"A programming resource or code repository index" matching MCP servers:

Enables AI agents to interact with a Git-native organizational governance system, supporting proposal-validation workflows, decision-making, and audit trail management through 21 MCP tools over stdio transport.

Turns a Claude Code workspace into something you can converse with by voice or text, answering questions about each project's status, recent activity, and code, and recording decisions back into the repo. Deep questions run through a read-only Claude Code session, so answers stay grounded in the actual files.

Enables local Claude Code to interact with Snowflake, Asana, M365, GitHub, and Hive Mind with automatic response truncation to prevent memory overload.

MCP server for Redmine that enables interaction with issues, wiki pages, and time entries through natural language.

基于滴答清单官方API的本地MCP服务，通过自然语言管理待办事项、创建和查询任务，支持OAuth认证和高级筛选。

Connects Claude to Jobber to manage clients, jobs, invoices, quotes, and scheduling through natural language.

Enables any MCP-capable coding agent to gate code writing behind user-approved design checkpoints, asking for the user's own approach first and recording decisions, project maps, and progress in a local .vibe-wise/ folder. Code is only written once the user explicitly confirms an implementation checkpoint, with no account, backend, or telemetry required.

Enables Claude Code to interact with Azure DevOps Server on-premises (work items, pull requests, repositories) through secure, controlled, safe-by-default access with read-only mode and explicit write confirmations.

Enables AI assistants to manage Bitrix24 CRM entities, tasks, project kanban boards, and Scrum sprints through an incoming webhook, requiring explicit user confirmation for all write operations.

Project management and session memory for AI agents that provides 13 tools for tracking projects, tasks, and context during AI coding sessions.

Enables Claude to interact with Notion workspaces, including searching, reading, creating, and editing pages and databases, as well as managing comments and users.

Lets an agent query Linear by writing JavaScript that the server runs in a throwaway worker, exposing schema introspection and a single request helper so only the return value comes back. Runs read-only by default, refusing mutations before any request leaves the process unless explicitly enabled.

Enables Boneyard to call authenticated, stateless Streamable HTTP tools for searching tickets and adding ticket comments, with caller context, attribution, and bounded results.

Provides sub-millisecond access to organizational and engineering data by pre-materializing data into a read-only SQLite database. Enables agents to query people, teams, issues, features, and governance documents without upstream latency or auth.

Enables task management through natural language by providing create, list, and update operations with SQLite persistence, usable locally with Claude Code or remotely via SSE.

A shared, concurrency-safe ledger for LLM code audits. It enables multiple agents to collaboratively report, verify, and resolve bugs with deduplication and hallucination resistance.

Automates three core workflows for Sangfor Engineer: project all-in-one (Excel to guide to validation to report), equipment health check, and Obsidian wiki integration.

Enables task management through MCP tools, resources, and prompts, backed by a PostgreSQL database.

Provides AI agents with structured access to project conventions, technology stacks, and architectural patterns to ensure consistency across development teams.

A read-only Model Context Protocol server that connects MCP clients such as Claude Desktop, Claude Code, Cursor or VS Code to KanbanFlow, exposing the configured boards and the tasks assigned to a chosen person across all of them. It resolves board, column, swimlane, color, label and people ids to readable names, reports which boards or columns could not be fully loaded, and never modifies any board.