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.
Automates Godot project creation, script validation, and runtime inspection for AI agents through headless and live modes.
Reduces LLM token costs by slimming tool and MCP schemas through safe, validation-equivalent transformations and CI gates.
Provides a structured document format and MCP server for deterministic AI communication, schema validation, and token-efficient compression.
Lets AI assistants read, write, edit, move, and delete files and run git and GitHub operations inside a confined project directory.
Lets AI clients query multi-chain blockchain data such as balances, tokens, NFTs, contracts, and transactions via Blockscout APIs.
$claude mcp add --transport http mcp-server-48b174 https://mcp.blockscout.com/mcp
Provides AI agents with a persistent knowledge graph of organizational intelligence and a decision assurance gate to verify actions against policies.
$claude mcp add graqle-214465 -- uvx graqle
Enables AI clients to analyze PostgreSQL query performance, recommend indexes, monitor database health, and test hypothetical indexes using HypoPG.
$claude mcp add pgtuner-mcp -- uvx pgtuner-mcp
Evaluates pull request diffs for regression risks using a semantic rule engine to provide machine-readable audit results.
$claude mcp add diffsense -- uvx diffsenseLets an AI assistant browse FiftyOne computer vision datasets, run operators and plugins, and control the FiftyOne App UI.
$claude mcp add fiftyone-mcp-server -- uvx fiftyone-mcp-server
Audits Amazon catalog files and Seller Central listings for attribute, title, and bullet quality issues, with JSON output for agents.
$claude mcp add amazon-catalog-cli -- npx -y @bwb03/catalog-cli-pro
Provides safety and decision-making tools for coding agents, including command validation, pull request routing, and context management.
Lets an AI client manage local models, configure Msty Studio, and orchestrate hybrid workflows between local and cloud AI models.
Reduces token usage for Unity MCP by providing a compact facade that enables on-demand tool discovery and batched operations.
Analyzes git diffs and AST mutations to detect breaking changes, map caller blast radius, and identify documentation drift.
Allows AI clients to query Korean laws, judicial precedents, administrative rules, and local ordinances via a CLI or MCP server.
Capture and inspect HTTP requests, emails, and DNS lookups to test webhooks, debug API callbacks, and perform security testing.
$claude mcp add webhook-mcp-server -- uvx webhook-mcp-server
Enables AI agents to obfuscate Python projects, scan for obfuscation risks, generate configuration files, and reverse obfuscated stack traces.
$claude mcp add pyobfus-mcp -- uvx pyobfus-mcp
Delegates coding tasks to local models with a safety layer that verifies patches through static analysis and real test runs.
$claude mcp add local-coding-agent -- uvx local-coding-agent
Reduces AI agent token usage by wrapping terminal commands with local compression and providing clean summaries instead of noisy raw logs.
$claude mcp add sage -- uvx psycgod-sage
Provides build-aware semantic indexing for embedded C/C++ firmware to give AI agents precise context through libclang and compile_commands.json.
$claude mcp add fw-context-mcp -- uvx fw-context-mcp