55Trust score 55 of 100, Fair
Author, validate and maintain a CRAYON-C4 architecture model — never write an invalid file.
Registry
Loading the directory
Loading the directory
Workspace file .vscode/mcp.json uses the servers key. User settings can hold the same shape. VS Code can run a local process over stdio or a remote HTTP or SSE endpoint. The config is JSON and the file to edit is mcp.json. MCPpedia currently has 43305 published MCP servers have an install config for VS Code. The highest trust scores right now are Repowise at 83, XERJ at 77, Firecrawl MCP Server at 77. Open a server and copy the VS Code tab, then fill in secrets yourself. MCPpedia never stores those values.
Workspace file .vscode/mcp.json uses the servers key. User settings can hold the same shape.
mcp.json at the path for your OS..vscode/mcp.jsonEvery server page builds a ready-to-paste JSON config for VS Code.
Published servers with an install config for VS Code.
Author, validate and maintain a CRAYON-C4 architecture model — never write an invalid file.
Read videos like images: index once locally, query the text layer, fetch frames on demand.
Manage your rented Macs at Halfpenny Mac: list, check online, credentials, restart, update macOS.
Unified OWASP MCP Top 10 scan — path or live tools/list, A–F grade, SARIF
Wraps any MCP server: identical write-tool calls run once, and every tool call is audit-logged.
Cited Australian tax answers from 34,500+ ATO documents, legislation and public rulings.
OWASP MCP10 context oversharing: session dumps, unscoped memory, shared context, prompt leaks
Odoo virtual employee via MCP: query, create, modify records, workflows, PDFs, and activities.
KVKK/GDPR-compliant LLM-to-database gateway: PII masking, RBAC, rate limiting, audit log
MCP server for one MySQL database: schema, read-only queries and guarded writes.
Radio directory from TuneIn RadioTime. No key required.
Find and fix drift between Supabase environments: schema, RLS, roles, auth, storage and more.
Complete Holded Invoice API integration with 72 MCP tools for invoices, contacts, products, and more
Probes vector-database endpoints for unauthenticated exposure of embeddings/RAG data
GuardBee MCP bridge to Agent Threat Rules (ATR) for runtime agent/MCP threat detection
Active jailbreak/extraction/obfuscation red-teaming for live LLM endpoints
Finds lethal-trifecta toxic flows in MCP tool catalogs: untrusted input, sensitive data, egress
Curated MCP tools from OpenAPI, websites, apps, Postman, cURL or SQL; your agent designs them.
Unknown author
Verified B2B contacts at named accounts, email verdicts, contract signals and drafted campaigns.
BrandPilot brands and design systems for coding agents: tokens, design context, repo rules.
Scans code for insecure LLM/AI integration: exposed keys, unsafe output, prompt injection
Predicts the DDL a dbt change will execute, before you run it. Reads files, not the warehouse.
Protein interaction networks from STRING DB. No key required.
Search the SwaggerHub API registry for public API definitions. No key required.