp.

Its tools are predict, recommend, relate, match, search, query, evaluate, get_schema, put_schema and upload_rows over the Aito v2 API. Each tool's description says when Aito fits and when another tool (a language model, a trained model, a search engine) is the better choice. Results carry $p (a probability you can set a threshold on) and $why (the evidence). It is read-only unless started with AITO_MCP_ALLOW_WRITES=1.

The server finds the instance like the Aito Python SDK: AITO_URL and AITO_API_KEY, or the profile aito start writes for a local Aito (pip install aitoai, then aito start).

claude mcp add aito -- uvx aito-mcp

Setup for Claude Code and other assistants: https://aito.ai/docs/articles/use-aito-from-claude-code-and-other-ai-assistants/

When Aito fits, and when another tool is the better choice: https://aito.ai/docs/articles/when-to-use-aito-and-when-not/

The code lives in aitoai (aito.mcp); this package only installs it with the mcp extra. Source: https://github.com/AitoDotAI/aito-python-tools

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.