- Conduid
- Marketplace
- #compatibility
MCP servers tagged compatibility
13 live MCP servers tagged "compatibility", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with compatibility.
Skills Compat Manager
Cross-platform compatibility layer for AI agent skills — pre-flight dependency checks, MCP-native, works with Claude Code, Cursor, Codex CLI, OpenCode and more
ProtocolArc
Contract lab for agent protocol envelopes - versioned MCP/A2A message contracts, envelope validation, and compatibility diffs (compatible/forward/breaking). Python 3 stdlib + opti…
Crosscheck
Run real MCP clients against your server and diff their rendered tool surface against tools/list. Deterministic — no LLM calls.
Harnessfacts
Open compatibility test suite for coding agents. Evidence-backed tests for instructions, skills, MCP, Git and CI.
CompatSentinel
Catch Windows app compatibility regressions before your users do.
Vedic Astrology AI MCP Server
World's first Vedic Astrology MCP Server — connect Claude, ChatGPT, Cursor, or any AI to real Vedic astrology. Horoscope predictions, compatibility matching, numerology, planetary…
Synastry API
Synastry API for relationship astrology. Inter aspect analysis between two charts plus compatibility score. RoxyAPI working samples.
Mcpsense Proxy
Bridge legacy stateful MCP servers to the July 28 2026 stateless MCP spec
Uplift
Run legacy MCP stdio servers behind the 2026-07-28 protocol. Translates the removed initialize handshake, sessions, and server-initiated requests.
Legacy Compat Shim
ASGI shim fixing the MCP Python SDK 1.x id-correlation bug that breaks fallback for 2026-07-28-era clients
Codex Upwork MCP Bridge
Unofficial compatibility bridge for using Upwork MCP with OpenAI Codex and ChatGPT
Agent Plugins Doctor
Validate, diagnose, and safely fix Agent Plugins, Agent Skills, MCP configs, compatibility, and portability issues.
Tool Semantics
Behavioral compatibility testing for MCP tools and AI-agent interfaces know when a change breaks the agent, not just the schema.