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.
-
coding-assistantgithub.com/Bessouat40/coding-assistantupdated this year
AI Coding Assistant powered by MCP server : it reads your code locally to provide truly context-aware help, explanations, and suggestions directly related to your files. Code smarter, locally or using external API..
MIT ★ 7 -
Selvedgeno update data
**Persistent decision memory for AI coding agents.** Selvedge records why code changed, which approaches were rejected, and when decisions deserve another look, so future sessions can retrieve that context before editing. Query a function, database column, API route or dependency instead of reconstructing its history from an old conversation. Claude Code, Codex, Cursor, Copilot, Gemini CLI and Windsurf can connect through MCP. The CLI works independently. Decisions live in a local SQLite store, with no required hosted account and no LLM in the core storage or retrieval path. A saved explanation is testimony supplied by a person or agent. Selvedge does not extract hidden model reasoning, verify that an explanation is true, or guarantee that an agent will consult it. [Compatibility and capabilities](https://selvedge.sh/reference/compatibility/) · [56-second technical demo](https://youtu.be/wXoA9htThAM)
smithery -
The Code Review Assistant is a simple multi-agent system built using the Model Context Protocol (MCP) and LangChain. Its purpose is to provide automated, preliminary feedback on code snippets, including syntax checking, code explanation, and improvement suggestions. It can be integrated with MCP-compatible clients like Cursor IDE or Claude for Desk
★ 5 -
CodeBraingithub.com/Tschonsen/CodeBrainupdated this year
An MCP server that offloads bulk work from Claude Code to a local LLM (Qwen2.5-Coder 14B via Ollama). Claude stays the reasoner; the local model takes the bulk drafting, polishing, and explanation work to free up rate limits and context budget.
MIT ★ 1 -
@j0hanz/code-assistantgithub.com/j0hanz/code-assistantupdated this year
Gemini-powered MCP server for code analysis.
npm MIT -
@j0hanz/code-lens-mcpgithub.com/j0hanz/code-lensupdated this year
Gemini-powered MCP server for code analysis.
npm MIT -
code-lensgithub.com/j0hanz/code-lensupdated this year
Gemini-powered MCP server for code analysis.
npm -
@frappe-inspector/mcpupdated this year
Local MCP server for Frappe-aware security scans, explanations and remediation guidance.
npm SEE LICENSE IN LICENSE -
MCP server that lets Claude explain ML model predictions with SHAP: feature importance, per-prediction explanations, what-if analysis and plots. Read-only and works with any joblib model.
-
Use this free claude extension to search and research Hadith, including isnād, Takhrīj, commentaries (Sharḥ & explanations), scholarly grading, and much more — in both Arabic and English, using the Dorar.net library.
MIT ★ 8 -
MCP servers for everyday development and security checks: OSV vulnerability lookup, security header grading, JWT decoding and verification, regex testing with ReDoS detection, cron explanation, JSON Schema validation, OpenAPI and Dockerfile linting, read-only git insights and llms.txt generation. TypeScript, stdio, zod-validated, no telemetry.
MIT ★ 1