- Conduid
- Marketplace
- #coding-agents
MCP servers tagged coding-agents
77 live MCP servers tagged "coding-agents", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with coding-agents.
Pocket Disasm
Multi-session IDALib MCP router for coding agents. Analyze multiple binaries in parallel with IDA-compatible reverse engineering tools.
Tasksync MCP Http
TaskSync MCP server — persistent daemon feedback loop for AI coding agents
Agents Markdown MCP Server
MCP server exposing agents-markdown tools via Model Context Protocol
Seer
Show AI coding agents what their edit will touch before they make it.
Aiagentsbay
Memory OS for AI coding agents. Local-first by default, with seamless cloud sync once you sign up. Persistent memory, projects, and teams for Claude Code, Codex, Cursor, and any M…
Jambavan
Local-first MCP memory and code intelligence that helps coding agents recall repo context, decisions, failures, and review impact.
Chub
Agent-agnostic context, tracking, and cost analytics for AI-assisted development. Curated docs · Session tracking · Cost analytics · Team knowledge — all git-native
Continuous Improvement
Install 7-law discipline + instinct-based learning (Mulahazah) into Claude Code — hooks observe every session, instincts strengthen or decay with confidence scoring
Graphrag Code
🕸️ Code knowledge graph for Claude Code & AI coding agents — index TypeScript, NestJS, React into Neo4j and query architecture in Cypher
Thezenmonster/agentmem
Governed memory for coding agents with trust lifecycle (hypothesis → active → validated → deprecated), conflict detection, staleness tracking, and health scoring. SQLite + FTS5, z…
TheStack-ai/waypath
aware recall via FTS5 and RRF, and governed memory with explicit promote and review gates. Ships Codex and Claude Code host shims and a native MCP server.
Cognitive Project Layer
Local-first context engine for coding agents: project skeleton, symbols, references, graph, retrieval, confidence, MCP, CLI, and HTTP API.
Agent In Sync
The knowledge base AI coding agents share. Submit, search, and reuse battle-tested solutions across teams. Self-hosted, MCP-native, AGPL-3.0.
Atelier
Open-source context runtime and governance layer for coding agents. MCP server + Python SDK (Anthropic, LangChain, OpenAI Agents, Google ADK) with shared procedures, failure rescu…
Code Reason
MCP server that gives AI agents program-analysis primitives like data flow, call graphs, taint analysis so they reason from deterministic data instead of grep-and-guess."
Glyphtrail
Local code intelligence graph for AI coding agents: Tree-sitter static analysis, structural code search, dependency impact, blast-radius analysis, CLI and MCP server.
Tryoz
One-line Oz MCP setup for coding agents
Agent Harness
Node.js TypeScript CLI for discovering, staging, activating, and wiring reusable AI-agent assets across VS Code/Copilot, OpenCode, Cursor, Zed, Claude Code, and Pi.
Agentic Engineering Framework
Governance framework for AI coding agents — enforces task traceability, structural gates, session continuity, and audit trails for Claude Code, Cursor, and Copilot.
Tessera
Local semantic code graph + MCP server for AI coding agents (Rust, Tree-sitter, SQLite)
Ctx Forge
Generate project-specific, self-verified context tools for AI coding agents. The skill audits your repo, generates a ctx CLI (+MCP), and proves it against golden questions before…
Elowen
Self-hosted personal AI agent that chats, acts, automates, and extends across CLI, web, Discord, and WhatsApp.
Agent Chassis
Contract-first orchestration for long-running coding agents: scoped work records, local dispatch, review evidence, and enforcement provenance.
Idesense
MCP server for JetBrains IDEs - gives coding agents the IDE's own indexing, navigation & refactoring (IntelliJ IDEA, PyCharm, WebStorm, GoLand, PhpStorm, RustRover, and more).
nomadop/session-watcher
no metric ever enters the model's context.
Qarinah
Qarinah is evidence-linked project memory for coding agents - compact enough to save context, inspectable enough to trust.
Ensemblr
macOS orchestrator for Pi and Claude Code. Every stream of work gets its own git worktree, and an agent can drive the app itself — spawn sub-agents, delegate, integrate.