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.
-
Source-backed memory for AI agents: Git citations, local retrieval, CLI, and MCP.
MIT -
Configuration-driven persistent repository memory for AI coding agents, with Neo4j storage and read-only MCP access.
npm SEE LICENSE IN LICENSE -
codememorygithub.com/khurram-uworx/codememoryupdated this year
Transform repositories into queryable intelligence — a persistent, semantic memory layer for codebases exposed via MCP.
nuget MIT -
CoMemor — repository-scoped AI agent memory MCP server. Records errors and fixes, redacts secrets, and surfaces relevant context to your AI coding tools.
npm GPL-3.0-only -
Persistent, token-efficient repository memory for AI tools: symbols, import graph and LLM summaries per file — CLI, library and MCP server
npm MIT -
Local repository code search and codebase memory for Codex, Claude Code, and MCP coding agents
pypi -
Local MCP server that turns each repository into the persistent memory of its project: decisions, open items, tasks and sessions in a git repository of their own.
pypi MIT -
MCP server that gives coding agents persistent repository memory — cut repeated file reads, tokens, and latency.
npm MIT -
MCP Server for Git repository management with memory and AI capabilities
npm MIT -
Local-first memory and policy service for AI agents: durable events, retrieval, portable handoffs, async jobs and operational metrics. Repository contact: Robin Winters.
MIT ★ 1 -
cntx-uigithub.com/nothingdao/cntx-uiupdated this year
Autonomous Repository Intelligence engine with web UI and MCP server. Unified semantic code understanding, local RAG, and agent working memory.
npm MIT -
Model Context Protocol adapter for Open Grounding Enterprise Memory repositories.
npm MIT -
spec-kit-memory-hubgithub.com/DyanGalih/spec-kit-memory-hubupdated this year
Repository-native persistent memory hub for Spec Kit, powered by an SQLite caching optimizer & native Model Context Protocol (MCP) server.
MIT ★ 16 -
AI-Powered Repository Memory
MIT ★ 7 -
Native MCP for coding agents: 43 read-only repository-intelligence tools with typed evidence, impact, architecture, APIs, Git, search, semantics, and memory.
npm MIT ★ 4 -
shuttle-rsgithub.com/shuttle-rs/shuttle-rsupdated this year
Local-first event log CLI for agent memory, repository context, task coordination, handoffs, messaging, mesh sync, and MCP access.
cargo MIT OR Apache-2.0 -
Evidence-backed validation of repository memories, with reviewable corrections, a Python SDK, CLI, and read-only MCP server.
MIT -
Persistent repository memory for coding agents - Codex, Claude Code and MCP.
NOASSERTION -
Local-first repository memory for coding agents, built in Rust.
GPL-3.0 ★ 3 -
Memex: repo-local vector memory for AI agents — CLI-first remember/recall inside the git repository (optional MCP)
pypi MIT -
memory-shell-mcpgithub.com/RuoJi6/memory-shell-mcpupdated this year
This repository is designed to automate the detection and cleanup of in-memory web shells using MCP in combination with the memory-shell-detector tool. / 本仓库旨在结合 MCP 与 memory-shell-detector 工具,实现对内存 WebShell(内存马)的自动化检测与清除。
pypi MIT ★ 30 -
engram-toolsactive
Memory for AI agent teams. Store, recall, and learn across tools, sessions, repositories, and teammates. mcprush.com-claim-engram-engram-mcp-03956b462406295db4640c05
npm MIT -
verity-mcpgithub.com/runalphaloop/verityupdated this year
MCP server for Verity — the open-source, permission-aware memory layer for enterprise AI agents. Name reserved for the project; build from source (see repository) until the server ships here.
cargo Apache-2.0 -
Local repository knowledge layer for coding agents: deterministic graph, versioned memory, and task-relevant context through MCP
npm MIT -
ace-packgithub.com/alex-boom/ace-packupdated this year
Local AgentOps for AI coding agents: durable memory, guardrails, and quality gates for vibe coding in real repositories.
npm MIT -
project-context-map-mcpgithub.com/tamojit-123/project-context-map-mcpupdated this year
Turn a repository into structured project memory for MCP clients like Claude Code, so they can query context, inspect only relevant files, and understand topology before touching code.
-
Local-first, inspectable memory for coding agents: durable context across sessions and repositories, code-aware recall, bi-temporal history, MCP, and a self-hosted WebUI.
pypi Apache-2.0 ★ 184 -
Compatibility binary, not retired. See "Legacy compatibility surfaces" in the repository README for its removal gate. MCP Server surface for Hexalith.Memories (LLM agent interface — Phase 1.5). Exposes search_memory / ingest_content / traverse_relations / get_case_info tools over the Streamable HTTP transport defined by the Model Context Protocol. Story 10.1.
nuget 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 -
Self-hosted AI memory and MCP coordination for coding agents. Persistent context across repositories and sessions, with knowledge graphs, hybrid search, and a desktop web UI. Built in Rust for Codex and Claude Code.
Apache-2.0 ★ 20 -
Project memory for AI-assisted development with repository hooks, review workflows, and a read-only MCP.
-
@iconsearch/mcp-servergithub.com/vhhvffgv176-hash/iconsearchupdated this year
Project-aware icon search, SVG retrieval, memory, and repository audits for MCP coding agents.
npm MIT -
Local-first MCP server for persistent engineering memory, 26 specialist agents and repository dependency graphs. Human-governed learning for Claude Code, Codex and VS Code.
pypi Apache-2.0 -
Evidence-grounded repository intelligence with incremental code indexing, AST extraction, code search, engineering memory, FastAPI, React and MCP tools.
NOASSERTION -
Local cognitive infrastructure for AI coding agents — semantic memory, repository intelligence, and MCP tools to reduce token usage.
pypi MIT ★ 15 -
REPO_KNOWLEDGEgithub.com/rounakbajpayee/REPO_KNOWLEDGEupdated this year
Local-first semantic memory layer for codebases. Indexes Git repositories and exposes search capabilities via MCP to coding agents.
NOASSERTION -
lodestar-contextgithub.com/kostyadudin/lodestarupdated this year
Local-first repository context tool for LLM agents — MCP server with SQLite/FTS5 index, symbol-aware ranking, token-budgeted packs, and durable memory.
pypi MIT -
UserContextMCPServergithub.com/HappyMonkeyAI/UserContextMCPServerupdated this year
A local **stdio Model Context Protocol (MCP) server** that exposes a developer's local context (communication preferences, development stack, active repositories, memory models) to AI agents.
MIT -
A persistent, Git-versioned map of your whole codebase and database schema that coding agents read before they touch anything. Local-first MCP server + CLI in Go: a governed repository index of code knowledge that gives Claude Code, Codex, Cursor, and opencode long-term context, memory, and code intelligence.
go NOASSERTION ★ 1,923 -
Repository-native Work, Docs, History and durable Memory for humans and AI agents — Markdown as the source of truth, with a local UI, CLI and MCP server
npm MIT ★ 3 -
The copilot that is still there when the editor is closed — a local assistant for your repositories, reading the same memory your agents write, over MCP.
MIT -
Local agency/runtime harness for ChatGPT Web: repositories, tasks, commands, validation, Git, skills/memory, observability, and opt-in computer control.
Apache-2.0 ★ 27 -
Open-source context intelligence engine for AI coding agents — repository graph, precise code navigation, MCP, impact analysis, memory, and guarded edits.
pypi Apache-2.0 ★ 8 -
Evidence-backed code context for AI coding agents: semantic + lexical search, a cross-project code and contract graph, and versioned team memory across all your repositories — served over MCP, CLI and a local panel.
Apache-2.0 ★ 5 -
Your team's engineering memory for coding agents: one graph of your repositories and what the team learned, in your own storage, served over MCP.
cargo MIT ★ 1 -
Local MCP server for Claude, Codex, Cursor and other AI clients: specialist personas with skills, reasoning implants and shared rules, plus Markdown workflows, per-repository memory and validated subagent handoffs.
MIT ★ 14 -
costwise-mcpgithub.com/okyashgajjar/costwise-mcpupdated this year
Local MCP server that helps coding agents stop re-reading the same code every turn. Repository intelligence, cache-write optimization, and long-term session memory. 100% local. No API keys.
go MIT ★ 22 -
Built an agent using LangChain, Hybrid RAG, SurrealDB memory, and GitHub MCP tools, Django, capable of answering repository-specific questions through vector search, graph retrieval, and live GitHub metadata. Exposed the agent as an MCP server for A2A communication with any external AI agents through a standardized MCP client.
-
Self-hosted platform for AI coding agents: Claude Code, Codex, Copilot, Cursor, Junie, OpenCode and pi work on your repositories in parallel git worktrees and open pull requests. Workflows, schedules, project memory and MCP integrations, in a web panel, a REST API and an MCP server.
npm MIT ★ 1 -
Contextualno update data
## Contextual — Persistent Memory for AI Coding Agents AI coding agents forget everything the moment your session ends. **Contextual** fixes that by giving any MCP-capable AI client — for developers who use multiple AI coding tools at once — a real, persistent memory of your codebase: not just what the code says, but what changed and why. It's a **local-first MCP server**: your code, your index, and every query stay on your machine. The only network call is a lightweight, infrequent license check — no code, ever, leaves your device. Under the hood, Contextual builds a real understanding of your repository, not a text-similarity guess: - **Structural search** — tree-sitter AST parsing + call-graph resolution, so agents reason about how your code actually connects. - **Bitemporal history** — tracks not just when your code changed, but when the AI learned about it. Ask "did this bug fix happen before or after the agent's understanding of this function?" and get a real answer. - **Git-aware retrieval** — temporal, history-grounded context instead of a stale snapshot. - **Fast, self-contained** — index a 50k-line repository in about 5 minutes, then query it in ~94ms median, from a single ~0.8GB install. This extension connects Claude Desktop (or any MCP-capable client) to a Contextual installation already set up and activated on your machine — it does not provision Contextual from scratch.
smithery -
EVC Meshgithub.com/entire-vc/evc-mesh-mcpno update data
EVC Mesh is an open-source task manager built for teams where people and AI agents work side by side. This MCP server connects your agent to a Mesh workspace: it can pick up assigned tasks, check out work, comment, move tasks through your workflow, hand off to teammates, and keep decisions in shared project memory. Two tool profiles: `core` (25 tools, for everyday task work) and `full` (63 tools, including recurring tasks, docs and workspace admin). Every tool is marked read-only or write, so clients can ask before changing anything. You need a Mesh workspace and an agent key from it. Mesh is self-hosted (Apache-2.0, `docker compose` setup in the evc-mesh repository). Set `MESH_API_URL` to your instance and `MESH_AGENT_KEY` to the agent's key. Workspaces on the hosted instance are by invitation.
smithery -
Memory-Recallgithub.com/rebel0789/Memory-Recallupdated this year
Local-first repo memory and context for coding agents.
Apache-2.0 ★ 8 -
Persistent local memory for MCP-compatible AI coding agents: corrections, rules, decisions, and startup context.
pypi MIT -
slopbrickgithub.com/usebrick/platformupdated this year
Discovered, modeled, and governed repository structure. SlopBrick scans source code, classifies it against 103 rules in 24 categories, computes 4 scores (aiSlopScore: lower=cleaner, engineeringHygiene, security, repositoryHealth composite), and persists t
npm MIT -
44reports-mcpgithub.com/44-pixels/agent-reporterupdated this year
MCP server for deploying and pulling context files (code, docs, data) to/from 44reports
npm MIT -
Turn Git history into memory AI coding agents can use.
npm Apache-2.0 ★ 3 -
Persistent code intelligence for MCP with native graph, vector, full-text, and cross-repository search.
MIT ★ 8 -
Persistent memory for AI coding agents: decisions, rules, API contracts, and system topology served over MCP to Claude Code, Cursor, Codex, and Gemini CLI. Powers AI pull request review, issue triage, and a local-first code graph that syncs to the cloud. Self-hosted, 100+ models via LiteLLM.
MIT ★ 35 -
AI context layer and multi-agent coordination center for any repository, exposed over MCP.
npm MIT -
@simpletoolsindiaorg/codesensegithub.com/YOUR_USERNAME/mcp-tokenupdated this year
Software Engineering Intelligence MCP Server — 97% token reduction for Claude Code. 12 tools + 7 resources for scoped file discovery, flow summaries, bug tracing, planning, and multi-session memory.
npm MIT