55Trust score 55 of 100, Fair
Any web page as a typed tool call, run in your own logged-in Chrome. Free to start; Pro adds more.
Registry
Loading the directory
Loading the directory
Windsurf stores MCP servers in mcp_config.json under the Codeium config directory. Windsurf 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_config.json. MCPpedia currently has 43265 published MCP servers have an install config for Windsurf. The highest trust scores right now are gitlab-mcp at 84, Repowise at 83, kordoc at 83. Open a server and copy the Windsurf tab, then fill in secrets yourself. MCPpedia never stores those values.
Windsurf stores MCP servers in mcp_config.json under the Codeium config directory.
mcp_config.json at the path for your OS.~/.codeium/windsurf/mcp_config.json~/.codeium/windsurf/mcp_config.json%USERPROFILE%\.codeium\windsurf\mcp_config.jsonEvery server page builds a ready-to-paste JSON config for Windsurf.
Published servers with an install config for Windsurf.
Any web page as a typed tool call, run in your own logged-in Chrome. Free to start; Pro adds more.
Extract a repo's contribution gates into machine-readable contribution-gates.json.
Local MCP proxy with a tamper-evident audit trail for GLP traceability.
Find and fix drift between Supabase environments: schema, RLS, roles, auth, storage and more.
OWASP MCP08 audit/telemetry gaps: missing tool-call logs, raw args in logs, disabled audit
Finds lethal-trifecta toxic flows in MCP tool catalogs: untrusted input, sensitive data, egress
Predicts the DDL a dbt change will execute, before you run it. Reads files, not the warehouse.
Finds transitive excessive agency across LangGraph/CrewAI/AutoGen orchestration graphs
OWASP MCP10 context oversharing: session dumps, unscoped memory, shared context, prompt leaks
Let a planning agent hand bounded language work to a local Ollama model.
Markdown linter, workspace-scoped stdio MCP server, and self-hosted text-only remote MCP server.
Tells your AI agent which vulnerabilities to fix first, using OSV.dev, FIRST EPSS, and CISA KEV.
Regulations.gov readiness, rulemaking dockets, documents, comments, and comment periods. 9 tools.
USAspending.gov contracts, grants, loans, subawards, recipients, agencies, and federal accounts.
Official Mexican public data for AI agents: Banxico rates, INEGI inflation, UMA and ISR tables.
Pay-per-call market news, CBR/MOEX/Rosstat data and Telegram tools; auto-pays USDC on Base via x402
KVKK/GDPR-compliant LLM-to-database gateway: PII masking, RBAC, rate limiting, audit log
MCP server to list, load, explain, and validate Agent Skills.
Sourcery security findings: MCP server, CLI, and fix-prompt builder over the Sourcery API.
Read Commonly pods and post as a Commonly agent you create, with a token from your Commonly account.
Shared local memory for coding agents: SQLite, semantic recall, linked entities, code navigation.
Multi-model rating for AI evaluation. Agreement is reliability, not validity. Maintenance mode.
A webhook inbox for agents: one call returns a live URL. Mock, verify, inspect and replay.
Generate production-ready Tableau workbooks (.twb / .twbx) from natural language and a CSV.