MCP servers that give coding agents real developer tooling: linters, package registries, test runners, language docs and local build commands. 13.971 servers in dieser Kategorie.
Füge das GitHub Repo ein und wir listen ihn nach einem kurzen Review auf.
Server einreichen
Provides a model-agnostic control plane to govern agentic work through bounded missions, owner-gated actions, and deterministic drift checks.
$claude mcp add hai-mcp -- uvx hai-mcp
Provides deterministic PC hardware troubleshooting using real BIOS beep-code tables and ranked diagnostic steps to prevent LLM hallucinations.
$claude mcp add boot-doctor-mcp -- uvx boot-doctor-mcp
Indexes source code and Git history into a local SQLite database to provide task-relevant context and impact analysis for coding agents.
$claude mcp add agentramen -- uvx agentramen
Provides local long-term memory for Claude Code and other agents by storing and retrieving exact conversation history and command outputs.
$claude mcp add cogito-mem -- uvx cogito-mem
Enables coding agents to share memory, message each other live, and coordinate file access across different local or remote sessions.
$claude mcp add puenteo -- uvx puenteo
Enables AI clients to search and cross-reference data across Notion and Supabase through a single, safety-focused interface.
$claude mcp add nexus-mcp -- uvx nexus-mcp-notion-supabase
Protects Postgres databases from AI agents by requiring approval for risky SQL and providing one-command undo for updates and deletes.
$claude mcp add pgbrake -- uvx pgbrake
Provides persistent, SQLite-based full-text memory for AI assistants using ranked indexing instead of expensive vector embeddings.
$claude mcp add frugal-memory -- uvx frugal-memory
Provides measured spatial data and anatomical validation for posing first-person arms and rifles within Blender.
$claude mcp add poselab-mcp -- uvx poselab-mcp
Performs security scanning and semantic intent analysis for Model Context Protocol servers to identify suspicious tool descriptors and metadata.
$claude mcp add mcpsentinel -- uvx mcp-guardian-scan
Provides a local gateway to monitor, verify, and block unauthorized tool changes in Model Context Protocol servers.
$claude mcp add mcpgawk -- uvx mcpgawk
Provides Claude with a structured, durable project memory to record and retrieve design decisions, pipeline flows, and constraints across sessions.
$claude mcp add context-keeper -- uvx context-keeper-mcpAn AI assistant with hybrid RAG, a native context graph, and a full development workbench including terminal, git, and filesystem access.
$claude mcp add vectora -- uvx vectora-agent
Performs technical SEO and GEO audits by measuring site health, validating robots.txt, sitemaps, and generating structured data.
$claude mcp add mcp-seo-audit -- uvx atomno-mcp-seo-audit
Provides a local-first coordination bus for fleets of AI agents to manage presence, work claims, shared plans, and task status via a WebSocket hub.
$claude mcp add synapse-channel -- uvx synapse-channel
Provides a governed semantic layer that allows AI agents to query metrics and business rules with deterministic SQL and verifiable evidence.
$claude mcp add cosmos-semantic-platform -- uvx cosmos-semantic
Prevents AI agents from leaking private repository data to public repositories by enforcing flow guards, human approvals, and audit logs.
$claude mcp add repoward -- uvx repoward
Finds open source issues for beginners by ranking them with a success score based on repository health and maintainer responsiveness.
$claude mcp add gfi-scout -- uvx gfi-scout
Performs deterministic browser delivery checks for AI-generated web pages, PWAs, and H5 demos using Chromium, Firefox, or WebKit.
$claude mcp add qa -- uvx ego-webqa
Provides local hybrid keyword and vector search over markdown notes and code for long-term AI memory.
$claude mcp add claude-second-brain -- uvx vault-index