55Trust score 55 of 100, Fair
Drive a running tModLoader (Terraria) instance from an agent: launch, query, screenshot, read state.
Registry
Loading the directory
Loading the directory
Claude Desktop reads mcpServers from claude_desktop_config.json. Restart the app after saving. Claude Desktop can run a local process over stdio or a remote HTTP or SSE endpoint. The config is JSON and the file to edit is claude_desktop_config.json. MCPpedia currently has 42850 published MCP servers have an install config for Claude Desktop. The highest trust scores right now are Repowise at 83, Firecrawl MCP Server at 77, Martin Loop at 77. Open a server and copy the Claude Desktop tab, then fill in secrets yourself. MCPpedia never stores those values.
Claude Desktop reads mcpServers from claude_desktop_config.json. Restart the app after saving.
claude_desktop_config.json at the path for your OS.~/Library/Application Support/Claude/claude_desktop_config.json~/.config/Claude/claude_desktop_config.json%APPDATA%\Claude\claude_desktop_config.jsonEvery server page builds a ready-to-paste JSON config for Claude Desktop.
Published servers with an install config for Claude Desktop.
Drive a running tModLoader (Terraria) instance from an agent: launch, query, screenshot, read state.
Checks what an agent did NOT read. Coverage over a retrieval step or a folder.
MCP server for Banco do Brasil — Pix, Cobrança (boleto), Conta-Corrente, Arrecadação (OAuth2 + mTLS)
Personal AI memory layer on your own computer. Read/write durable memory across MCP clients.
Omitly's local, verifiable PDF redaction for AI agents — your documents never leave your device.
Read-only evidence for the tools agents run: MCP server records, coverage and policy.
Start, prompt and read AI coding agent sessions (Claude Code, Codex, Gemini CLI and more) in Codeman
Local-first LLM deployment planner: GPU/VRAM sizing, cost and latency, with provenance
Unknown author
US Rx prices by pharmacy near you + free discount card; foreign-brand equivalents; 12 languages
Check web pages for responsive design problems and screenshot them on phone, tablet and desktop.
Governed SolarWinds Orion + PRTG + Zabbix ops: SWQL, alert rollup, health, 42 tools.
Discover x402 endpoints and check their trust score before your agent pays them.
Build mind maps, kanban boards and whiteboards in your TabTree account, team spaces included.
Human-in-the-loop approvals and notifications for AI coding agents through a local stdio MCP server.
Local log forensics: compress logs into citable evidence with root-cause confidence tiers.
Read-only OpenIM search for institutional buy-side investment models and architecture.
Graph-powered codebase reasoning, impact analysis, and governance tools over MCP.
Local structured analysis of deployed EVM runtime bytecode
Read-only GitHub repos, issues, PRs and commits, with tool descriptions tuned on a benchmark.
Create PDFs from your CastPDF templates or HTML, issue EU e-invoices, and look up documents.
Project memory across sessions for AI agents. A queryable decision log in the repo.
Reference integrity for AI agents. Scans and verifies links, imports, assets, deps.
Turn an OpenAPI spec into WireMock stubs, contract tests and chaos scenarios, on local LLMs.
Local snapWONDERS MCP: hide, reveal, analyse and convert files on your own machine