MCP servers that give coding agents real developer tooling: linters, package registries, test runners, language docs and local build commands. 13,951 servers in this category.
Build and deploy declarative AI pipelines, autonomous agents, and MCP servers using a single YAML configuration file.
Scrape Google search results using a real Chrome browser and residential proxies to provide clean JSON data for AI agents and SEO tools.
Provides persistent, searchable shared memory for AI coding agents across different clients and sessions using hybrid search and a typed-edge graph.
Provides a persistent, Mem0-compatible memory layer for AI agents using hybrid retrieval and LLM fact extraction.
$claude mcp add --transport http deepmem https://deepmem.dev/mcp
Lets an AI client analyze vibration signals to detect machine faults, assess ISO severity, and generate diagnostic reports.
Lets AI agents query Langfuse traces, sessions, exceptions, prompts, datasets, and metrics for debugging and observability.
$claude mcp add langfuse-mcp -- uvx langfuse-mcp
An audit toolkit that verifies AI-generated research quotes, citations, and PRISMA counts against source texts to prevent hallucinations.
Lets AI agents list, subscribe to, publish on and call ROS 2 topics, services and actions on a live robot via rclpy.
Verifies BibTeX bibliographic records against multiple scholarly sources and reports metadata consistency issues.
$claude mcp add bibverify -- uvx bibverify
Bridges Fabric's patterns, models, and REST API into MCP clients so AI tools can list and run Fabric prompts and configurations.
Extracts PDFs page-by-page with self-auditing multi-engine routing and certifies any extractor's output for silently dropped pages.
$claude mcp add pdfmux -- uvx pdfmux
Automatically generates confidence-scored knowledge graphs from mixed documents using an induced RDFS/OWL ontology.
Gives AI agents a durable memory layer to capture episodes, curate concepts, and recall context with temporal facts and semantic search.
Records AI coding sessions byte-exact and locally, lets an AI client search them with verifiable citations or abstain, and restore deleted sessions.
$claude mcp add brain-mcp -- uvx brain-mcp
Lets an AI client design, simulate, measure, and analyze SPICE circuits with LTspice and ngspice, including schematic editing and Monte Carlo sweeps.
Provides an open-source telephony API that enables AI agents to make and receive phone calls, send SMS, and navigate IVR menus via MCP or REST.
Enables AI assistants to perform AI-assisted development and project scaffolding using the Duck Python web framework.
$claude mcp add --transport http duck https://duckframework.com/mcp
Enables AI agents to inspect, control, and automate Minecraft gameplay for testing and developing mods via the Model Context Protocol.
$claude mcp add minecraft-mod-mcp -- npx -y minecraft-mod-mcp
Audits an MCP server and returns a 0–100 score with cited, fixable findings on protocol, tools, and security.
$claude mcp add mcpscore -- npx -y @mcp-box/mcpscore
Extracts structured content, hierarchies, and tables from large documents to allow AI clients to read only relevant sections without exceeding context limits.
$https://github.com/DocSlicer/DocSlicer/releases/download/v0.2.5/docslicer-0.2.5.mcpb