ScreenshotOne MCP Server

Created By
screenshotonea year ago
A simple implementation of an MCP server for the ScreenshotOne API
Overview

What is MCP?

MCP is a command-line tool and local user interface designed for discovering, installing, and managing Model Context Protocol (MCP) servers, acting as a broker between different clients and these servers.

How to use MCP?

To use MCP, install the tool and utilize command-line commands like mcp install <client>, mcp registry search <query>, and mcp package install <package[@<version>]> to manage your MCP servers.

Key features of MCP?

  • Discover and install MCP servers from a public registry.
  • Manage OAuth2 credentials for server authentication and authorization.
  • Maintain an audit log of operations with a UI for reviewing.
  • Use Docker to run servers in a secure and isolated way without modifying the host environment.

Use cases of MCP?

  1. Efficiently managing multiple MCP servers for AI clients like Claude and Zed.
  2. Ensuring secure interactions with various servers through OAuth2 management.
  3. Running and uninstalling servers seamlessly through CLI commands.

FAQ from MCP?

  • What does MCP stand for?

MCP stands for Model Context Protocol, which is a framework for server-client interactions in AI environments.

  • Does MCP support all AI clients?

MCP currently supports clients such as Claude and Zed, with plans for broader compatibility in the future.

  • Is MCP a standalone server?

No, MCP acts as a broker and requires the installation of MCP servers that it can manage.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
screenshotone
Star
21
Language
TypeScript
License
MIT license

Recommend Servers

View All
AI Work Market — USDC settlement rails for AI labor on Base Mainnet)
@Dario (DME)

AI Work Market is a USDC escrow protocol on Base Mainnet, designed for autonomous AI agents to find work, post jobs, and settle payments without humans in the loop. This MCP server exposes 10 tools: **Escrow lifecycle** - `create_intent_quote` — get calldata + gas estimate for funding a new escrow intent - `submit_proof_quote` — get calldata for the seller to submit a proof URI - `release_funds_quote` — get calldata for the buyer to release payment (or claim/refund) **x402 single-call binding** - `x402_consume` — replaces the 5-step x402 flow with one HMAC-signed POST that returns a delivery URL **Onboarding & discovery** - `agent_onboard` — generate a signed agent card with marketplace attestation - `agent_search` — tf-idf search over the live agent catalog - `agent_reputation` — server-side reputation from on-chain Released/Refunded/Disputed events **Live state** - `system_status` — live on-chain state (nextIntentId, accumulatedFees, contract balance, owner) - `escrow_rules` — contract semantics, lifecycle, call guides, failure modes - `events_subscribe` — SSE stream of new on-chain intent events All endpoints are serverless (Vercel) and return their schema on GET. No browser, no wallet UI required for an agent to integrate. The protocol takes a 1% commission on every settlement; the rest goes to the seller. The full AgentCard is at `/.well-known/agent-card.json` (A2A-compatible). The OpenAPI 3.0.3 spec is at `/.well-known/openapi.json` with `components.securitySchemes` (none, hmacX402). `robots.txt` allows GPTBot, ClaudeBot, anthropic-ai, PerplexityBot, Google-Extended, Applebot-Extended, CCBot, Amazonbot.

3 hours ago
Gpt Scrambler

2 days ago