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.
Enables coding agents to perform deterministic root-cause analysis and verify the completeness of bug fixes using git history.
$claude mcp add culprit -- uvx culprit
Tracks LLM API spending across multiple providers and exposes cost data to coding agents via MCP or a CLI.
$claude mcp add llm-usage-mcp -- uvx llm-usage-mcp
Coordinates multiple AI coding agents in shared rooms with task claiming, file locking, and cross-vendor commit reviews.
$claude mcp add quorus -- uvx quorus-ai
Provides an AI decision layer that delivers typed answers with provably calibrated confidence scores for agents.
$claude mcp add poordjaevin -- uvx poordjaevin
An event-sourced ticket tracker and Jira reconciler that uses a git-backed event log to coordinate parallel AI agents.
$claude mcp add rebar -- uvx nava-rebar
Lets an AI client execute arbitrary Python code and manage pipelines within a ParaView session via a TCP bridge plugin.
$claude mcp add paraview-mcp -- uvx paraview-mcp-server
Provides a read-only visualization layer for Cortex memory, sessions, traces, and codebase graphs through six interactive viewing angles.
$claude mcp add cortex-viz -- uvx hypermnesia-mcp-viz
Lets an AI agent manage Google Colab runtimes, execute code, work with notebooks, and manage files and long-running background jobs.
$claude mcp add colab-mcp -- uvx colab-cli-mcp
An AI coding agent for the terminal that records all actions in a tamper-evident, hash-chained causal ledger for verifiable auditing.
$claude mcp add korgex -- uvx korgex
Provides AI clients with persistent, version-tracked knowledge vaults for project documentation, specifications, and architecture decisions.
$claude mcp add loredocs -- uvx loredocs
Reads and normalizes session history from multiple coding agents to allow AI clients to audit plans, intents, and tool usage.
$claude mcp add ai-r -- uvx agent-session-reader
Provides shared memory for coding agents to track projects, reusable code, sessions, and commits across multiple machines.
$claude mcp add codemem -- uvx codemem-mcp
An agentic workflow kit that provides a 25-agent squad, persistent memory, and parallel task dispatching for AI coding assistants.
$claude mcp add graphyloop -- npx -y graphyloopRecords Claude Code sessions as plain markdown files and provides FTS5-powered search and retrieval for AI clients.
$claude mcp add mneme -- npx -y mneme-mcp-server
Provides vault-native, markdown-based memory for Claude Code and MCP clients using SQLite FTS5 for searchable session history.
$claude mcp add mneme -- npx -y mneme-mcp-server
Enables an AI client to control Digilent WaveForms instruments including oscilloscopes, arbitrary waveform generators, and logic analyzers.
$claude mcp add dwf-mcp-server -- docker run -i --rm ghcr.io/kenosinc/dwf-mcp-server:0.2.1
Enables AI agents to perform security configuration validation, documentation searches, and live threat detection within the Guard ecosystem.
$claude mcp add guard-core-mcp -- uvx guard-core-mcp
Delegates coding tasks to Claude Code, Codex, or Antigravity agents from any MCP client.
$claude mcp add nexus-mcp -- uvx nexus-mcp
Provides static analysis for Python projects to trace call paths, control flow, and change impact for coding agents.
$claude mcp add codecanvas -- uvx codecanvas-mcp
Converts structured data like JSON, CSV, and Parquet into the TOON format to reduce LLM token usage based on estimated savings.
$claude mcp add datoon -- uvx datoon