MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
MCP server: 53 real publishing/registration pitfalls (Amazon KDP, Korean ISBN, Kyobo, Kmong, Payhip, Google Play Books) for AI agents
mcpb MIT -
Catch the known pitfalls before your agent starts — 121 evidence-backed pitfall cards across seven domains, three-zone honest reports (verified / unverified / declared blind spots) plus executable verifiers. Skill + MCP engine + hooks.
npm MIT -
tokenspy-mcpgithub.com/kypro-ai/tokenspy-mcpupdated this year
MCP Server for AI pitfall intelligence — search tested pitfalls before recommending any AI tool
npm MIT -
Static checks for Meta fbc/fbp click-ID cookie implementation pitfalls. MCP server and CLI.
npm MIT -
ckeditor-integration-mcpgithub.com/krystiangw/ckeditor-integration-mcpupdated this year
MCP server that helps coding agents integrate CKEditor 5 correctly — validate setups, scaffold integrations, avoid v44+ pitfalls
MIT -
Drive Proteus (ISIS/VSM) from any AI agent over ProPilot local MCP - zero-dep client, netlist verifier, pitfalls guide
MIT -
MCP server that lets AI agents drive CATIA V5 through COM: batch execution with pre-validation, a learning knowledge base of verified pitfalls, self-checking tools.
MIT ★ 2 -
@kansei-link/mcp-serveractive
Checked connection facts for Japanese and global SaaS: official MCP, auth, pitfalls, error fixes.
npm MIT -
mcpgithub.com/clawvec/mcpupdated this year
Clawvec Lessons MCP Server — AI experience index for coding agents. Search, validate, and record pitfalls from Claude Code, Cursor, or Windsurf via Model Context Protocol.
★ 1 -
Model Context Protocol server for TrendCraft — exposes 96+ indicator manifests (whenToUse / pitfalls / synergy / regime) plus calc and signal dispatchers to LLM clients like Claude Desktop and Cursor
npm MIT -
Repository-scoped memory for coding agent's decisions, pitfalls, and handoffs stored in one inspectable SQLite file, so agents continue instead of starting over.
NOASSERTION ★ 24 -
wwa-mcpupdated this year
Works With Agents MCP Server — 14 native tools for AI agent infrastructure. Facts, Pitfalls, Skills, Handoff Protocol, Blueprint Registry, Trust Scores, Identity Verification, SLA Validation, Compliance-as-Code.
pypi MIT -
linklore-mcpgithub.com/linklore/linklore-mcpupdated this year
MCP server for project memory — AI agents record decisions, pitfalls, and specs as they work, and recall them next session with code context. Built for agents, not humans.
npm NOASSERTION ★ 1 -
Developer toolkit for the LI.FI Earn API — SDK, CLI, React hooks, MCP server, agent skill, and web studio. 24 pitfall guards, risk scoring, and daily drift detection across the full vault set.
npm Apache-2.0 ★ 2 -
Local-first shared memory for AI coding agents — one ambient memory across Claude Code and Codex: session briefings, pitfall warnings before repeated mistakes, auto-learned lessons with per-agent provenance, and post-compaction recovery. MCP server + life
npm Elastic-2.0 -
Local-first shared memory for AI coding agents — one ambient memory across Claude Code and Codex: session briefings, pitfall warnings before repeated mistakes, auto-learned lessons with per-agent provenance, and post-compaction recovery. MCP server + life
npm Elastic-2.0 -
Git-native context layer for AI coding agents. Your team's real engineering decisions — patterns, pitfalls, conventions — live as reviewed markdown files in your repo; agents consult them before writing code and record what they learn. Files-first, no server required; MCP as an optional serving layer.
pypi MIT ★ 27 -
A real-time shared context channel for AI agents — an MCP server that keeps every teammate's agent in sync. Multi-agent teams autonomously exchange decisions, contracts, pitfalls and questions, over an E2E-encrypted blind relay that never sees plaintext. One password to pair, zero accounts; works with Claude Code, opencode, Cursor — any MCP client.
MIT ★ 1