PluginBench
MCP Server

Splitifi Intelligence MCP MCP Server

io.github.mysplitifi/splitifi-mcp

RepositoryRegistry
How to choose

What this kind of tool is for

  • Hand your agent a structured way to call a model or an inference API.
  • Compare outputs from two different providers on the same prompt.
  • Wire retrieval, embeddings, or generation into an existing agent workflow.

How to compare servers like this

Provider coverage:
Match the tool's supported providers and models to the ones your project uses.
Cost exposure:
Model-backed tools spend real API budget; check how usage and limits are configured.
Maintenance signal:
The provider landscape shifts weekly; prefer tools updated within the last few months.
Config surface:
Prefer tools whose environment-variable or config keys are documented plainly.

This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.

What is the Splitifi Intelligence MCP MCP server?

Outcome predictions and judge profiles from 2,741 ML models trained on 30.3M court records.

How to install Splitifi Intelligence MCP

Copy-paste configuration for popular MCP clients.

transport: stdio
Config generated by PluginBench — verify against the source before use.
Environment / auth
  • SPLITIFI_API_KEY
    required
    secret

    Your Splitifi API key. Get one at mysplitifi.com/developers. Keys start with sk_live_ (production) or sk_test_ (sandbox — all tools unlocked, synthetic responses).

  • SPLITIFI_API_URL

    Override the backend URL. Defaults to https://backend.mysplitifi.com/api/v1/intelligence. Set to http://localhost:8080/api/v1/intelligence for local development.

~/Library/Application Support/Claude/claude_desktop_config.json
JSON config
{
  "mcpServers": {
    "splitifi-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "splitifi-mcp"
      ],
      "env": {
        "SPLITIFI_API_KEY": "<YOUR_SPLITIFI_API_KEY>",
        "SPLITIFI_API_URL": "<YOUR_SPLITIFI_API_URL>"
      }
    }
  }
}

Related MCP servers

AI code-review assistant that hunts security issues via hypothesis-driven scanning, variant analysis, and multi-stage verification.

41
TypeScript
MIT
View repository →

MCP server for image/video understanding & generation (Gemini/OpenAI/Grok)

4
Python
Apache-2.0
View repository →

Persistent AI memory with hybrid search, knowledge graphs, and encrypted sync—open, free, unlimited.

10
Python
Apache-2.0
View repository →

Real astrology for AI agents: cosmic weather, synastry, timing, astrocartography, and divination.

Mzizi design system MCP: components, tokens, skills and docs. Free; sign-in only for Fundi.

View repository →

政府統計 (e-Stat) の API を通じて、統計データやメタ情報を取得するためのサービスです。