MCP servers that give coding agents real developer tooling: linters, package registries, test runners, language docs and local build commands. 13,944 servers in this category.
Lets AI agents run Python code against STAAD.Pro models via the OpenSTAAD API to define load cases, extract data, and set properties.
$https://github.com/BentleySystems/openstaad-mcp/releases/download/v1.3.0/openstaad-mcp.mcpb
Lets AI agents build a persistent knowledge graph of code, docs and policies, and gate decisions with signed verdicts.
$claude mcp add graqle -- uvx graqle
Enables AI agents to search, retrieve, store, and analyze DICOM images using DIMSE and DICOMweb protocols.
$claude mcp add dicom-agent-mcp -- uvx dicom-agent-mcp
Provides a shared memory and coordination layer for multiple AI agents across different CLIs and IDEs using a unified SQLite store.
$claude mcp add thread-keeper -- uvx threadkeeper
Connects coding agents to a live registry of reviewed engineering skills to discover, verify, and apply proven fixes for software failures.
$claude mcp add noosphere -- uvx noosphere-mcp
Refines and optimizes LLM prompts through adaptive questioning and multi-provider support for various AI backends.
$claude mcp add promptheus -- uvx promptheus
Performs static security scanning on MCP servers and agent skill files to detect vulnerabilities and toxic attack chains using OWASP AIVSS scoring.
$claude mcp add scanner -- uvx bawbel-scannerPerforms static security scanning on MCP servers and agent skill files to detect vulnerabilities and toxic attack chains using OWASP AIVSS scoring.
$claude mcp add bawbel-scanner -- uvx bawbel-scanner
Provides deterministic structural analysis and change control for AI agents to manage Python code modifications and prevent regressions.
$claude mcp add codeclone -- uvx codeclone
An agent runtime and Python SDK for building AI agent fleets with persistent knowledge-graph memory and effort-based model routing.
$claude mcp add aither-adk -- uvx aither-adk
Records approved project decisions and their reasons, then surfaces that reasoning to AI agents in later sessions.
$claude mcp add nauro -- uvx nauro
Verifies AI agent actions by auditing tool records to identify skipped tests, unverified changes, or unread documents.
$claude mcp add assurance -- uvx assurance-mcp
Indexes local chat transcripts from Cursor, Claude, and ChatGPT to provide BM25 search and memory for AI agents.
$claude mcp add chronicle-mcp -- uvx chronicle-mcp-server
Connect AI assistants to Bitbucket Cloud to manage repositories, pull requests, pipelines, and issues through natural language.
$claude mcp add bitbucket-mcp -- uvx bitbucket-mcp-py
Provides a cross-agent intelligence network that shares tool failure patterns and successful recovery actions to prevent redundant retries.
$claude mcp add failecho -- npx -y failecho-mcp
Provides a local-first shared memory system for multiple AI agents using Markdown files and git to compound knowledge through usage and validation.
$claude mcp add compound-memory -- uvx compound-memoryValidates email addresses, phone numbers, and postal addresses across 240+ countries via Byteplant APIs.
$claude mcp add byteplant-mcp -- uvx byteplant-mcp
Allows AI agents to create test inboxes and automatically block until an OTP or magic link arrives for application testing.
$claude mcp add mailsocket-mcp -- uvx mailsocket-mcp
Enables AI agents to triage issues, fix bugs, verify SARIF scanner reachability, and perform semantic code recall within a repository.
$claude mcp add codna-cli -- uvx codna
Lets an AI client build, chat with, and evaluate LLM agents and workflows that connect to MCP servers.