"pre-commit" matching MCP servers:

Enables validation of commit messages, branch names, author info, push safety, and repository state using commit-check rules, accessible as MCP tools.

Enables AI agents to coordinate atomic distributed transactions across a swarm through a prepare/vote phase, unanimous commit-or-abort consensus, quorum validation, and failure recovery. It also layers in vector-clock causal stamping, LWW CRDT reconciliation, and gossip dissemination so multi-node state converges deterministically without external dependencies.

A remote MCP server exposing 3 tools via Model Context Protocol: score_prompt (free, grades any LLM prompt A-F on 0-40 scale), optimize_prompt (returns optimized prompt + dimension breakdown, $0.025 USDC), and compare_models (Claude vs GPT-4o head-to-head, $1.25 USDC). Remote HTTP server at /api/mcp.

Pre-computed financial market intelligence for AI agents. Stocks, crypto, and ETFs.

AI code review against your team's own rules from your repository, before the pull request: two tools, review_changes and get_team_rules. Closed-source binary distributed via GitHub Releases; published in the official MCP Registry as dev.reviewgate/reviewgate.

MCP server that exposes pre-extracted facts about code behavior, design decisions, and assumptions to AI agents, saving time and tokens by avoiding direct source file reading.

ReportFlow MCP Server - PDF report generation for Claude and AI agents

Non-custodial memory MCP server with client-side encryption, enabling secure remember, recall, forget, and share operations with post-quantum security.

A gateway that connects MCP servers and REST APIs, allowing you to curate tools into groups and expose them as virtual MCP servers for agents.

Use 3,000+ pre-built cloud tools from Apify, known as Actors, to extract data from websites, e-commerce, social media, search engines, maps, and more

Stops your AI from re-introducing bugs, leaking provider keys, or weakening tests. Bug fixes become permanent regression guards; blocked mistakes become AI lessons the agent reads and learns from before its next edit.

Maango is the pre-flight check for AI agents on the web. Before an agent scrapes, summarises, trains on, or searches a site, it calls Maango and gets back whether the action is allowed for that domain, along with the reason and the policy signals that decided it.

Gives AI agents instant access to software architecture, dependencies, and impact analysis through pre-computed sgraph models, replacing dozens of grep/read cycles with a single tool call.

A meta-MCP server that aggregates authoritative web search and browser research tools, providing a unified interface with a cost-efficient fetch ladder for web research.

Hashlock Markets (hashlock.markets) — sealed-bid intent-based crypto trading protocol with HTLC atomic settlement. AI agents can create, commit, and validate trading intents on Ethereum, Bitcoin, and Sui. Canonical npm package: @hashlock-tech/mcp. Not the cryptographic hashlock primitive, not Hashlock Pty Ltd (hashlock.com).

MCP server for AI-agent governance using trust scoring, behavioral signals, and pre-flight action checks.

Universal MCP server that emits Context Passport records for AI agent decisions and actions. Drop into any MCP-compatible client to give your agent a commit/verify/replay/export toolset for verifiable, tamper-evident records.

Runs commands on machines you cannot SSH into by publishing steps to a transport the far side already reaches (git, file share, S3, relay), then reads back a log with every line timestamped in UTC. Seven tools cover send, status, logs, stall detection and a pre-flight check.

An MCP server that enables AI assistants to interact with Ansys CFX through PyCFX, supporting natural-language-assisted CFX-Pre, CFX Solver, and CFD-Post workflows for setup, execution, and postprocessing.

Enables any MCP client to look up CVE intelligence — severity summaries, filtered searches, and full per-CVE detail fusing NVD, MITRE-CNA pre-NVD, CISA KEV, EPSS, and GitHub GHSA data — alongside a Shodan-derived internet-exposure footprint showing how many internet-facing services run a version mapping to a given CVE. It is free, keyless, and read-only, and distinguishes verified zeros from unassessed or failed lookups.