Sparkient MCP Server

by sparkient

Not rated
GitHub

About

Sub-100ms Decision Intelligence API. Instant structured decisions for content moderation, fraud detection, ticket triage, and approval workflows.

Details

Author
sparkient
Categories
Cloud Service, API, Automation

Setup

Install Sparkient MCP Server in your MCP client (Claude Desktop, Cursor, Windsurf, and others).

Repository: https://github.com/sparkient/sparkient-mcp-server

Follow the installation instructions in the repository README, then restart your MCP client.

Sub-100ms Decision Intelligence API. Instant structured decisions for content moderation, fraud detection, ticket triage, and approval workflows.

MCP (Model Context Protocol) server for theSparkientDecision Intelligence API. Connect your AI agents directly to Sparkient for sub-100ms structured decisions — no REST client code needed.

The cloud MCP server atmcp.sparkient.aiwraps the Sparkient REST API as MCP tools. You need aSparkient API keyto connect.

Add to yourclaude_desktop_config.json:

{ "mcpServers": { "sparkient": { "url": "https://mcp.sparkient.ai/mcp", "headers": { "Authorization": "Bearer sk-YOUR_API_KEY" } } } }
{ "mcpServers": { "sparkient": { "url": "https://mcp.sparkient.ai/mcp", "headers": { "Authorization": "Bearer sk-YOUR_API_KEY" } } } }

Create.vscode/mcp.jsonin your project:

{ "servers": { "sparkient": { "type": "http", "url": "https://mcp.sparkient.ai/mcp", "headers": { "Authorization": "Bearer sk-YOUR_API_KEY" } } } }
npx -y @smithery/cli install sparkient --client claude
git clone https://github.com/sparkient/sparkient-mcp-server.git cd sparkient-mcp-server pip install -e ".[dev]" # Set your API key and start export SPARKIENT_API_URL=https://api.sparkient.ai python -m sparkient_mcp

The Sparkient MCP server is listed on the following directories so agents and developers can discover it:

Smithery discovers tools by scanning the live server. The MCP server includes middleware that serves tool metadata to directory scanners that don't follow the full MCP handshake (sendingtools/listwithoutinitialize).

- Stateless HTTP mode(stateless_http=True): Required for Cloud Run where requests route to different instances.
- Scanner middleware(UnknownMethodGuard): Intercepts discovery requests without a session and serves tool metadata directly from the FastMCP instance. Also returns-32601for non-standard methods likeai.smithery/events/list.
- Auth: Smithery's gateway passes the user's API key via theAuthorizationheader.

Most MCP directories discover capabilities by connecting to the server and callingtools/list. The server is designed to respond correctly to both:
- Standard MCP clientsinitializenotifications/initializedtools/list(returns via SSE)
- Directory scannerstools/listdirectly withoutinitialize(returns via JSON)

For sub-10ms decisions with zero network dependency, use the edge MCP server:

{ "mcpServers": { "sparkient-edge": { "command": "python", "args": ["-m", "edge"] } } }

The edge server uses downloaded edge bundles (CEL rules + ONNX models) for local inference. Export a bundle from the Sparkient dashboard or via theexport_edge_bundleMCP tool.

AI Agent (Claude/Cursor/VS Code/LangChain) ↓ Streamable HTTP + API Key Sparkient MCP Server (this package) ↓ httpx (async HTTP) Sparkient REST API (api.sparkient.ai) ↓ Decision Pipeline: CEL Rules → ONNX Classifier → Gemini Escalation

The MCP server is a stateless thin wrapper. Each request is handled independently — no session tracking. Multiple Cloud Run instances serve concurrent requests behind a single URL.

Zero-setup MCP gateway securely connecting AI to your tools with authentication and workflows

Interact with Arcanna's AI use cases through the Model Context Protocol (MCP).

MCP server for electronic consignment notes (eCMR). Create, sign, manage, and track electronic transport documents with QR codes, PDF generation, and digital signatures through the Cargoffer ECMR API. Designed for AI agents like Claude Desktop, Cursor, and Cline

Integrate Hygraph directly into MCP-compatible tools like Claude and Cursor, executing content operations via natural language

Invoke task chains on the iFlytek SparkAgent Platform.

MCP server for the Dropbox Sign API supporting signature requests, templates, teams, accounts, events, documents, signers, reports, bulk operations, and workflows.

A ModelContextProtocol (MCP) server for interacting with the SAP Integration Suite.

A curated collection of 11 MCP servers for popular SaaS APIs — Stripe, Sentry, Notion, Linear, Datadog, Vercel, PagerDuty, HubSpot, Intercom, Shopify, and Google Workspace.

The Most Comprehensive ServiceNow AI Toolkit — 400+ MCP tools, 26 AI capabilities, SDK mode, Direct API mode. Covers ITSM, ITOM, CMDB, HRSD, CSM, SecOps, GRC and 35+ modules.

Integrates with the WeChat cloud development reservation system API.

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.