MCP servers that give coding agents real developer tooling: linters, package registries, test runners, language docs and local build commands. 13,961 servers in this category.
Enforces engineering discipline for coding agents by managing preparation, tool installation, and independent review processes.
Allows an AI agent to review LaTeX papers via a rendered PDF while simultaneously editing the source code.
$claude mcp add tex-mcp-web -- uvx tex-mcp-web
Provides a modular Python ecosystem for multi-agent orchestration, graph RAG, cloud deployment, and personal AI infrastructure via MCP tools.
An open-source Databricks app that provides a coding agent with workspace context including Unity Catalog, SQL warehouses, notebooks, and jobs.
Performs build-time security scanning for MCP servers using static analysis, GPT semantic review, and Docker-isolated runtime probes.
A Claude Code plugin that intercepts and fixes shell commands and file operations to prevent errors and maintain file integrity.
Enables file transfers between remote MCP clients and servers using S3-compatible presigned URLs to avoid sending binary data through JSON-RPC.
Enforces project decisions and rejected paths by providing a runtime gate that checks agent actions against a local knowledge graph before files change.
Provides AI coding agents with a local Bayesian memory that learns from user feedback and project context to maintain persistent beliefs.
Manages FRP instances and proxy configurations through a Python CLI and local stdio MCP server for LLM-assisted maintenance.
Performs agentic AI code reviews on GitLab MRs and GitHub PRs by posting actionable findings as inline threads using your preferred LLM.
Enforces phase gates, scope constraints, and human approval for agentic coding sessions in Claude Code.
Records engineering work as structured threads to provide AI coding agents with context and decisions from previous sessions.
A deterministic long-term memory system for AI agents using Markdown files and a SQLite index to provide reliable retrieval without vector embeddings.
An MCP server and CLI that enables AI agents to read web content, triage GitHub Actions, perform HTML audits, and control browsers or Windows applications.
Maps codebases offline by generating HTML wikis and dependency maps that show how repositories, modules, and symbols interact.
Unifies conversation histories from multiple AI agents into a searchable, distilled, and reusable memory asset using a built-in RAG engine.
Verifies claims in a thesis against measurements to produce MATCH, DRIFT, or UNVERIFIABLE verdicts with a tamper-evident sealed registry.
Enables AI clients to develop, review, and manage Spring Boot applications through specialized skills, agents, and build coordination tools.
Lets ChatGPT inspect Codex Desktop projects and dispatch confirmed coding tasks to the local Codex CLI or app-server.