MCP servers that give coding agents real developer tooling: linters, package registries, test runners, language docs and local build commands. 13,953 servers in this category.
Audits academic citations for existence, metadata accuracy, and claim support by querying scholarly databases like OpenAlex and arXiv.
$claude mcp add citeguard -- uvx citationguard
Audits AI agent skills using static, semantic, adversarial, and supply-chain scanning to identify security risks and malicious intent.
$claude mcp add tar-engine -- uvx tar-engine
A secret broker that allows AI agents to resolve and inject secrets at the execution boundary without exposing raw values to the LLM context.
$claude mcp add portunus -- docker run -i --rm ghcr.io/mdostal/portunus:0.34.0
Finds and fixes first-person weapon bugs by measuring weapon poses through a custom probe and validating changes against a gate.
$claude mcp add weaponlab-mcp -- uvx weaponlab-mcp
Provides a persistent research workspace for AI agents to investigate sources, track evidence, and export cited reports.
$claude mcp add sibyl -- uvx sibyl-research
Generates WireMock stubs, contract tests, and chaos scenarios from OpenAPI specifications using LLM agents.
$claude mcp add api-shakedown -- uvx api-shakedown
Enables Claude Code to use cheap models like DeepSeek V4.1 Flash to review code for bugs, provide second opinions, and investigate project structures.
$claude mcp add deputy -- uvx deputy-cc
Lets an AI client calculate, compare, and recommend AI model costs across multiple providers and aggregators.
$claude mcp add aicost -- uvx aicost-cli
Analyzes Turkish text to detect AI patterns, enforce TDK spelling and punctuation rules, and adapt writing style to specific genres.
$claude mcp add yontu -- uvx yontu
A Git and CI MCP server designed to test verification proxies by providing a full protocol surface including tools, resources, and prompts.
$claude mcp add mcp -- uvx devmcp-server
Provides session memory for AI coding agents by recording decisions, dead ends, and verifiable claims to prevent context loss and stale information.
$claude mcp add cogsession -- uvx cogsession
Enables AI agents to write, implement, and verify code against structured, testable intent artifacts to prevent hallucinations.
$claude mcp add --transport http ivd https://mcp.ivdframework.dev/mcp
Enforces design systems and prevents AI-generated UI clichés by synthesizing briefs, injecting constraints, and auditing code for token compliance.
$claude mcp add handmade -- uvx handmade
Extracts representative log snippets and Python tracebacks using Drain3 clustering to reduce large logs for AI analysis.
$claude mcp add logdetective-mcp -- uvx logdetective-mcp
Provides a file-first, local-first memory layer for AI coding assistants using Markdown and YAML instead of a vector database.
$claude mcp add agentic-memory -- uvx memory-fabric
Compiles portable AI skill specifications into integration artifacts for various LLM providers, MCP hosts, and Chromium browsers.
$https://github.com/daubesonntag-dotcom/daube-agent-bridge/releases/download/v0.1.3/daube-agent-bridge-0.1.3.mcpb
Validates XML instances against SDC4 XSD schemas using two-tier error classification and schema-aware XML/JSON conversion.
$claude mcp add sdcvalidator -- uvx sdcvalidator
Enables AI agents to build, flash, monitor, and run hardware-in-the-loop tests for ESP-IDF projects on real ESP32 hardware.
$claude mcp add esp-idf-mcp -- uvx esp-idf-mcp
Automates Git branch management, version bumping, and changelog enforcement through configuration-driven release policies.
$claude mcp add repo-release-tools -- uvx repo-release-tools
Lets an AI client discover, search, and safety-scan x402 paid APIs, MCP servers, and A2A agents through an intent-based directory.
$claude mcp add agenttoolscollection -- uvx agent-tools-mcp